{"as_of":"2026-08-12T07:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4c5c0336541d6e7f6115df4b06ddc1eaa9e7e0c08b36f4d32338716b709fcb3a","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T20:39:25.574270Z","state":"measured"},{"denominator":72,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":72,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2507.02217/citation-record","integrity":"/paper/2507.02217/integrity","json":"/paper/2507.02217/citation-record.json","paper":"/paper/2507.02217"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:39:32.349208Z","title":"Gpt-4 technical report, 2023","venue":null,"work_id":"00616dcd-56cd-4f35-855f-94acc60bbb52","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.088241Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:2a39b38655341b2bef2c3f2290e2b2b5e85b913f9b66a109cdb59424131639b5","observation_id":"24bad93b-7231-4fa8-9222-e82b10f83f42","resolution":{"observed_at":"2026-08-06T20:39:32.417937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08466","last_updated":"2023-04-17T17:42:29Z","snapshot_observed_at":"2026-07-06T15:16:38.500909Z","submitted_at":"2023-04-17T17:42:29Z","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08466","snapshot_observed_at":"2026-08-06T20:39:19.200515Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.200515Z"},"links":{"cited_paper":"/paper/2304.08466","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:b8eb4e68ccb84a77ff82649fa25ec6a60562befa83b95c8a6bfdecd20ab74a16","observation_id":"1fa5460a-2ea7-4e83-949a-9b8e022accbf","resolution":{"observed_at":"2026-08-06T20:39:19.200515Z","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":"2026-08-06T20:39:32.201871Z","title":"Label-efficient se- mantic segmentation with diffusion models, 2022","venue":null,"work_id":"d09355bf-1176-4d31-aecf-63eea308ea56","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.251211Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:bd0d36c33daf7e6bb300bc7990b8e79f74d6cd583e925e12a1f5b452978b47c6","observation_id":"192501a5-7a48-4b48-92b6-14a8bc2456a0","resolution":{"observed_at":"2026-08-06T20:39:32.271250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:32.038520Z","title":"Mvtec ad — a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":"4505b5f5-9ea7-4fa6-a760-3c05bb88d31e","year":2019},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.335969Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:03ad6731436c8ff5a966a4675eabc8929fcc9984e9c69a260238652bd474e800","observation_id":"680696a2-4666-40af-a291-ff53e4d97fc3","resolution":{"observed_at":"2026-08-06T20:39:32.109155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:31.887735Z","title":"A computational approach to edge detection","venue":null,"work_id":"c681429a-5b7f-44bf-b2c4-ddeb8dd84e58","year":1986},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.415977Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:fc62c0e642768334d3fd41f56c1aab82d06955f47bb30c9e2d658d40ff5ba941","observation_id":"d910e2ff-37bf-4ae8-a754-77eceecfd351","resolution":{"observed_at":"2026-08-06T20:39:31.950587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:19.539152Z","title":"A computational approach to edge detection","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.539152Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:767705bac67e208c087a9b7064384e34674e469a9be94eae463ca7e0df546158","observation_id":"2d259fed-73e3-4ee1-be79-848fa90c88ec","resolution":{"observed_at":"2026-08-06T20:39:19.539152Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.13993","last_updated":"2023-12-11T12:46:04Z","snapshot_observed_at":"2026-08-10T06:31:47.617362Z","submitted_at":"2022-11-25T10:05:06Z","title":"Combating noisy labels in object detection datasets","version":3},"cited_work":{"arxiv_id":"2211.13993","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.13993","snapshot_observed_at":"2026-08-06T20:39:27.107988Z","title":"Combating noisy labels in object detection datasets","venue":"cs.CV","work_id":"ebe771db-1b06-41bc-9c08-82129c150c73","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.663097Z"},"links":{"cited_paper":"/paper/2211.13993","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:0b9557722216b92e1afdb571233078a5dce8ca49aaab8efc9478c7b37099906a","observation_id":"eaa04a14-c335-4907-9d48-9b4a13c485df","resolution":{"observed_at":"2026-08-06T20:39:27.156798Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.13719","last_updated":"2019-11-14T04:51:03Z","snapshot_observed_at":"2026-08-11T06:01:58.805402Z","submitted_at":"2019-09-30T14:05:14Z","title":"RandAugment: Practical automated data augmentation with a reduced search space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.13719","snapshot_observed_at":"2026-08-06T20:39:19.720046Z","title":"Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.720046Z"},"links":{"cited_paper":"/paper/1909.13719","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:9c0ae53707a40263aa602b7998d55ceaff5eeac2cf333375493d581eb80f5cdf","observation_id":"702c7882-ec05-4d02-b54e-97b240856f95","resolution":{"observed_at":"2026-08-06T20:39:19.720046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15807","last_updated":"2023-09-27T17:30:19Z","snapshot_observed_at":"2026-08-02T11:54:13.342379Z","submitted_at":"2023-09-27T17:30:19Z","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15807","snapshot_observed_at":"2026-08-06T20:39:19.811379Z","title":"Emu: