{"as_of":"2026-08-09T16:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:438b9fc37235283824bb5140d39f9e75b8ad3f317142a81fdfe05848f4ff6cfb","coverage":[{"denominator":95,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":95,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:56:03.866876Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.09562/citation-record","integrity":"/paper/2507.09562/integrity","json":"/paper/2507.09562/citation-record.json","paper":"/paper/2507.09562"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.532961Z","title":"BioSAM: Generating SAM Prompts From Superpixel Graph for Biological In- stance Segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.532961Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f88e56ef9b61e8641d3d14e03aa48ee26f1f5ce35d1c60c9e9ba406d4a86c40a","observation_id":"15ad3b6f-bcf1-40fd-ba1a-3cfe858c8377","resolution":{"observed_at":"2026-08-06T17:56:03.532961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2025.35361","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:05.214136Z","title":"Personalizing Vision-Language Models With Hybrid Prompts for Zero-Shot Anomaly Detection","venue":null,"work_id":"5ce212fd-abe2-4991-b08c-4fbcdbe632cd","year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.537564Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:1b9f7a131a031aa921792c9a1e1dbc15d7870c51add176a9126dc82d6c2e8599","observation_id":"436c2634-dac8-4417-a980-aaf8aac02935","resolution":{"observed_at":"2026-08-06T17:56:05.220660Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.542413Z","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.542413Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:37039243d946094d5fca7c0edc9cb1e1bb8bf9d06df2a11ef1b28549db9df921","observation_id":"21cc5df1-8f53-48ed-b5b3-228a34ffca1a","resolution":{"observed_at":"2026-08-06T17:56:03.542413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07183","last_updated":"2024-03-20T06:42:18Z","snapshot_observed_at":"2026-08-09T04:05:08.326425Z","submitted_at":"2023-10-11T04:14:59Z","title":"SAM-OCTA: Prompting Segment-Anything for OCTA Image Segmentation","version":2},"cited_work":{"arxiv_id":"2310.07183","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.07183","snapshot_observed_at":"2026-08-06T17:56:05.136796Z","title":"SAM-OCTA: Prompting Segment-Anything for OCTA Image Segmentation","venue":"cs.LG","work_id":"5799bced-f280-4d7f-8516-ab389e7f6f5f","year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.545980Z"},"links":{"cited_paper":"/paper/2310.07183","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:0a72ef251a23318cdb95b5a68a6c00cdb6f6efed546c44da5cfe4eba9736fb29","observation_id":"d37862e8-26e5-4aac-b56c-7de7f0e5a73e","resolution":{"observed_at":"2026-08-06T17:56:05.140111Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.550396Z","title":"Segmentation by registration-enabled SAM prompt engineering using five reference images","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.550396Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:e9fa495fad06dd1dffc4e126c5b93752818ef631122ffc581b391f2b2bf3698f","observation_id":"14690656-2672-4117-ae62-d01f27879b63","resolution":{"observed_at":"2026-08-06T17:56:03.550396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.00290","last_updated":"2023-08-29T03:31:58Z","snapshot_observed_at":"2026-07-06T15:49:11.121894Z","submitted_at":"2023-07-01T10:12:46Z","title":"All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning","version":2},"cited_work":{"arxiv_id":"2307.00290","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.00290","snapshot_observed_at":"2026-08-06T17:56:05.108061Z","title":"All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning","venue":"cs.CV","work_id":"d2cd2a2f-c83c-47f6-a187-60d191849253","year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.558357Z"},"links":{"cited_paper":"/paper/2307.00290","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:0175e79106779dbbfc2c0ad04678bc31475f5b2042e4db4aca0240e30f8400ee","observation_id":"7ea8613b-864a-461f-86bc-a2e50a123db4","resolution":{"observed_at":"2026-08-06T17:56:05.112400Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01187","last_updated":"2024-03-19T12:27:37Z","snapshot_observed_at":"2026-07-06T15:49:47.586513Z","submitted_at":"2023-07-03T17:52:44Z","title":"SAMAug: Point Prompt Augmentation for Segment Anything Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01187","snapshot_observed_at":"2026-08-06T17:56:03.562790Z","title":"SAMAug: Point Prompt Augmenta- tion for Segment Anything Model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.562790Z"},"links":{"cited_paper":"/paper/2307.01187","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:3cda09c225f59e0d387d242c8f2b669bc29e13ffab18dcfa528bc8537ff1023a","observation_id":"4595d20f-a178-4441-b39f-9a356ffca704","resolution":{"observed_at":"2026-08-06T17:56:03.562790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11998","last_updated":"2024-04-18T08:46:12Z","snapshot_observed_at":"2026-07-06T18:02:02.384288Z","submitted_at":"2024-04-18T08:46:12Z","title":"Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation","version":1},"cited_work":{"arxiv_id":"2404.11998","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.11998","snapshot_observed_at":"2026-08-06T17:56:05.083820Z","title":"Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation","venue":"cs.CV","work_id":"58d223ee-889b-42ba-a651-a303c880831f","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.567186Z"},"links":{"cited_paper":"/paper/2404.11998","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:a4f391318368997fb603a263a0126928a2f120fdc495546fbcc5405fdd036793","observation_id":"a731a88c-e06f-42f2-b7fa-5bdd12cb1df7","resolution":{"observed_at":"2026-08-06T17:56:05.087584Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04973","last_updated":"2023-07-11T02:27:45Z","snapshot_observed_at":"2026-07-06T15:52:24.803146Z","submitted_at":"2023-07-11T02:27:45Z","title":"SAM-U: Multi-box prompts triggered uncertainty estimation for reliable SAM in medical image","version":1},"cited_work":{"arxiv_id":"2307.04973","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.04973","snapshot_observed_at":"2026-08-06T17:56:05.069760Z","title":"SAM-U: Multi-box prompts triggered uncertainty estimation for reliable SAM in medical image","venue":"cs.CV","work_id":"ef79dec3-a384-439f-849c-e4d829a3f3ac","year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.571150Z"},"links":{"cited_paper":"/paper/2307.04973","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:79f3418cc88845e6a406fc34f78f07afe0120592007ab7932b08e7de980add0e","observation_id":"84889892-16e0-4231-a0d6-2c02d2d28ebe","resolution":{"observed_at":"2026-08-06T17:56:05.073852Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06825","last_updated":"2024-10-09T12:37:12Z","snapshot_observed_at":"2026-07-06T19:30:21.486298Z","submitted_at":"2024-10-09T12:37:12Z","title":"K-SAM: A Prompting Method Using Pretrained U-Net to Improve Zero Shot Performance of SAM on Lung Segmentation in CXR Images","version":1},"cited_work":{"arxiv_id":"2410.06825","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.06825","snapshot_observed_at":"2026-08-06T17:56:05.056170Z","title":"K-SAM: A Prompting Method Using Pretrained U-Net to Improve Zero Shot Performance of SAM on Lung Segmentation in CXR Images","venue":"eess.IV","work_id":"a1bc02f7-f356-45bf-b9f7-0b1def7a1853","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.574930Z"},"links":{"cited_paper":"/paper/2410.06825","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:1f3ef0ec6f2b93d5326e6067a3b33de7426cfff0c8c47dc7dfc2a9ebfe3f34e3","observation_id":"6089519b-2b26-4acb-a0c0-fea62ce03576","resolution":{"observed_at":"2026-08-06T17:56:05.059830Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.20293","last_updated":"2024-09-30T13:53:01Z","snapshot_observed_at":"2026-07-06T19:24:35.007698Z","submitted_at":"2024-09-30T13:53:01Z","title":"Automating MedSAM by Learning Prompts with Weak Few-Shot Supervision","version":1},"cited_work":{"arxiv_id":"2409.20293","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.20293","snapshot_observed_at":"2026-08-06T17:56:05.042273Z","title":"Automating MedSAM by Learning Prompts with Weak Few-Shot Supervision","venue":"cs.CV","work_id":"9acd5d82-80fa-46e2-a345-66a95d146dc5","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.578785Z"},"links":{"cited_paper":"/paper/2409.20293","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:eb022dcda9cfe8855af5e33a3dbe17890c2ae89bc143d2661f56181cdce2e0e1","observation_id":"15997316-3d74-47b0-b62e-c9247c205b2d","resolution":{"observed_at":"2026-08-06T17:56:05.045944Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.07172","last_updated":"2024-09-11T10:35:42Z","snapshot_observed_at":"2026-07-06T19:13:42.074230Z","submitted_at":"2024-09-11T10:35:42Z","title":"Swin-LiteMedSAM: A Lightweight Box-Based Segment Anything Model for Large-Scale Medical Image Datasets","version":1},"cited_work":{"arxiv_id":"2409.07172","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.07172","snapshot_observed_at":"2026-08-06T17:56:05.027643Z","title":"Swin-LiteMedSAM: A Lightweight Box-Based Segment Anything Model for Large-Scale Medical Image Datasets","venue":"cs.CV","work_id":"490ec65c-b3e7-403d-a2d1-3992ae127319","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.582093Z"},"links":{"cited_paper":"/paper/2409.07172","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:13d3ade1ff4197bffa19451a76173049b375dc8f748e92625be8b157a36560e4","observation_id":"d9b587d8-d065-4da3-8b59-306c29690b89","resolution":{"observed_at":"2026-08-06T17:56:05.031591Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.585220Z","title":"Lite Class-Prompt Tiny-VIT for Multi-modality Medical Image Segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.585220Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7c4991ebc89bf1e3b77d095c034a4d14cf91bacdecbe5db1cc54ac8357cc0f54","observation_id":"12a1a84e-2992-47d4-8179-b14f251ea585","resolution":{"observed_at":"2026-08-06T17:56:03.585220Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.588317Z","title":"APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.588317Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:91c068d1b1217f53511772337133cc77c6b442f438d6e3e9a8d73d8dc1a049d4","observation_id":"e4d0af7c-3cd0-422a-b0ca-d208cf8c9bec","resolution":{"observed_at":"2026-08-06T17:56:03.588317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.594919Z","title":"Relax Image-Specific Prompt Require- ment in SAM: A Single Generic Prompt for Segment- ing Camouflaged Objects","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.594919Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:9cac6ec0ff011260d7cd80305e8483b358b86e4e0a740810cb412f06f2d03a3c","observation_id":"567284f3-253c-420a-9727-cb72e63bd824","resolution":{"observed_at":"2026-08-06T17:56:03.594919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08372","last_updated":"2024-06-13T03:10:17Z","snapshot_observed_at":"2026-08-09T15:27:45.137377Z","submitted_at":"2024-06-12T16:20:58Z","title":"APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"2406.08372","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.08372","snapshot_observed_at":"2026-08-06T17:56:05.011348Z","title":"APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation","venue":"cs.CV","work_id":"38e282fb-b075-4645-a8f4-76c0eae79f07","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.591406Z"},"links":{"cited_paper":"/paper/2406.08372","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:65b7e9100c9e753bff9b509076f6a58231779248c2f06281747234e1e7890834","observation_id":"4108d9f1-12bb-41ec-bcd1-7a9a68f854fa","resolution":{"observed_at":"2026-08-06T17:56:05.015659Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06817","last_updated":"2025-04-16T03:40:29Z","snapshot_observed_at":"2026-08-09T10:50:02.569952Z","submitted_at":"2025-02-05T03:08:17Z","title":"Diffusion-empowered AutoPrompt MedSAM","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06817","snapshot_observed_at":"2026-08-06T17:56:03.602547Z","title":"Diffusion-empowered AutoPrompt MedSAM","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.602547Z"},"links":{"cited_paper":"/paper/2502.06817","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:e5978d6009df0c1d1ce9322395cecd679e73626dc9b86d4db2303dfb905cb006","observation_id":"a04d7fa8-bb61-4ed6-8f56-1259d326a78a","resolution":{"observed_at":"2026-08-06T17:56:03.602547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04651","last_updated":"2024-01-09T16:24:25Z","snapshot_observed_at":"2026-08-04T14:50:11.565250Z","submitted_at":"2024-01-09T16:24:25Z","title":"Learning to Prompt Segment Anything Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04651","snapshot_observed_at":"2026-08-06T17:56:03.598319Z","title":"Learning to Prompt Segment Anything Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.598319Z"},"links":{"cited_paper":"/paper/2401.04651","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:2107b18b24d6a4078aeffdfd38f2964ea34989ef7d94ed3e516e3435b6e6e92f","observation_id":"fcaae867-d249-48a2-99f8-088839477017","resolution":{"observed_at":"2026-08-06T17:56:03.598319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21284","last_updated":"2024-07-31T02:16:28Z","snapshot_observed_at":"2026-07-06T18:54:49.923926Z","submitted_at":"2024-07-31T02:16:28Z","title":"Robust Box Prompt based SAM for Medical Image Segmentation","version":1},"cited_work":{"arxiv_id":"2407.21284","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.21284","snapshot_observed_at":"2026-08-06T17:56:04.978984Z","title":"Robust Box Prompt based SAM for Medical Image Segmentation","venue":"cs.CV","work_id":"cf0d6c9f-47cf-45b5-8c12-57aa84e682cf","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.610184Z"},"links":{"cited_paper":"/paper/2407.21284","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:c07d1a52811a1732211afe847818cf82ddd96e1347ecc1fd0054e404f47f5177","observation_id":"c2903221-8b7a-405f-abc0-1c8b44a12666","resolution":{"observed_at":"2026-08-06T17:56:04.982942Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.606107Z","title":"Optimizing Efficiency and Effec- tiveness in Sequential Prompt Strategy for SAM us- ing Reinforcement Learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.606107Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:94057a4d4a5d358db0aa440635702605e4cf1439b8750c0f19a756e7815726cc","observation_id":"cd32f2aa-e2a2-4c26-acec-61f41f27ba2e","resolution":{"observed_at":"2026-08-06T17:56:03.606107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12781","last_updated":"2025-03-17T03:33:36Z","snapshot_observed_at":"2026-08-08T11:36:26.286106Z","submitted_at":"2025-03-17T03:33:36Z","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.12781","snapshot_observed_at":"2026-08-06T17:56:03.617338Z","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.617338Z"},"links":{"cited_paper":"/paper/2503.12781","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:035b73b332410bf8ea17f41a679fd7a0e4de462e494d000c0290fc080c4fcf45","observation_id":"289f5e13-0aa5-4ce2-9648-8522fff6928f","resolution":{"observed_at":"2026-08-06T17:56:03.617338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15759","last_updated":"2024-10-14T14:41:52Z","snapshot_observed_at":"2026-07-06T17:34:53.153463Z","submitted_at":"2024-02-24T08:10:54Z","title":"TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation","version":2},"cited_work":{"arxiv_id":"2402.15759","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.15759","snapshot_observed_at":"2026-08-06T17:56:04.964082Z","title":"TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation","venue":"cs.CV","work_id":"38949b45-64ce-4239-8420-834b8495612d","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.613836Z"},"links":{"cited_paper":"/paper/2402.15759","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:454f0a5687d6286f600e93db80e34994b9a4d93320d3df799b8ca24b8568054d","observation_id":"b112e6ad-4eaf-4e5b-86ad-89e480845df2","resolution":{"observed_at":"2026-08-06T17:56:04.967828Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.02643","last_updated":"2023-04-05T17:59:46Z","snapshot_observed_at":"2026-08-08T05:14:59.435033Z","submitted_at":"2023-04-05T17:59:46Z","title":"Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.02643","snapshot_observed_at":"2026-08-06T17:56:03.625174Z","title":"Segment Anything","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.625174Z"},"links":{"cited_paper":"/paper/2304.02643","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:d88cfceca72366982050abd384b68bc63a8340c5d114947d4db759e11e62342b","observation_id":"ade55baa-af27-45b6-85dd-1fcaa6b0f58d","resolution":{"observed_at":"2026-08-06T17:56:03.625174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.621306Z","title":"Ul- tralytics YOLOv8","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.621306Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7287a3e3721f5be7acc0fd3a02f57c4a9b1dc77b0123f29463f0f6aa087f0781","observation_id":"3735bddb-bff8-4e63-b979-5b2c9c7c4868","resolution":{"observed_at":"2026-08-06T17:56:03.621306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.03857","last_updated":"2022-06-17T10:32:21Z","snapshot_observed_at":"2026-07-06T12:16:15.735863Z","submitted_at":"2021-12-07T17:47:50Z","title":"Grounded Language-Image Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.03857","snapshot_observed_at":"2026-08-06T17:56:03.635888Z","title":"Grounded Language-Image Pre-training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.635888Z"},"links":{"cited_paper":"/paper/2112.03857","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:959a9b999cf9ed7d65e0a8f3a7681c3ee4464cfd985305a2a8ffe04051c6afe5","observation_id":"88b9d180-4932-4cf0-aa7f-acb343543d6e","resolution":{"observed_at":"2026-08-06T17:56:03.635888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.628800Z","title":"AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.628800Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f27e9c610b47157d198a2132a7cd63f0646f6cb7934b3be38bb035fdc4fc1be9","observation_id":"32749c5c-320b-4e7d-af05-98f4bbffe3cb","resolution":{"observed_at":"2026-08-06T17:56:03.628800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05653","last_updated":"2024-09-16T09:10:00Z","snapshot_observed_at":"2026-07-06T15:14:44.015806Z","submitted_at":"2023-04-12T07:16:55Z","title":"A Closer Look at the Explainability of Contrastive Language-Image Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05653","snapshot_observed_at":"2026-08-06T17:56:03.642271Z","title":"A Closer Look at the Explainability of Con- trastive Language-Image Pre-training","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.642271Z"},"links":{"cited_paper":"/paper/2304.05653","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:c51b3753bee827b3b6c29985316b49d646cef1ad7816bee8ce95977e09d63c4b","observation_id":"5ea382ed-e060-4ca9-8108-5dab0216cfab","resolution":{"observed_at":"2026-08-06T17:56:03.642271Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2410.09714","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:04.848176Z","title":"AM-SAM: Automated Prompting and Mask Calibration for Segment Anything Model","venue":null,"work_id":"98e9b001-41b3-4046-a938-5e054a7be83c","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.645375Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:9863a0aa9d49fbf0f01e6c2ef4eaf44c44babd058694d8c0d89ebf63d4a1317f","observation_id":"a03b3165-40be-40ee-97c9-7a4762714936","resolution":{"observed_at":"2026-08-06T17:56:04.853660Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.639428Z","title":"ClipSAM: CLIP and SAM collabo- ration for zero-shot anomaly segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.639428Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:40ecbc58e9383d1da7fe106e40534d56ef05a5c54749bfd7455ab6f2bb48b4d5","observation_id":"6615a959-794e-4b0b-828e-02ede25f15c8","resolution":{"observed_at":"2026-08-06T17:56:03.639428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06756","last_updated":"2025-03-16T10:12:23Z","snapshot_observed_at":"2026-08-09T04:04:20.740573Z","submitted_at":"2025-02-10T18:33:15Z","title":"SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06756","snapshot_observed_at":"2026-08-06T17:56:03.652348Z","title":"SAMRefiner: Taming Segment Any- thing Model for Universal Mask Refinement","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.652348Z"},"links":{"cited_paper":"/paper/2502.06756","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:cc7233bf0ecb485c15ace838abd3fdcc8a774f2431ccd175f6547a331dd60ca1","observation_id":"2acd78b7-37ca-432a-bf77-e750333dcadb","resolution":{"observed_at":"2026-08-06T17:56:03.652348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.655364Z","title":"Training- Free Open-Ended Object Detection and Segmentation via Attention as Prompts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.655364Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:5adee7c2de448b4950113bdef6782b2208f2b4ad8079dfcd2037c063c7601c2b","observation_id":"45ec1059-57d9-439a-98e3-ec592b5863db","resolution":{"observed_at":"2026-08-06T17:56:03.655364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13258","last_updated":"2024-03-20T02:39:15Z","snapshot_observed_at":"2026-07-06T17:47:26.534826Z","submitted_at":"2024-03-20T02:39:15Z","title":"SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts","version":1},"cited_work":{"arxiv_id":"2403.13258","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.13258","snapshot_observed_at":"2026-08-06T17:56:04.772619Z","title":"SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts","venue":"cs.CV","work_id":"7e17581b-eca3-4c9e-874c-22545074ae01","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.648451Z"},"links":{"cited_paper":"/paper/2403.13258","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:708a8628f5d9c92a7b49f69d9c161934c6c69e0f801a1f206b1d1de69f0d159d","observation_id":"5218031c-c5ee-477a-a71d-f6dc6c057fe1","resolution":{"observed_at":"2026-08-06T17:56:04.777374Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00741","last_updated":"2024-03-31T17:02:24Z","snapshot_observed_at":"2026-07-06T17:53:44.044640Z","submitted_at":"2024-03-31T17:02:24Z","title":"Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts","version":1},"cited_work":{"arxiv_id":"2404.00741","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.00741","snapshot_observed_at":"2026-08-06T17:56:04.731972Z","title":"Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts","venue":"cs.CV","work_id":"46daa3b7-e820-4c15-818d-c1835abccc40","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.662871Z"},"links":{"cited_paper":"/paper/2404.00741","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:5747dddd00cef8783a23095a1d4c8d82be7067a4410fca1dd0788a39af9050c3","observation_id":"e8731712-80b3-4052-b17e-4d8817514c62","resolution":{"observed_at":"2026-08-06T17:56:04.736805Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.05499","last_updated":"2024-07-19T06:00:41Z","snapshot_observed_at":"2026-07-06T15:00:58.804337Z","submitted_at":"2023-03-09T18:52:16Z","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.05499","snapshot_observed_at":"2026-08-06T17:56:03.667197Z","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object De- tection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.667197Z"},"links":{"cited_paper":"/paper/2303.05499","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:6ce03672d95056fa4e0153899eb8a2e1ba9fef1b34d9bc54b83e01289a203752","observation_id":"b47fcfa1-a7ef-49ad-affa-122558501eb0","resolution":{"observed_at":"2026-08-06T17:56:03.667197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01010","last_updated":"2024-01-02T03:37:11Z","snapshot_observed_at":"2026-07-06T17:10:39.974230Z","submitted_at":"2024-01-02T03:37:11Z","title":"Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt","version":1},"cited_work":{"arxiv_id":"2401.01010","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.01010","snapshot_observed_at":"2026-08-06T17:56:04.747813Z","title":"Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt","venue":"cs.CV","work_id":"f5c81e69-3d40-488b-bf30-8a9297d915d2","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.659116Z"},"links":{"cited_paper":"/paper/2401.01010","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:43bdf375e09c93447e85bb5dbccc6a8d0041fc6198966d0eb46fad84efb47768","observation_id":"4370c5d7-1f32-4048-b13a-aa88c07f8ed0","resolution":{"observed_at":"2026-08-06T17:56:04.751899Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16271","last_updated":"2024-06-24T02:33:46Z","snapshot_observed_at":"2026-07-06T18:35:45.699877Z","submitted_at":"2024-06-24T02:33:46Z","title":"Feature-prompting GBMSeg: One-Shot Reference Guided Training-Free Prompt Engineering for Glomerular Basement Membrane Segmentation","version":1},"cited_work":{"arxiv_id":"2406.16271","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.16271","snapshot_observed_at":"2026-08-06T17:56:04.691881Z","title":"Feature-prompting GBMSeg: One-Shot Reference Guided Training-Free Prompt Engineering for Glomerular Basement Membrane Segmentation","venue":"cs.CV","work_id":"0c96344b-8b1a-4835-a654-404c3f3a3ea6","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.673842Z"},"links":{"cited_paper":"/paper/2406.16271","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:06bd440313e79e8abb101e3adcf81df9746e25db83d1b851a33ec68c373b2dfa","observation_id":"82db0b4e-17c5-4ec3-98b3-fde59be56eab","resolution":{"observed_at":"2026-08-06T17:56:04.697030Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.677294Z","title":"SAM-RSIS: Progressively Adapt- ing SAM With Box Prompting to Remote Sensing Im- age Instance Segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.677294Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:44505dca143338c65fd6e6b593f70f5d45692644ae0bf6c2d10a0dbb8311625d","observation_id":"a39dcf39-ed16-42bb-b23f-78ec5dc83d2d","resolution":{"observed_at":"2026-08-06T17:56:03.677294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00706","last_updated":"2024-08-01T16:52:39Z","snapshot_observed_at":"2026-07-06T18:55:41.459417Z","submitted_at":"2024-08-01T16:52:39Z","title":"Point-supervised Brain Tumor Segmentation with Box-prompted MedSAM","version":1},"cited_work":{"arxiv_id":"2408.00706","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.00706","snapshot_observed_at":"2026-08-06T17:56:04.707510Z","title":"Point-supervised Brain Tumor Segmentation with Box-prompted MedSAM","venue":"cs.CV","work_id":"7ce71cf9-dfc1-4444-8f39-5c34ca3c4edb","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.670414Z"},"links":{"cited_paper":"/paper/2408.00706","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7c9dc2eff92ec53b43153cbd6ff279a5e08c98458c72e3436ca75b56d3c7f6c2","observation_id":"23782cd2-f165-4de0-8f7a-b804dcce4a1f","resolution":{"observed_at":"2026-08-06T17:56:04.711231Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16246","last_updated":"2025-01-27T17:43:51Z","snapshot_observed_at":"2026-07-06T20:26:50.822135Z","submitted_at":"2025-01-27T17:43:51Z","title":"CLISC: Bridging clip and sam by enhanced cam for unsupervised brain tumor segmentation","version":1},"cited_work":{"arxiv_id":"2501.16246","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.16246","snapshot_observed_at":"2026-08-06T17:56:04.519377Z","title":"CLISC: Bridging clip and sam by enhanced cam for unsupervised brain tumor segmentation","venue":"cs.CV","work_id":"d75d7946-af51-49c6-974b-bf1f8de8afd4","year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.686063Z"},"links":{"cited_paper":"/paper/2501.16246","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:9d3a3f5f0e6c91e66bed84a2e10bd366997390e62f6558e2c085b453d2dc8c7f","observation_id":"604e03be-f9b1-4d51-a5ba-8b31db9a6103","resolution":{"observed_at":"2026-08-06T17:56:04.523720Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09484","last_updated":"2024-09-14T17:11:37Z","snapshot_observed_at":"2026-08-09T03:24:25.705269Z","submitted_at":"2024-09-14T17:11:37Z","title":"Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model","version":1},"cited_work":{"arxiv_id":"2409.09484","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.09484","snapshot_observed_at":"2026-08-06T17:56:04.502152Z","title":"Self-Prompting Polyp Segmentation in Colonoscopy using Hybrid Yolo-SAM 2 Model","venue":"eess.IV","work_id":"5587207c-5a5e-4661-b28d-1c999f230d92","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.689653Z"},"links":{"cited_paper":"/paper/2409.09484","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:031cae5a1be7e287f28eb6ec778c5d91babee3d6dd0000c86308a44612b71e82","observation_id":"0756f776-404d-4cdb-9da9-1c80605c9b28","resolution":{"observed_at":"2026-08-06T17:56:04.507057Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.680295Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.680295Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:5e24d7b74ca34d3efc55b015cdf1a8437da0c3ae0a41836a3a5a353b9a4be9f3","observation_id":"f89d6282-715d-4bff-bfb1-0c0fbb06fc71","resolution":{"observed_at":"2026-08-06T17:56:03.680295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.683298Z","title":"GroupPrompter: A Prompting Method for Semantic Segmentation Based on SAM","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.683298Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7d26245ba2549f24f8b572488b2a70a3f6b9998e323ae99b1d28fb0e7aa6511a","observation_id":"fddd6059-67d3-470d-b596-797a21b563b1","resolution":{"observed_at":"2026-08-06T17:56:03.683298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01538","last_updated":"2021-10-14T18:27:04Z","snapshot_observed_at":"2026-07-06T10:56:19.759252Z","submitted_at":"2021-04-04T05:27:13Z","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","version":3},"cited_work":{"arxiv_id":"2104.01538","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.01538","snapshot_observed_at":"2026-08-06T17:56:04.472497Z","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","venue":"cs.CV","work_id":"4f03fa4f-f15f-4a36-986f-7f907184213a","year":2021},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.700858Z"},"links":{"cited_paper":"/paper/2104.01538","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:1e293ef570a6df875fd7f284374269963ffa8e5a17006f1abbe80d3dbdb45efc","observation_id":"fdeabbb9-def9-4d37-9bfd-f5a0d34aaee8","resolution":{"observed_at":"2026-08-06T17:56:04.476087Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06795","last_updated":"2025-07-15T09:10:02Z","snapshot_observed_at":"2026-07-06T18:43:38.955120Z","submitted_at":"2024-07-09T12:08:07Z","title":"CycleSAM: Few-Shot Surgical Scene Segmentation with Cycle- and Scene-Consistent Feature Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06795","snapshot_observed_at":"2026-08-06T17:56:03.704048Z","title":"CycleSAM: One-Shot Surgical Scene Segmentation using Cycle-Consistent Feature Matching to Prompt SAM","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.704048Z"},"links":{"cited_paper":"/paper/2407.06795","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:2d0a69e62b642c582b529fcee3912358c62241fe5f1cbf8a5a52e7141a08cb81","observation_id":"4b9185cd-8d8e-427e-ae0f-cf21d77d3380","resolution":{"observed_at":"2026-08-06T17:56:03.704048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.02075","last_updated":"2025-08-21T14:39:31Z","snapshot_observed_at":"2026-08-04T18:35:43.328961Z","submitted_at":"2024-07-02T09:08:06Z","title":"Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts","version":4},"cited_work":{"arxiv_id":"2407.02075","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.02075","snapshot_observed_at":"2026-08-06T17:56:04.487648Z","title":"Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts","venue":"cs.CV","work_id":"23315e1d-d899-46cf-a215-bddd05ab84b3","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.693316Z"},"links":{"cited_paper":"/paper/2407.02075","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:fc94e4f15877c703a01c0597ecbcdf6e9bd14832873c564d07d64271c11a557f","observation_id":"91aa0fcc-e747-47cc-8e27-ac5d7377d437","resolution":{"observed_at":"2026-08-06T17:56:04.491236Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.697265Z","title":"Cross Prompting Consistency with Segment Anything Model for Semi-supervised Medi- cal Image Segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.697265Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:59d2d0fa4b2acad6a2fd4a5334b0e8c8b0fcd5ad59ecabb95e58828757f2c03e","observation_id":"aa9027e9-a4da-4d77-aceb-b497cbf9ed5e","resolution":{"observed_at":"2026-08-06T17:56:03.697265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.714928Z","title":"Benchmarking Human and Au- tomated Prompting in the Segment Anything Model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.714928Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7b4b8ed2d02ea4c3e73e412fc2f4b34f22ba8eac42b1700d4808e0cf79d8716c","observation_id":"eb015687-a4e5-4da5-a72c-dfb8a592e292","resolution":{"observed_at":"2026-08-06T17:56:03.714928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00020","last_updated":"2021-02-26T19:04:58Z","snapshot_observed_at":"2026-07-06T10:45:03.059688Z","submitted_at":"2021-02-26T19:04:58Z","title":"Learning Transferable Visual Models From Natural Language Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00020","snapshot_observed_at":"2026-08-06T17:56:03.723010Z","title":"Learning Transferable Visual Mod- els From Natural Language Supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.723010Z"},"links":{"cited_paper":"/paper/2103.00020","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f0cdf0c67eb67d0bac9f5a610f0eb355606d72a568c860a619af2c27a1586b4f","observation_id":"14034ff9-b270-41bd-81ab-ddab08b7fac0","resolution":{"observed_at":"2026-08-06T17:56:03.723010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.13220","last_updated":"2024-01-24T04:23:17Z","snapshot_observed_at":"2026-07-06T17:19:44.130417Z","submitted_at":"2024-01-24T04:23:17Z","title":"Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.13220","snapshot_observed_at":"2026-08-06T17:56:03.707859Z","title":"Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.707859Z"},"links":{"cited_paper":"/paper/2401.13220","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:db0f1ad65377cc7bbfea1e45c4d074eb4c856463f9d15ffd99fd2b7aeafbd453","observation_id":"2288b4cb-de84-4c05-a836-9333a146de69","resolution":{"observed_at":"2026-08-06T17:56:03.707859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11998","last_updated":"2024-12-16T17:26:06Z","snapshot_observed_at":"2026-07-06T20:07:54.727859Z","submitted_at":"2024-12-16T17:26:06Z","title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","version":1},"cited_work":{"arxiv_id":"2412.11998","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.11998","snapshot_observed_at":"2026-08-06T17:56:04.439194Z","title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","venue":"cs.CV","work_id":"82009419-1026-4e76-90ba-fa10ffc2f999","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.711771Z"},"links":{"cited_paper":"/paper/2412.11998","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:78d59383dc896fb09beea93b431070d425ce72fdd364dfccb5746bcb753fecb8","observation_id":"f5c9f04c-3cca-460c-9352-ba3d276a36bc","resolution":{"observed_at":"2026-08-06T17:56:04.443171Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.732813Z","title":"Temporally-Extended