Enhanc- ing image generation models using photogenic needles in a haystack","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.811379Z"},"links":{"cited_paper":"/paper/2309.15807","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:3f509b383ef28d3b75da6ffa3aa9423e333e2850cd2b58dbee95b61aee5fc920","observation_id":"800df193-7fa1-44c2-8df4-ae0c0e2a41b5","resolution":{"observed_at":"2026-08-06T20:39:19.811379Z","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":"2026-08-06T20:39:31.717039Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"c3923820-f7c0-49d3-a4d3-029254c0e17f","year":2009},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.897362Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:341ffb2312dc0fc460de04b1671a328a55d56b6850a8c9e9e39ecdb8e9adcd2c","observation_id":"6b086015-38df-4efe-a964-67a61441ea15","resolution":{"observed_at":"2026-08-06T20:39:31.783346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.17033","last_updated":"2024-04-25T20:47:08Z","snapshot_observed_at":"2026-08-10T06:51:02.368355Z","submitted_at":"2024-04-25T20:47:08Z","title":"Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation","version":1},"cited_work":{"arxiv_id":"2404.17033","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.17033","snapshot_observed_at":"2026-08-06T20:39:26.977899Z","title":"Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation","venue":"cs.CV","work_id":"c309d9ff-8696-4f4b-87bc-6ee058690b81","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:19.967525Z"},"links":{"cited_paper":"/paper/2404.17033","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:d8e48104d29b17bb82513a92d67c68f5397f73185a761296820a67ea3faee24a","observation_id":"45057e26-dae1-404f-8b7f-5c8d40256620","resolution":{"observed_at":"2026-08-06T20:39:27.030716Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:31.550254Z","title":null,"venue":null,"work_id":"18747b34-506b-4ecc-b397-65eea972ed9f","year":2010},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.070145Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:ef279d4c02b2fb13a4c2a2b014f18a2811688fc0fb43ad4df6947c9c9823579e","observation_id":"41fa1fd7-25d0-43c5-9c64-b1fa7f7c0d4e","resolution":{"observed_at":"2026-08-06T20:39:31.621505Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:31.374199Z","title":"Instagen: Enhancing object detection by training on syn- thetic dataset","venue":null,"work_id":"84cf9d46-dda7-4152-a521-3fdee738a4ca","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.205747Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:763a1d821ef0f7be2838cd78b528ca0c039338112529c0d5497c7ae038da51aa","observation_id":"9c06d696-d836-4c44-9e27-265d5f02b357","resolution":{"observed_at":"2026-08-06T20:39:31.450806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:31.165884Z","title":"Instructdiffusion: A generalist modeling inter- face for vision tasks","venue":null,"work_id":"e93de0ae-489b-43e6-af27-b46cf71e1552","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.321791Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:e387e2f283fb4e8de9b5eeabe6a601b4f54d431bec5e1ab0da65544f1b638bba","observation_id":"495c68ee-580d-4889-916e-1533362ccf6b","resolution":{"observed_at":"2026-08-06T20:39:31.285500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13808","last_updated":"2024-07-18T09:15:00Z","snapshot_observed_at":"2026-08-10T15:02:43.931673Z","submitted_at":"2024-03-20T17:59:58Z","title":"On Pretraining Data Diversity for Self-Supervised Learning","version":3},"cited_work":{"arxiv_id":"2403.13808","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.13808","snapshot_observed_at":"2026-08-06T20:39:26.837640Z","title":"On Pretraining Data Diversity for Self-Supervised Learning","venue":"cs.CV","work_id":"54d57836-a7a3-424a-9218-f9e58f6967e7","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.461039Z"},"links":{"cited_paper":"/paper/2403.13808","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:5c296df19a93a4e189c032bbd6933fd60bab2d4bb5697d15ee49d7a02e96ef7f","observation_id":"13f02161-cf7d-4c32-bd1e-4f186a5360b5","resolution":{"observed_at":"2026-08-06T20:39:26.893969Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.07841","last_updated":"2023-03-27T15:40:57Z","snapshot_observed_at":"2026-07-06T13:00:57.257337Z","submitted_at":"2022-04-16T16:45:06Z","title":"Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting","version":3},"cited_work":{"arxiv_id":"2204.07841","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.07841","snapshot_observed_at":"2026-08-06T20:39:26.749386Z","title":"Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting","venue":"cs.CV","work_id":"0d9eeacb-a922-4189-a7e6-460eb137e37d","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.571086Z"},"links":{"cited_paper":"/paper/2204.07841","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:ff4e1f87eec64f0a4481d939af9e3d6caf00cd515e633cfd46a5d3c5f9db369f","observation_id":"7b59f7c2-f2fd-4524-82c6-396b4ce9de94","resolution":{"observed_at":"2026-08-06T20:39:26.777577Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:30.959584Z","title":"Meta faster r-cnn: Towards accurate few-shot object detection with attentive feature alignment","venue":null,"work_id":"61c9236d-5483-4864-b47e-5eb19175c11f","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.677233Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:4f3c2fe999af63014d1f5106d3068ca46adeada45d6195b85e773ca1dcf79e7b","observation_id":"5751e9ff-f0d3-41f0-9907-7fd8e348983f","resolution":{"observed_at":"2026-08-06T20:39:31.039726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.06870","last_updated":"2018-01-24T07:54:08Z","snapshot_observed_at":"2026-08-08T19:08:12.187509Z","submitted_at":"2017-03-20T17:53:38Z","title":"Mask R-CNN","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.06870","snapshot_observed_at":"2026-08-06T20:39:20.815939Z","title":"Girshick","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.815939Z"},"links":{"cited_paper":"/paper/1703.06870","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:3e64a5476d83547794477aedc588e13f3a9697cfd04bb97ea1c5f7ba6a2ed5a0","observation_id":"7c792609-2136-439b-a0db-4a07ede3a42e","resolution":{"observed_at":"2026-08-06T20:39:20.815939Z","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":"2026-08-06T20:39:30.786067Z","title":"IS SYN- THETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION? In The Eleventh Interna- tional Conference on Learning Representations, 2023","venue":null,"work_id":"230ebd06-d7c2-4882-89c0-6befc8e60ad4","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:20.900489Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:425efd130f0639b3f73ff2ffecc528d620e958ab566ac51a0c44cd801b58b97d","observation_id":"b467b52a-3662-4c12-b506-37e24a66dce2","resolution":{"observed_at":"2026-08-06T20:39:30.871163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-06T20:39:21.034562Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.034562Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:d5d831d8e730c351ee3c11ffa4d0537e3fd56662db6b0abba8b41add967aaa55","observation_id":"74804412-bf6c-4887-a864-99a1c4d45e03","resolution":{"observed_at":"2026-08-06T20:39:21.034562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11239","last_updated":"2020-12-16T21:15:05Z","snapshot_observed_at":"2026-08-10T05:21:27.485481Z","submitted_at":"2020-06-19T17:24:44Z","title":"Denoising Diffusion Probabilistic Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11239","snapshot_observed_at":"2026-08-06T20:39:21.111068Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.111068Z"},"links":{"cited_paper":"/paper/2006.11239","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:0075233c42998057d713eb996ba42e1a5cbd5798f99537d5e2dc12bc6183adbd","observation_id":"e0162e79-9667-40b7-b635-f9629c32f698","resolution":{"observed_at":"2026-08-06T20:39:21.111068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T20:39:21.209260Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.209260Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:8d0120a488340179944c850aaaf2f7d2c4b7824bab8b931809013ae877aa4b02","observation_id":"a4a43c41-c268-4bf9-abe3-9c1cc6feb43b","resolution":{"observed_at":"2026-08-06T20:39:21.209260Z","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":"2026-08-06T20:39:30.619798Z","title":"Task agnos- tic meta-learning for few-shot learning","venue":null,"work_id":"79c8502d-e8c5-47b2-a754-5b2c11aae547","year":2019},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.332269Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:fc58999f42dd4269aaa3d3bb0267d019297e43130a212e33e4ab6170fdae040b","observation_id":"46308d15-9607-473c-8a2d-40c5055b59ae","resolution":{"observed_at":"2026-08-06T20:39:30.702638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:30.437341Z","title":"Ultralytics YOLO, 2023","venue":null,"work_id":"a6319b2f-44fe-40e0-b0c0-79175269f91f","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.443291Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:9e75db8e52302c7a6a3720bd92abdc9e093a5d8cc59873f0813cdd3b60099ee1","observation_id":"2fc874fe-08cd-4c1b-aa9a-c37a8173feb9","resolution":{"observed_at":"2026-08-06T20:39:30.521540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09468","last_updated":"2024-07-15T08:36:59Z","snapshot_observed_at":"2026-07-06T17:44:37.894023Z","submitted_at":"2024-03-14T15:07:36Z","title":"Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing","version":2},"cited_work":{"arxiv_id":"2403.09468","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.09468","snapshot_observed_at":"2026-08-06T20:39:26.593471Z","title":"Eta Inversion: Designing an Optimal Eta Function for Diffusion-based Real Image Editing","venue":"cs.CV","work_id":"74ee86ab-762a-4ad5-b264-e96ef5d5f349","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.605906Z"},"links":{"cited_paper":"/paper/2403.09468","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:225a0a39dd12be544d6547c1297512c58665304d9241ab2b876a1924bde92d97","observation_id":"fc9edcce-7245-4888-bae8-b4fdcd262594","resolution":{"observed_at":"2026-08-06T20:39:26.640194Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:30.269092Z","title":"Berg, Wan-Yen Lo, Piotr Dollár, and Ross B","venue":null,"work_id":"e2b3c97f-b9f2-4b0a-8773-709b52323f03","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.683376Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:bfc2ae06bb3805c998339798df7db50c13545e21766774f8242a532df59fe261","observation_id":"686df2a1-2010-412d-8c03-0d5cfc48b36f","resolution":{"observed_at":"2026-08-06T20:39:30.336545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:21.788277Z","title":"Overcoming