Prompts Optimization for SAM in Interactive Medical Im- age Segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.732813Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:a5f354ea43a74d3fb2b2850d6b0ab2aff99cd1d4fbccfa47180d4952e6fbcfb3","observation_id":"75fd4680-1a32-44e2-b7a6-5da3903e592a","resolution":{"observed_at":"2026-08-06T17:56:03.732813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.22048","last_updated":"2024-10-30T18:51:38Z","snapshot_observed_at":"2026-08-02T01:07:20.177956Z","submitted_at":"2024-10-29T13:56:31Z","title":"Benchmarking Human and Automated Prompting in the Segment Anything Model","version":2},"cited_work":{"arxiv_id":"2410.22048","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.22048","snapshot_observed_at":"2026-08-06T17:56:04.423239Z","title":"Benchmarking Human and Automated Prompting in the Segment Anything Model","venue":"cs.CV","work_id":"2fe80ec5-c0a5-421d-8041-8f174f7a5183","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.718410Z"},"links":{"cited_paper":"/paper/2410.22048","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:b62a520546330ca976bcf146d6dda755803c06121a85a0b78aab9d658b7e1335","observation_id":"24d0ad99-ef17-4717-9b2a-3cb5c8d330ba","resolution":{"observed_at":"2026-08-06T17:56:04.426913Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.739877Z","title":"EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.739877Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:8e723d08baf0ca25d6716836be57e2fca88a5940823f47f1daed4d85d9466e80","observation_id":"03eefa40-662b-46e1-8b6a-c7671f9d633e","resolution":{"observed_at":"2026-08-06T17:56:03.739877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16740","last_updated":"2024-05-27T01:13:01Z","snapshot_observed_at":"2026-07-06T18:20:14.021759Z","submitted_at":"2024-05-27T01:13:01Z","title":"PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation","version":1},"cited_work":{"arxiv_id":"2405.16740","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16740","snapshot_observed_at":"2026-08-06T17:56:04.396729Z","title":"PP-SAM: Perturbed Prompts for Robust Adaptation of Segment Anything Model for Polyp Segmentation","venue":"cs.CV","work_id":"f2c5809c-fe6f-4d88-8f9d-d6c2b6cc2e00","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.726393Z"},"links":{"cited_paper":"/paper/2405.16740","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f1e0207c44a495efc01f320ca0882369af8203db3a839a9ce16bb2f102a9328e","observation_id":"2b84c285-32b4-4572-af13-8b110c880b48","resolution":{"observed_at":"2026-08-06T17:56:04.400579Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.00719","last_updated":"2025-02-02T08:40:14Z","snapshot_observed_at":"2026-07-06T20:29:45.369233Z","submitted_at":"2025-02-02T08:40:14Z","title":"Vision and Language Reference Prompt into SAM for Few-shot Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.00719","snapshot_observed_at":"2026-08-06T17:56:03.729432Z","title":"Vision and Language Reference Prompt into SAM for Few-shot Segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.729432Z"},"links":{"cited_paper":"/paper/2502.00719","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:4eb30b3a73c1d4e8aa247bca78825714007dd4f920d1614115da203f63cb349d","observation_id":"95cf200c-2baa-42b4-a440-6ceecb325b54","resolution":{"observed_at":"2026-08-06T17:56:03.729432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.750299Z","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.750299Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:2b4bb5ee33cea434214725d82a88fddb52dd8b810562e7bf46ef721598f366bc","observation_id":"1a6808a4-3766-4812-9a1e-7714c19f2d50","resolution":{"observed_at":"2026-08-06T17:56:03.750299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12562","last_updated":"2024-10-16T13:38:01Z","snapshot_observed_at":"2026-08-06T04:53:19.272377Z","submitted_at":"2024-10-16T13:38:01Z","title":"Adaptive Prompt Learning with SAM for Few-shot Scanning Probe Microscope Image Segmentation","version":1},"cited_work":{"arxiv_id":"2410.12562","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.12562","snapshot_observed_at":"2026-08-06T17:56:04.318202Z","title":"Adaptive Prompt Learning with SAM for Few-shot Scanning Probe Microscope Image Segmentation","venue":"cs.CV","work_id":"98fd5523-0aa7-4870-8971-28a4f3d5fcc9","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.736080Z"},"links":{"cited_paper":"/paper/2410.12562","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:217debb7f6561687afcfdf0b899a5dfcac0e560bd44434b4d9b22bf3c13a9db7","observation_id":"64963b31-13f7-469d-8933-d4f691d65deb","resolution":{"observed_at":"2026-08-06T17:56:04.321932Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.760452Z","title":"CogVLM: Visual Expert for Pre- trained Language Models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.760452Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:402922a26be751c34172ce6fcc68772a04dcee4b360bf8aeef8aba3637954067","observation_id":"fcc94408-edc4-4101-ae27-11c4c45e3098","resolution":{"observed_at":"2026-08-06T17:56:03.760452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09212","last_updated":"2019-02-25T11:55:28Z","snapshot_observed_at":"2026-08-07T10:40:09.140030Z","submitted_at":"2019-02-25T11:55:28Z","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.09212","snapshot_observed_at":"2026-08-06T17:56:03.743278Z","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.743278Z"},"links":{"cited_paper":"/paper/1902.09212","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:db337ba680e5d2e985bbd0d5eaf4b246f9bd2ab1537dbc3864c07ba596a3dc59","observation_id":"42646093-a1c2-4d38-8545-8b951bcc61ef","resolution":{"observed_at":"2026-08-06T17:56:03.743278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04960","last_updated":"2026-06-04T11:59:03Z","snapshot_observed_at":"2026-08-02T12:51:51.839797Z","submitted_at":"2024-10-07T11:59:54Z","title":"On Efficient Variants of Segment Anything Model: A Survey","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04960","snapshot_observed_at":"2026-08-06T17:56:03.746472Z","title":"On Efficient Variants of Segment Anything Model: A Survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.746472Z"},"links":{"cited_paper":"/paper/2410.04960","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:5ca7cc320185e78289aa8bae6631dc06bd85f964535b68fe5b2295b2f7868726","observation_id":"a5d8743d-c446-4aa2-95c8-d8c46d9a0dae","resolution":{"observed_at":"2026-08-06T17:56:03.746472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.10666","last_updated":"2022-07-21T17:59:56Z","snapshot_observed_at":"2026-07-06T13:33:54.916595Z","submitted_at":"2022-07-21T17:59:56Z","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.10666","snapshot_observed_at":"2026-08-06T17:56:03.770740Z","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.770740Z"},"links":{"cited_paper":"/paper/2207.10666","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:cd2ca45442b08bfd715213cc20906966bad121c46a622f72e588720d1cd73caa","observation_id":"e8bc9b41-a176-45d1-a94b-bf0ef87e5a4a","resolution":{"observed_at":"2026-08-06T17:56:03.770740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.06821","last_updated":"2024-09-10T19:04:44Z","snapshot_observed_at":"2026-07-06T19:13:24.690465Z","submitted_at":"2024-09-10T19:04:44Z","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","version":1},"cited_work":{"arxiv_id":"2409.06821","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.06821","snapshot_observed_at":"2026-08-06T17:56:04.283753Z","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","venue":"cs.CV","work_id":"64ef45f9-d7c8-4a9d-acb2-a87059477b7f","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.753689Z"},"links":{"cited_paper":"/paper/2409.06821","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:1a32296efdb7e9cf728a403a862805d2ea0514538084f06ca9a8c75ea9e6f302","observation_id":"c943913a-4cec-4eda-a1cc-6b441129a33e","resolution":{"observed_at":"2026-08-06T17:56:04.287615Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.13426","last_updated":"2025-05-22T02:03:01Z","snapshot_observed_at":"2026-07-06T20:24:50.262766Z","submitted_at":"2025-01-23T07:08:48Z","title":"Auto-Prompting