catastrophic forgetting in neu- ral networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.788277Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:9bfbd3f4a61e4716d78827c7cf7311af6e1ad7409b1d1eac65ba5675e23aebf9","observation_id":"fb697080-fb0d-4d66-be5b-2237cc3e03c5","resolution":{"observed_at":"2026-08-06T20:39:21.788277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08249","last_updated":"2024-06-12T14:18:07Z","snapshot_observed_at":"2026-08-03T08:52:07.032422Z","submitted_at":"2024-06-12T14:18:07Z","title":"Dataset Enhancement with Instance-Level Augmentations","version":1},"cited_work":{"arxiv_id":"2406.08249","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.08249","snapshot_observed_at":"2026-08-06T20:39:26.483677Z","title":"Dataset Enhancement with Instance-Level Augmentations","venue":"cs.CV","work_id":"cf8c37b3-15d2-4ddc-830c-b253a424fb80","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.859151Z"},"links":{"cited_paper":"/paper/2406.08249","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:10367ae3526410172d7b14838f6661871cd4a59b9026639f02b7e46245946c4f","observation_id":"6b95f737-9f06-4a34-9a47-6b1d131ba080","resolution":{"observed_at":"2026-08-06T20:39:26.539133Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:30.066706Z","title":"Controlnet ++: Improving conditional controls with efficient consistency feedback","venue":null,"work_id":"d414ee3c-cd95-49c6-9882-c73e56630bc0","year":2025},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:21.957212Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:a9a696428f78e1195f19cbd09daf0711f8e4fbd1c9926e81a4152dca4c2a4fe2","observation_id":"4c4303fc-a807-4950-a3ac-f10075f77071","resolution":{"observed_at":"2026-08-06T20:39:30.167469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:22.126729Z","title":"Gligen: Open-set grounded text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.126729Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:910e33318b7629f1e9594e987648af54953f3a6f8fe3122013bb6193060f1869","observation_id":"14953de5-3722-4326-93b4-66528f8f200c","resolution":{"observed_at":"2026-08-06T20:39:22.126729Z","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":"2026-08-06T20:39:29.917256Z","title":"Lawrence Zitnick","venue":null,"work_id":"f9bf292e-4fbf-4db0-ba3f-656abff161bd","year":2014},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.246630Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:d06f43e4475f73929ea5610cd5c2552470711d55180a506f55d26b7542305250","observation_id":"c4054436-db0e-49e5-aa51-e06f6d01c656","resolution":{"observed_at":"2026-08-06T20:39:29.986114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:22.363535Z","title":"Improved baselines with visual instruction tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.363535Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:a3c98549ba4174a93f20bb19a276f2b4a5703f5fa787040e2841632ef59aca97","observation_id":"3a657d26-32d9-4fb1-a839-ac5402ae6ac4","resolution":{"observed_at":"2026-08-06T20:39:22.363535Z","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":"2026-08-06T20:39:22.442678Z","title":"Visual instruction tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.442678Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:c95ff5de7d3b7ba31f934bb1523c5f1699ac6dcb35c157cd040cfc8d7afc5370","observation_id":"ae515b5c-eca9-489a-8f3f-7b6e9fe0c5c8","resolution":{"observed_at":"2026-08-06T20:39:22.442678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-06T20:39:22.517022Z","title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detec- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.517022Z"},"links":{"cited_paper":"/paper/2303.05499","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:25b641d37212cfba09462b4d8e0a8e058e282f3109f997ff600a8aa4d42bf3e1","observation_id":"88901c7f-c211-4aa3-8c58-f75992c8c65c","resolution":{"observed_at":"2026-08-06T20:39:22.517022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-06T20:39:22.676246Z","title":"Fixing weight decay reg- ularization in adam","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.676246Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:79957b0c60eb415afc072c4f01bfc72a1ef53e2a377406d116c0f704e9ee15de","observation_id":"e144cfd4-2722-4634-8cd1-7eb3f5fe9e00","resolution":{"observed_at":"2026-08-06T20:39:22.676246Z","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":"2026-08-06T20:39:29.612070Z","title":"The effect of improving annotation quality on object detection datasets: A preliminary study","venue":null,"work_id":"94bfd949-08ce-46c4-a0a1-32b3135f533c","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.766968Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:00cb9fe39e838724199be2fec41a2d412f6d79885dbe325a82638e6738a482c8","observation_id":"e6c03bf1-de47-4b3d-980e-9cdb730c3e0b","resolution":{"observed_at":"2026-08-06T20:39:29.692743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.01073","last_updated":"2022-01-05T00:07:35Z","snapshot_observed_at":"2026-08-08T06:35:17.078531Z","submitted_at":"2021-08-02T17:59:47Z","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.01073","snapshot_observed_at":"2026-08-06T20:39:22.826663Z","title":"Sdedit: Guided image synthesis and editing with stochastic differential equa- tions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.826663Z"},"links":{"cited_paper":"/paper/2108.01073","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:08c712fe9c9333d0368baaa6605ce2fedcac8764f01bfbc3bff83eaf40054db4","observation_id":"40a0d8a3-34c3-415d-b760-f8dc84e2c758","resolution":{"observed_at":"2026-08-06T20:39:22.826663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09683","last_updated":"2024-05-22T13:00:02Z","snapshot_observed_at":"2026-08-04T22:40:33.196944Z","submitted_at":"2023-06-16T08:27:46Z","title":"Scaling Open-Vocabulary Object Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09683","snapshot_observed_at":"2026-08-06T20:39:22.883135Z","title":"Gritsenko, and Neil Houlsby","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.883135Z"},"links":{"cited_paper":"/paper/2306.09683","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:eda2c3532bed3f9fe12ddc07b6b953e3b1ba5cb2d4b0cf426ff19857a7761dd8","observation_id":"93317109-d5c3-4692-b5a2-19dac4591b97","resolution":{"observed_at":"2026-08-06T20:39:22.883135Z","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":"2026-08-06T20:39:29.442381Z","title":null,"venue":null,"work_id":"35b1d109-6fd6-4cf6-aebe-e9356126860e","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.941694Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:2da7a7471b275d7b4a991977d10ad2cf91216adf8e14b312b9b57c05efe2d8a4","observation_id":"754c22e1-28e8-4142-88d9-f4696e07ea83","resolution":{"observed_at":"2026-08-06T20:39:29.528272Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.07039","last_updated":"2022-12-14T09:03:35Z","snapshot_observed_at":"2026-08-12T01:16:15.850384Z","submitted_at":"2022-08-15T07:29:31Z","title":"Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning","version":3},"cited_work":{"arxiv_id":"2208.07039","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.07039","snapshot_observed_at":"2026-08-06T20:39:26.327490Z","title":"Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning","venue":"cs.CV","work_id":"d9685dc1-4de5-48b8-9b98-ebf7d5758562","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.054739Z"},"links":{"cited_paper":"/paper/2208.07039","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:2ce3d0a91c68a38c6e1e2fa173d1e0ba559d104ee1622245b54d7740a5d94272","observation_id":"7d36e69e-ec2b-40b0-a47a-f70b16d1c4fe","resolution":{"observed_at":"2026-08-06T20:39:26.397054Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:23.169972Z","title":"Localizing object-level shape variations with text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.169972Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:36148a990ccf2e3d07c7c6101b6d3fdd6e3dd87002fa17c51cc5431afc1d33c1","observation_id":"695a2c0e-6435-4823-9cac-dfc91fec528f","resolution":{"observed_at":"2026-08-06T20:39:23.169972Z","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":"2026-08-06T20:39:29.266446Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis, 2023","venue":null,"work_id":"b6c2ada7-d557-4c6a-b885-0d9d134cf8d2","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.231366Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:97005adbbe9a85364e150c7b3e2cb72e1dcb4010b7adb00d2c8593bb9646d34f","observation_id":"f5a3d6ea-10b4-4aa3-9966-af57197d4c4d","resolution":{"observed_at":"2026-08-06T20:39:29.355284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:29.125200Z","title":"Meta-learning with implicit gradients","venue":null,"work_id":"1810ff42-adb0-4ed1-a679-54e823c83308","year":2019},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.305793Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:cc6d5eebadc16c09cfcb494d5d48d8a431913e144c81e33e74f80072801ee8b2","observation_id":"b4b2a65e-7bdc-4546-aa34-5c29103f5b4c","resolution":{"observed_at":"2026-08-06T20:39:29.176141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:23.365116Z","title":"Zero-shot text-to-image generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.365116Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:bd2ba925369a9b95219226c865b848f9b0bc5767c724801e971c22d10ea1eff5","observation_id":"dc46b9ba-9d31-4594-a940-79364e2c3fed","resolution":{"observed_at":"2026-08-06T20:39:23.365116Z","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":"2026-08-06T20:39:23.451279Z","title":"Hierarchical text-conditional image gener- ation with clip latents, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.451279Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:d76658295336f0971f0e1617a5b6ef0f924a80c47a805e4afe81590707771d1f","observation_id":"9a257532-f8a3-4355-83fc-658783e6bc0f","resolution":{"observed_at":"2026-08-06T20:39:23.451279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.08242","last_updated":"2016-12-25T07:21:38Z","snapshot_observed_at":"2026-08-07T17:10:53.380887Z","submitted_at":"2016-12-25T07:21:38Z","title":"YOLO9000: Better, Faster, Stronger","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.08242","snapshot_observed_at":"2026-08-06T20:39:23.491195Z","title":"YOLO9000: better, faster, stronger","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.491195Z"},"links":{"cited_paper":"/paper/1612.08242","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:c315c13c0ec5736c439b04eadc80290a54061d146f0410140e3dad68604ab271","observation_id":"b235714f-f8aa-4c24-901a-e594e082a5b9","resolution":{"observed_at":"2026-08-06T20:39:23.491195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.02767","last_updated":"2018-04-08T22:27:57Z","snapshot_observed_at":"2026-08-06T11:09:16.409556Z","submitted_at":"2018-04-08T22:27:57Z","title":"YOLOv3: An Incremental Improvement","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.02767","snapshot_observed_at":"2026-08-06T20:39:23.597200Z","title":"Yolov3: An incremental improvement","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.597200Z"},"links":{"cited_paper":"/paper/1804.02767","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:ab0b879259d94118767abcbbdc2877252ab6b85747985392e874c031a0208875","observation_id":"66692a97-c228-4dcf-a1d5-1147d5cfb754","resolution":{"observed_at":"2026-08-06T20:39:23.597200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.02640","last_updated":"2016-05-09T22:22:11Z","snapshot_observed_at":"2026-07-06T04:20:15.965140Z","submitted_at":"2015-06-08T19:52:52Z","title":"You Only Look Once: Unified, Real-Time Object Detection","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.02640","snapshot_observed_at":"2026-08-06T20:39:23.687482Z","title":"Girshick, and Ali Farhadi","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.687482Z"},"links":{"cited_paper":"/paper/1506.02640","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:ca02be5bcce241fe426ee91f82966ec277e2c49fd31e9a480b973f1f56414678","observation_id":"60c4225a-919b-4026-a0a8-8ebfb5af5893","resolution":{"observed_at":"2026-08-06T20:39:23.687482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.09972","last_updated":"2024-05-22T05:05:38Z","snapshot_observed_at":"2026-08-10T13:04:49.713390Z","submitted_at":"2023-05-17T06:11:10Z","title":"Real-Time Flying Object Detection with YOLOv8","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.09972","snapshot_observed_at":"2026-08-06T20:39:23.835177Z","title":"Real-time flying object detection with yolov8","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.835177Z"},"links":{"cited_paper":"/paper/2305.09972","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:ccaa2526ea9d959b59a0c21f1f6e18ad75eaf3a557c52d7b57159beba8764ee0","observation_id":"243bbacb-383d-42bd-a619-e7a9dc5e63be","resolution":{"observed_at":"2026-08-06T20:39:23.835177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.10752","last_updated":"2022-04-13T11:38:44Z","snapshot_observed_at":"2026-07-06T12:20:47.369918Z","submitted_at":"2021-12-20T18:55:25Z","title":"High-Resolution Image Synthesis with Latent Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10752","snapshot_observed_at":"2026-08-06T20:39:23.936345Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:23.936345Z"},"links":{"cited_paper":"/paper/2112.10752","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:b6e22526387ca57349e392490c9cfc69492f7e1ae7285fa78b4d0e484657d964","observation_id":"7345dbcf-18ea-4ba8-bf38-53a36ac2da89","resolution":{"observed_at":"2026-08-06T20:39:23.936345Z","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":"2026-08-06T20:39:24.012973Z","title":"Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.012973Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:074c164e8f71af92813c6499163c1fca842edf6c7ede5be26aa56280f19512ca","observation_id":"2ad1d5fb-1804-4046-b36a-4da489234c38","resolution":{"observed_at":"2026-08-06T20:39:24.012973Z","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":"2026-08-06T20:39:24.077254Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.077254Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:24f6bc15cf9de495f71df655b4e9d40a24c63e824b821794005e11b7c3162d0f","observation_id":"a6c2f10d-2f94-4af6-a302-61d319ac4425","resolution":{"observed_at":"2026-08-06T20:39:24.077254Z","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":"2026-08-06T20:39:28.940736Z","title":"Meta-learning with memory-augmented neural networks","venue":null,"work_id":"1659135b-f35e-4085-b662-2793fdbfa256","year":null},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.151699Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:f9e0cb23f9d31022b1e42de77243afd724bb775f6f3855f7e2d4f7d8a8de46f6","observation_id":"d59562c4-c9c9-4d34-858e-ed94d1e59b8b","resolution":{"observed_at":"2026-08-06T20:39:29.016599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16794","last_updated":"2024-05-09T22:53:10Z","snapshot_observed_at":"2026-08-06T10:20:37.251394Z","submitted_at":"2023-10-25T17:24:38Z","title":"Using Diffusion Models to Generate Synthetic Labelled Data for Medical Image Segmentation","version":2},"cited_work":{"arxiv_id":"2310.16794","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.16794","snapshot_observed_at":"2026-08-06T20:39:26.170131Z","title":"Using Diffusion Models to Generate Synthetic Labelled Data for Medical Image Segmentation","venue":"eess.IV","work_id":"6763b35d-c22e-40e9-8931-6a0c471df818","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.204504Z"},"links":{"cited_paper":"/paper/2310.16794","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:f7ae28f4ceffe48040d31458ab02d5eae4e23aaf6cfd888441779b07f2582724","observation_id":"0863883e-fad4-4aed-81f0-3578d8c636b4","resolution":{"observed_at":"2026-08-06T20:39:26.217186Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"video/5523504","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:39:25.983978Z","title":"How