SAM for Weakly Supervised Landslide Extraction","version":2},"cited_work":{"arxiv_id":"2501.13426","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.13426","snapshot_observed_at":"2026-08-06T17:56:04.269367Z","title":"Auto-Prompting SAM for Weakly Supervised Landslide Extraction","venue":"cs.CV","work_id":"87bc87bd-a796-414e-8256-e306f55b9392","year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.757241Z"},"links":{"cited_paper":"/paper/2501.13426","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:9ea8ec7e2c56baea53b24b9e1ed598397454df9e98ac4b827b6f00586400de64","observation_id":"fdebbcd3-9203-48e1-a8e5-7d035ef15139","resolution":{"observed_at":"2026-08-06T17:56:04.273086Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:05.327003Z","title":"Self-Prompt SAM: Medical Image Seg- mentation via Automatic Prompt SAM Adaptation","venue":null,"work_id":"3bf02819-5714-47e2-bec0-4b0c768e51c3","year":null},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.779668Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:3e08b4969a3e066e8af36c64442fb6f6858355d2aef74bb3b414b379921b5f93","observation_id":"bdc40d2b-fd8d-4adc-8a55-02889471cecb","resolution":{"observed_at":"2026-08-06T17:56:05.331248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07205","last_updated":"2025-03-11T12:55:57Z","snapshot_observed_at":"2026-07-06T20:04:25.198952Z","submitted_at":"2024-12-10T05:50:50Z","title":"CrackESS: A Self-Prompting Crack Segmentation System for Edge Devices","version":3},"cited_work":{"arxiv_id":"2412.07205","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.07205","snapshot_observed_at":"2026-08-06T17:56:04.255913Z","title":"CrackESS: A Self-Prompting Crack Segmentation System for Edge Devices","venue":"cs.CV","work_id":"5d02c6a7-6e34-4a52-bacb-ce5b6583095c","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.763652Z"},"links":{"cited_paper":"/paper/2412.07205","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:4c1d6937fa59f1ba85fa64d60078759bdfb79dd738646d267ac20b295695026d","observation_id":"78dd3b14-746a-4886-92de-99dcaa8b78ec","resolution":{"observed_at":"2026-08-06T17:56:04.259814Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.17943","last_updated":"2024-12-28T15:39:00Z","snapshot_observed_at":"2026-08-08T14:49:04.580655Z","submitted_at":"2024-12-23T19:54:42Z","title":"Optimizing Prompt Strategies for SAM: Advancing lesion Segmentation Across Diverse Medical Imaging Modalities","version":2},"cited_work":{"arxiv_id":"2412.17943","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.17943","snapshot_observed_at":"2026-08-06T17:56:04.240695Z","title":"Optimizing Prompt Strategies for SAM: Advancing lesion Segmentation Across Diverse Medical Imaging Modalities","venue":"eess.IV","work_id":"77fea406-25f6-4769-829b-adc4ee0f5503","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.767394Z"},"links":{"cited_paper":"/paper/2412.17943","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:51c5cfa29e18ab15d10f824afa8165e7dbc7a4b3b1379c565010e32f8bad7a3b","observation_id":"72d8c4a3-2589-4c46-b721-73249c6ecfcf","resolution":{"observed_at":"2026-08-06T17:56:04.244527Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14153","last_updated":"2025-07-01T04:07:15Z","snapshot_observed_at":"2026-07-06T18:48:53.833921Z","submitted_at":"2024-07-19T09:32:30Z","title":"De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14153","snapshot_observed_at":"2026-08-06T17:56:03.792775Z","title":"ESP-MedSAM: Efficient Self- Prompting SAM for Universal Domain-Generalized Medical Image Segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.792775Z"},"links":{"cited_paper":"/paper/2407.14153","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f882669facedb47f111b5c61258adb27603e5845ce178d94348aa0e98cf20b0e","observation_id":"99146d75-9310-4b65-b881-44323d1dc1e5","resolution":{"observed_at":"2026-08-06T17:56:03.792775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.773821Z","title":"Self- Prompting Large Vision Models for Few-Shot Med- ical Image Segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.773821Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:c67a8cb27f82f34a792335aa730d11674a68793bdd85b74503d0d97ea52ce4cc","observation_id":"e3d198ab-0394-424d-866f-fd67eaa15ef9","resolution":{"observed_at":"2026-08-06T17:56:03.773821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:05.341598Z","title":"Integrating multi-scale informa- tion and diverse prompts in large model SAM-Med2D for accurate left ventricular ejection fraction estima- tion","venue":null,"work_id":"021b5548-432c-4e7e-8070-758b4dd7a913","year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.776779Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:85f7dc59fa44d55c0ce29bf1073dbba4fc537771390198f425dfb5e4cdb5c7dd","observation_id":"59e54dff-fab0-49c7-831b-a87772afc910","resolution":{"observed_at":"2026-08-06T17:56:05.346248Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.06692","last_updated":"2025-01-12T02:57:04Z","snapshot_observed_at":"2026-08-03T04:13:11.611905Z","submitted_at":"2025-01-12T02:57:04Z","title":"PGP-SAM: Prototype-Guided Prompt Learning for Efficient Few-Shot Medical Image Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.06692","snapshot_observed_at":"2026-08-06T17:56:03.803147Z","title":"PGP-SAM: Prototype-Guided Prompt Learning for Efficient Few-Shot Medical Im- age Segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.803147Z"},"links":{"cited_paper":"/paper/2501.06692","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f884ed080872a45ff9417694076fc7c9a5848d4254c69d3c7a896636806d1d04","observation_id":"463fb685-a52d-4916-896a-d73e58d8ee0f","resolution":{"observed_at":"2026-08-06T17:56:03.803147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.05393","last_updated":"2024-12-28T09:34:11Z","snapshot_observed_at":"2026-07-06T19:12:23.792177Z","submitted_at":"2024-09-09T07:43:58Z","title":"TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentation","version":2},"cited_work":{"arxiv_id":"2409.05393","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.05393","snapshot_observed_at":"2026-08-06T17:56:04.139475Z","title":"TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentation","venue":"cs.CV","work_id":"33b2a392-8514-44af-ac26-a09cebcf373e","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.806855Z"},"links":{"cited_paper":"/paper/2409.05393","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:9a2b4672d03bfd4c2fa28bdabca2abe3f4370e2739c017cb92b906f91da86282","observation_id":"90c93ea0-ca7c-4711-96fb-7d221a108d7c","resolution":{"observed_at":"2026-08-06T17:56:04.143341Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19917","last_updated":"2024-12-27T20:33:39Z","snapshot_observed_at":"2026-08-03T18:15:57.284297Z","submitted_at":"2024-12-27T20:33:39Z","title":"Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts","version":1},"cited_work":{"arxiv_id":"2412.19917","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.19917","snapshot_observed_at":"2026-08-06T17:56:04.204098Z","title":"Char-SAM: Turning Segment Anything Model into Scene Text Segmentation Annotator with Character-level Visual Prompts","venue":"cs.CV","work_id":"b81efe9f-33e2-432a-8b68-0b3f7ed8ec2a","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.785826Z"},"links":{"cited_paper":"/paper/2412.19917","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:acd2757bae6a96c42abfdd52343c1a79f40ee69397df0ad8a633aecbe4b5ff3d","observation_id":"ff199018-7170-401f-945e-7776b9363f61","resolution":{"observed_at":"2026-08-06T17:56:04.207661Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17363","last_updated":"2024-11-26T12:12:12Z","snapshot_observed_at":"2026-07-06T19:57:14.289258Z","submitted_at":"2024-11-26T12:12:12Z","title":"SAM-MPA: Applying SAM to Few-shot Medical Image Segmentation using Mask Propagation and Auto-prompting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17363","snapshot_observed_at":"2026-08-06T17:56:03.789703Z","title":"SAM-MPA: Applying SAM to Few- shot Medical Image Segmentation using Mask Propa- gation and