ford uses ai for quality control","venue":null,"work_id":"16a34ecf-43af-4aa1-9a97-ccbe79d47362","year":2025},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.262008Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:5180cd7fa1fca648aca46cc5a1c7ca91194f3538e75667840cfc471eed35fdf5","observation_id":"f2ff70de-26ee-482c-bc7e-c0ed028e55e7","resolution":{"observed_at":"2026-08-06T20:39:26.043285Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.03585","last_updated":"2015-11-18T21:50:51Z","snapshot_observed_at":"2026-07-06T04:11:47.439779Z","submitted_at":"2015-03-12T04:51:37Z","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.03585","snapshot_observed_at":"2026-08-06T20:39:24.348987Z","title":"Weiss, Niru Mah- eswaranathan, and Surya Ganguli","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.348987Z"},"links":{"cited_paper":"/paper/1503.03585","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:debc482f7c6abe9736f2ca473882786d02e2330de69025bc27d2aeead5226d5e","observation_id":"beb921f9-341c-4880-8a30-4ef67e819527","resolution":{"observed_at":"2026-08-06T20:39:24.348987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-06T20:39:24.439186Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.439186Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:b11f326f9aa8cfeac1111257ef5e27722e841490499b9c5b7158bf0d508c7188","observation_id":"a067e855-270e-40ee-8925-50eb4da19b20","resolution":{"observed_at":"2026-08-06T20:39:24.439186Z","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":"2026-08-06T20:39:28.767119Z","title":"Fsce: Few-shot object detection via contrastive pro- posal encoding","venue":null,"work_id":"a999eb25-0b4a-4dbb-9ec9-bd5a6f654470","year":2021},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.509435Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:5cacc1bc7125fdbad4f998d4e93df81f0e73636209feae3c7a503ca6ed3fc423","observation_id":"dbd94184-8835-4582-bb88-157ad0478af1","resolution":{"observed_at":"2026-08-06T20:39:28.848198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04566","last_updated":"2023-12-07T18:59:58Z","snapshot_observed_at":"2026-08-09T22:50:18.803445Z","submitted_at":"2023-12-07T18:59:58Z","title":"Gen2Det: Generate to Detect","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04566","snapshot_observed_at":"2026-08-06T20:39:24.620212Z","title":"Gen2det: Generate to detect","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.620212Z"},"links":{"cited_paper":"/paper/2312.04566","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:88963ec1e2eb672dd4e05907d7c19deeb9233a382283781bab8b8c556d926148","observation_id":"271b50a6-4942-4f27-943a-62d1a8f209c6","resolution":{"observed_at":"2026-08-06T20:39:24.620212Z","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":"2026-08-06T20:39:28.589762Z","title":"Effective data augmentation with diffu- sion models","venue":null,"work_id":"b39aa947-051a-44b3-a66d-27e304632e63","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.670826Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:a2a472bfc39eee10995596405270c612bde9e0839c5d181f53858efd4ae345ad","observation_id":"ad993b3a-752b-4756-9715-2f249e962fef","resolution":{"observed_at":"2026-08-06T20:39:28.671265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:28.415837Z","title":"Magic: Multi-modality guided image completion","venue":null,"work_id":"ce5f84a6-9382-4e69-b582-f6b3814312fb","year":2024},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.731651Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:64bfad6834cd9dd46a9a719c3dbb2627c4f58b86fd912f428b775e70ddbab853","observation_id":"86153594-0958-455d-b298-8007fa346e54","resolution":{"observed_at":"2026-08-06T20:39:28.485495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:28.218641Z","title":"Investigating prompt engineering in diffusion models, 2022","venue":null,"work_id":"fc9d9d47-ea04-4a54-87bd-71921ac787af","year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.810218Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:d572fc24b986c147f48e38b90e85beb6a02d599c51e24d2d42e89c99300439b3","observation_id":"448d43d7-841c-4865-8f9d-5089ffb89911","resolution":{"observed_at":"2026-08-06T20:39:28.312610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06160","last_updated":"2023-10-10T03:59:41Z","snapshot_observed_at":"2026-08-11T09:37:04.395790Z","submitted_at":"2023-08-11T14:38:11Z","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","version":2},"cited_work":{"arxiv_id":"2308.06160","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.06160","snapshot_observed_at":"2026-08-06T20:39:25.693015Z","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","venue":"cs.CV","work_id":"d0112ce2-32ad-4963-aa10-5c43dcdf809f","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.859169Z"},"links":{"cited_paper":"/paper/2308.06160","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:5204ea67784a9d867b0ba10a1b885e083a6ba61c80588a6e7a9f15260b92241e","observation_id":"3d3ba372-c395-4d81-85a3-c03ae11ea2da","resolution":{"observed_at":"2026-08-06T20:39:25.775023Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:28.072021Z","title":"Meta-rcnn: Meta learning for few-shot object detection","venue":null,"work_id":"660cfde2-72b5-4638-aba2-4a44a5315f75","year":2020},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:24.923382Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:2da0b3090ef217f7df9371ba7514e638bd789b92753cb7391f5f3c5f64025789","observation_id":"ac5377db-b222-49ba-a7aa-422770436751","resolution":{"observed_at":"2026-08-06T20:39:28.153416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11550","last_updated":"2023-02-22T18:47:51Z","snapshot_observed_at":"2026-08-11T09:48:55.827823Z","submitted_at":"2023-02-22T18:47:51Z","title":"Scaling Robot Learning with Semantically Imagined Experience","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11550","snapshot_observed_at":"2026-08-06T20:39:25.029975Z","title":"Scaling robot learning with semantically imagined experi- ence","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.029975Z"},"links":{"cited_paper":"/paper/2302.11550","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:962403ae3175f5af87ee5155035bb0bfb3869bb5dccbb0df2e19692508974334","observation_id":"1a398493-b803-4728-8c9d-13c43d1f803b","resolution":{"observed_at":"2026-08-06T20:39:25.029975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.03605","last_updated":"2022-07-11T10:30:29Z","snapshot_observed_at":"2026-08-07T03:38:32.486362Z","submitted_at":"2022-03-07T18:55:26Z","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.03605","snapshot_observed_at":"2026-08-06T20:39:25.114871Z","title":"Dino: Detr with improved denoising anchor boxes for end- to-end object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.114871Z"},"links":{"cited_paper":"/paper/2203.03605","citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:613e60484c04a98486bc96e709362255a5335746264400245760dc3f99cd3d10","observation_id":"215791eb-4f06-4e84-a519-0f87dfdbfc2f","resolution":{"observed_at":"2026-08-06T20:39:25.114871Z","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":"2026-08-06T20:39:27.949721Z","title":"Adding conditional control to text-to-image diffusion models, 2023","venue":null,"work_id":"5936882c-1471-4947-8035-29137f82db4b","year":2023},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.226407Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:9fa5e86dafc6711fa749c7b5928af31bd4964dd573146cb77e5afc15fbbf631c","observation_id":"e26a57a7-af9b-4f4c-8a4d-a372b390d98e","resolution":{"observed_at":"2026-08-06T20:39:28.015329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:27.785458Z","title":"Rethinking pre- training and self-training","venue":null,"work_id":"a63451e2-19bf-4468-bdbf-6ce5d9b5f83f","year":2020},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.327414Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:64795daf8507db89dc8d18b00be47b8a761a84fa078711aead55ccabbad20ca7","observation_id":"a004189a-9b45-4168-81a8-4298e7317e4e","resolution":{"observed_at":"2026-08-06T20:39:27.875387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:27.587470Z","title":"These datasets are chosen to span a representative set of tasks that re- searchers and practitioners use when training and evaluat- ing object detection models","venue":null,"work_id":"d6cac6a8-c2b4-4c0f-9ee1-ac35c710b5b0","year":null},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.410156Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:50036b444d426240a5303560b9f9790c0cbf23a026a7018e0490e7ef67fdcfe9","observation_id":"bb34534d-22fa-4af9-92a7-3ce53765dbaf","resolution":{"observed_at":"2026-08-06T20:39:27.675423Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:27.371118Z","title":"g e n e r a t i o n prompt","venue":null,"work_id":"20cbd5af-9c97-4e5f-b19e-6f98b7dd15d6","year":2014},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.485989Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:5ff792409d547eb4954289f68c4feb76717c33b8216235680289b3907946b2b2","observation_id":"f9da5b30-eda2-454d-9ce5-c81d2dd56153","resolution":{"observed_at":"2026-08-06T20:39:27.499501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:27.243320Z","title":null,"venue":null,"work_id":"03aa1ae2-e2be-4de8-ab7a-dc452eed74d9","year":null},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:25.574270Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:f1b1b1ee0470856996fa53d1b0b3f1b8b012b2f4126d69a6a31f013b725fdf7c","observation_id":"9e075bca-2890-4d1f-93a0-404687e91da7","resolution":{"observed_at":"2026-08-06T20:39:27.276899Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T20:39:29.773578Z","title":null,"venue":null,"work_id":"24043b4e-a048-454f-a1ba-341018ec388d","year":null},"citing_paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:22.311891Z"},"links":{"citing_paper":"/paper/2507.02217"},"observation_digest":"sha256:130ddc911767e89a0364eaf6d9fba0e543732ace512ee6ddf745fb8361fd067c","observation_id":"538f8777-9500-46a4-a50c-c06bd4e94b48","resolution":{"observed_at":"2026-08-06T20:39:29.846264Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.02217","last_updated":"2025-07-03T00:44:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T13:51:07.227319Z","submitted_at":"2025-07-03T00:44:31Z","title":"Understanding Trade offs When Conditioning Synthetic Data"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":35,"verified_exact":10,"verified_fuzzy":27},"total_outbound_references":72},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 0 inbound Pith citation observations for arXiv:2507.02217."}