Auto-prompting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.789703Z"},"links":{"cited_paper":"/paper/2411.17363","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:4ada8ade75ec0e636027984578fa61feca29b600fdf6d99e2048864caa9f65c1","observation_id":"aac91243-ab07-4011-afe8-9673e62f9d9d","resolution":{"observed_at":"2026-08-06T17:56:03.789703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08746","last_updated":"2023-12-21T11:56:08Z","snapshot_observed_at":"2026-07-06T16:07:06.809394Z","submitted_at":"2023-08-17T02:51:01Z","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","version":2},"cited_work":{"arxiv_id":"2308.08746","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.08746","snapshot_observed_at":"2026-08-06T17:56:04.107820Z","title":"SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation","venue":"cs.CV","work_id":"e98a6e23-2223-4409-aecd-3af8e9235fc1","year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.817522Z"},"links":{"cited_paper":"/paper/2308.08746","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:85463ef8d2d9b8035e0d698bf840b0a8cae46c1c0577f344bd51472146a67bc2","observation_id":"24b2c8de-2640-4836-b7e8-210d704f6dc6","resolution":{"observed_at":"2026-08-06T17:56:04.111852Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12231","last_updated":"2023-08-23T16:13:58Z","snapshot_observed_at":"2026-08-09T04:04:56.667405Z","submitted_at":"2023-08-23T16:13:58Z","title":"SPPNet: A Single-Point Prompt Network for Nuclei Image Segmentation","version":1},"cited_work":{"arxiv_id":"2308.12231","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.12231","snapshot_observed_at":"2026-08-06T17:56:04.172574Z","title":"SPPNet: A Single-Point Prompt Network for Nuclei Image Segmentation","venue":"eess.IV","work_id":"b8eae659-aa3b-435b-996b-7fcbbe3ffc83","year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.796432Z"},"links":{"cited_paper":"/paper/2308.12231","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:20452c640f8ccaecc498cc81af89fc7ae0debf377f841a1ad8c923eb9a1de84f","observation_id":"4fcfca8c-a9ab-4f51-88dc-dc4c55165568","resolution":{"observed_at":"2026-08-06T17:56:04.176326Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.12484","last_updated":"2022-10-13T01:53:23Z","snapshot_observed_at":"2026-08-09T12:09:37.466096Z","submitted_at":"2022-04-26T17:55:04Z","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.12484","snapshot_observed_at":"2026-08-06T17:56:03.799771Z","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.799771Z"},"links":{"cited_paper":"/paper/2204.12484","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:59435f82e7620d1b561e353e45ddae2ea042e667361c000c745036de0e11ad92","observation_id":"c43331d7-32b4-49a9-b036-c96b36276fa0","resolution":{"observed_at":"2026-08-06T17:56:03.799771Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18858","last_updated":"2024-11-28T01:58:28Z","snapshot_observed_at":"2026-07-06T19:58:18.076549Z","submitted_at":"2024-11-28T01:58:28Z","title":"COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection","version":1},"cited_work":{"arxiv_id":"2411.18858","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.18858","snapshot_observed_at":"2026-08-06T17:56:04.082815Z","title":"COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection","venue":"cs.CV","work_id":"202618a9-ed1b-4dd9-b32b-d95ad0d320c3","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.827892Z"},"links":{"cited_paper":"/paper/2411.18858","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:fa8d70f7443490152cc9eee3652d297448b421ae4db9085e44053bf486b48e86","observation_id":"11ecc90a-50e5-4d6a-9ddb-360ec1187ab4","resolution":{"observed_at":"2026-08-06T17:56:04.087049Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08083","last_updated":"2024-02-01T08:05:26Z","snapshot_observed_at":"2026-08-07T22:37:17.297156Z","submitted_at":"2024-01-16T03:21:42Z","title":"UV-SAM: Adapting Segment Anything Model for Urban Village Identification","version":2},"cited_work":{"arxiv_id":"2401.08083","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08083","snapshot_observed_at":"2026-08-06T17:56:04.067302Z","title":"UV-SAM: Adapting Segment Anything Model for Urban Village Identification","venue":"cs.CV","work_id":"d5f6e0c5-cf8c-4f45-b667-ce429ad512b2","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.831589Z"},"links":{"cited_paper":"/paper/2401.08083","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7e4c27f23a53d4f02b2c89db3197c97f291ac6d29970a7c78fe2eea5a35f2979","observation_id":"0eed46f3-8f41-4750-bb05-bdc70fcb0d67","resolution":{"observed_at":"2026-08-06T17:56:04.072001Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-031-72890-7_24","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T00:03:56.115653Z","title":"Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization","venue":"Lecture notes in computer science","work_id":"35ca4fd3-0021-4b82-ab99-b53c09979445","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.810802Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:3942034789ca99a40a59d533948bfa068eba5ce6bde88feea38da700b6fb641f","observation_id":"bd5da4fd-8bf4-4d08-b59e-0d8c6d0d5889","resolution":{"observed_at":"2026-08-06T17:56:03.894626Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14481","last_updated":"2024-03-23T03:13:35Z","snapshot_observed_at":"2026-07-06T17:06:58.615343Z","submitted_at":"2023-12-22T07:17:51Z","title":"SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation","version":2},"cited_work":{"arxiv_id":"2312.14481","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.14481","snapshot_observed_at":"2026-08-06T17:56:04.123312Z","title":"SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation","venue":"cs.CV","work_id":"cef1e8fe-c4ab-4996-9914-414d7f4bf44f","year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.813856Z"},"links":{"cited_paper":"/paper/2312.14481","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:fae65d391f1199ef4b2b044f267a584c5064e3a76d470bc5c5ac979c579fc323","observation_id":"10715ede-db99-4703-8881-a371319c2727","resolution":{"observed_at":"2026-08-06T17:56:04.127348Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:05.302167Z","title":"Automatic Seg- mentation Annotation of Space Target Using Segment Anything Model and Object Detection Prompts","venue":null,"work_id":"18e96ba5-67ba-4bcf-99fc-6b115024b99a","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.841643Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:c15df7d01541b6888e8302dcd58e256ebe5d392ca7af0c6d8c61fe5f10aed8e0","observation_id":"d67ca4de-c1c1-4530-92be-91df47bfe18d","resolution":{"observed_at":"2026-08-06T17:56:05.306908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:05.314923Z","title":"A Survey on Segment Any- thing Model (SAM): Vision Foundation Model Meets Prompt Engineering","venue":null,"work_id":"ef31509e-647a-4ff9-a7f0-8ce124a5ea43","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.821618Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7a9f510221d7c341be7f2adaa7f83be01758513d988e025c70e71f53ffc75a18","observation_id":"6cbe4cec-e8fd-4ac2-b211-ee1154ca50d3","resolution":{"observed_at":"2026-08-06T17:56:05.319197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08196","last_updated":"2023-05-19T16:33:03Z","snapshot_observed_at":"2026-08-05T18:19:34.804424Z","submitted_at":"2023-05-14T16:23:22Z","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.08196","snapshot_observed_at":"2026-08-06T17:56:03.824585Z","title":"A Comprehensive Survey on Seg- ment Anything Model for Vision and Beyond","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.824585Z"},"links":{"cited_paper":"/paper/2305.08196","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:41f3b9301e551669e5a0bfbefd2d6ca41c77df5dccf92bdc54e29f11ea4183da","observation_id":"7c4ee73d-5102-4752-ba2e-58d8b1209621","resolution":{"observed_at":"2026-08-06T17:56:03.824585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00695","last_updated":"2024-09-01T11:00:18Z","snapshot_observed_at":"2026-08-08T19:32:01.111818Z","submitted_at":"2024-09-01T11:00:18Z","title":"Curriculum Prompting Foundation Models for Medical Image Segmentation","version":1},"cited_work":{"arxiv_id":"2409.00695","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.00695","snapshot_observed_at":"2026-08-06T17:56:03.962381Z","title":"Curriculum Prompting Foundation Models for Medical Image Segmentation","venue":"cs.CV","work_id":"f47395d4-bee4-495d-916e-ee9b2601c590","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.851147Z"},"links":{"cited_paper":"/paper/2409.00695","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:a6e53761199e4b7772cc39c7e1ca8cd0baf4904c6e1fca1292b73414d74bbf34","observation_id":"477c555b-863c-4d69-89ef-d81d3f2f58dd","resolution":{"observed_at":"2026-08-06T17:56:03.966270Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.06660","last_updated":"2025-09-07T19:09:41Z","snapshot_observed_at":"2026-07-06T17:00:00.321552Z","submitted_at":"2023-12-11T18:59:52Z","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.06660","snapshot_observed_at":"2026-08-06T17:56:03.855214Z","title":"EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.855214Z"},"links":{"cited_paper":"/paper/2312.06660","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:b7f92ba7a3f0aaf28dfe3a6f893101fe55f0d7b12cd4e337698f3a697b1bc715","observation_id":"b448b334-fcd0-4656-93e6-de55560d783f","resolution":{"observed_at":"2026-08-06T17:56:03.855214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03678","last_updated":"2023-08-11T04:23:29Z","snapshot_observed_at":"2026-07-06T15:23:52.761222Z","submitted_at":"2023-05-05T16:48:45Z","title":"Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03678","snapshot_observed_at":"2026-08-06T17:56:03.835409Z","title":"Towards Segment Any- thing Model (SAM) for Medical Image Segmentation: A Survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.835409Z"},"links":{"cited_paper":"/paper/2305.03678","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:e9fe69a12fece3677a9c27a720c177cd651a0d8f4a92d469c775cecd93860b4a","observation_id":"a5212793-1c11-4e3b-ae40-15e19fe40275","resolution":{"observed_at":"2026-08-06T17:56:03.835409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.10529","last_updated":"2024-03-18T08:47:03Z","snapshot_observed_at":"2026-07-06T16:49:04.651019Z","submitted_at":"2023-11-17T13:49:00Z","title":"Enhancing the Reliability of Segment Anything Model for Auto-Prompting Medical Image Segmentation with Uncertainty Rectification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.10529","snapshot_observed_at":"2026-08-06T17:56:03.838493Z","title":"Enhancing the Reliability of Seg- ment Anything Model for Auto-Prompting Medical Im- age Segmentation with Uncertainty Rectification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.838493Z"},"links":{"cited_paper":"/paper/2311.10529","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:0e162ddea75201979844d6a7d45a17f382069eb63917033f58117a5be7d001c1","observation_id":"f88cf439-37fe-4eda-9b9b-7d550bb4b553","resolution":{"observed_at":"2026-08-06T17:56:03.838493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06718","last_updated":"2023-07-11T18:13:14Z","snapshot_observed_at":"2026-08-05T05:31:21.900215Z","submitted_at":"2023-04-13T17:59:40Z","title":"Segment Everything Everywhere All at Once","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06718","snapshot_observed_at":"2026-08-06T17:56:03.866876Z","title":"Segment Everything Everywhere All at Once","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.866876Z"},"links":{"cited_paper":"/paper/2304.06718","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:f71dbdfb7c9e288d87eb66de216fd20c66604158677dd97f17fe1585d462bada","observation_id":"8e008236-00e6-4e64-8d6f-cc78ffb88613","resolution":{"observed_at":"2026-08-06T17:56:03.866876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.845024Z","title":"Semantic-Enhanced Point-Box Joint Prompting for Video Object Segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.845024Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:0167bd1a2b54f2c60e9017aa2a7419b658f0c07e8d646bb5055b8fecf5bdaa12","observation_id":"8d361070-cdfa-4a80-9a83-c437165454c3","resolution":{"observed_at":"2026-08-06T17:56:03.845024Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.12156","last_updated":"2023-06-21T10:08:29Z","snapshot_observed_at":"2026-07-06T15:45:01.961896Z","submitted_at":"2023-06-21T10:08:29Z","title":"Fast Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.12156","snapshot_observed_at":"2026-08-06T17:56:03.848050Z","title":"Fast Segment Anything","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.848050Z"},"links":{"cited_paper":"/paper/2306.12156","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:7e98eb4c93ea9cdb8f23b727ca6f09a9ca829a1ccd241f0ad527cd1115385b90","observation_id":"97323e76-0230-4f2c-9d8b-69ce71a072c3","resolution":{"observed_at":"2026-08-06T17:56:03.848050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00924","last_updated":"2024-09-02T03:40:07Z","snapshot_observed_at":"2026-08-08T20:15:10.159687Z","submitted_at":"2024-09-02T03:40:07Z","title":"MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM","version":1},"cited_work":{"arxiv_id":"2409.00924","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.00924","snapshot_observed_at":"2026-08-06T17:56:03.936985Z","title":"MedSAM-U: Uncertainty-Guided Auto Multi-Prompt Adaptation for Reliable MedSAM","venue":"cs.CV","work_id":"922d5600-3883-40d1-9bd4-c98c7065e59c","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.859273Z"},"links":{"cited_paper":"/paper/2409.00924","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:4fd534d847cc73f46eff356892ed05b504f83e90c55b02133d569066a27d069d","observation_id":"720937dc-a082-4fbe-bf8e-34b49107847b","resolution":{"observed_at":"2026-08-06T17:56:03.941307Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06594","last_updated":"2023-03-12T07:22:08Z","snapshot_observed_at":"2026-07-06T15:01:49.803305Z","submitted_at":"2023-03-12T07:22:08Z","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06594","snapshot_observed_at":"2026-08-06T17:56:03.863141Z","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual De- scriptions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.863141Z"},"links":{"cited_paper":"/paper/2303.06594","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:2b84f43619d516a52d3a5dfe162c8bb3a07e0d021b5232e43afc2196205027e7","observation_id":"693d6196-8f77-4f8b-8a6c-a0382fd50ecd","resolution":{"observed_at":"2026-08-06T17:56:03.863141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17933","last_updated":"2024-07-25T10:46:29Z","snapshot_observed_at":"2026-07-06T18:51:45.603762Z","submitted_at":"2024-07-25T10:46:29Z","title":"Segmentation by registration-enabled SAM prompt engineering using five reference images","version":1},"cited_work":{"arxiv_id":"2407.17933","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.17933","snapshot_observed_at":"2026-08-06T17:56:05.123569Z","title":"Segmentation by registration-enabled SAM prompt engineering using five reference images","venue":"cs.CV","work_id":"cedb8886-1f7e-4219-a09e-16bf55fb8f5b","year":2024},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.554013Z"},"links":{"cited_paper":"/paper/2407.17933","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:ac4698bb8aecc01d049c8db6adf3c751203be921b158ec6f996f00b76b61fe44","observation_id":"585da220-c1a7-46dd-8828-5b48ff51dcc4","resolution":{"observed_at":"2026-08-06T17:56:05.127452Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.00630","last_updated":"2025-02-02T02:42:24Z","snapshot_observed_at":"2026-08-09T06:10:27.730945Z","submitted_at":"2025-02-02T02:42:24Z","title":"Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptation","version":1},"cited_work":{"arxiv_id":"2502.00630","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.00630","snapshot_observed_at":"2026-08-06T17:56:04.218088Z","title":"Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptation","venue":"cs.CV","work_id":"5935147e-7033-4030-bd67-7eda24df9bd7","year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.782683Z"},"links":{"cited_paper":"/paper/2502.00630","citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:a69318856ca874cf492cdca9b714df1d55d6f5ec0d4dc66c955ea9b00c8a0632","observation_id":"0358123a-c8d1-4b95-8da5-fcf19de2880d","resolution":{"observed_at":"2026-08-06T17:56:04.221739Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.632855Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","version":1},"reference_index":3580,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:03.632855Z"},"links":{"citing_paper":"/paper/2507.09562"},"observation_digest":"sha256:e9bc96d4c8ae02d6486ef57135bb4880240f764204866f0284dc560c2b65e5df","observation_id":"c285a3da-ee4f-4e08-8881-3b16ecc97c33","resolution":{"observed_at":"2026-08-06T17:56:03.632855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.09562","last_updated":"2025-07-13T10:10:17Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T15:24:35.785392Z","submitted_at":"2025-07-13T10:10:17Z","title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges"},"reference_resolution":{"displayed":95,"state_counts":{"malformed_identifier":3,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":48,"verified_exact":40,"verified_fuzzy":3},"total_outbound_references":95},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 0 inbound Pith citation observations for arXiv:2507.09562."}