{"as_of":"2026-08-18T00:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8fbe5afba5adbf0eeb72689f70d8a733220df9e11b7299911bc0708c9643a944","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":60,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:16:41.468412Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T20:00:08.947700Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2211.05100","last_updated":"2023-06-27T09:57:58Z","snapshot_observed_at":"2026-08-04T18:56:03.233715Z","submitted_at":"2022-11-09T18:48:09Z","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","version":4},"reference_index":285,"source":"arxiv_source","source_observed_at":"2026-05-12T00:51:10.919818Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2211.05100"},"observation_digest":"sha256:e63484306fa346bdfe8a9889ddcc1159a61ce925bd7110cf3753f6acfae9bd32","observation_id":"34966529-0331-4e3e-beb2-7ed4c2504adf","resolution":{"observed_at":"2026-05-12T00:51:11.651426Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2212.03533","last_updated":"2024-02-22T06:21:51Z","snapshot_observed_at":"2026-07-06T14:27:46.217000Z","submitted_at":"2022-12-07T09:25:54Z","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-11T04:54:03.524365Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2212.03533"},"observation_digest":"sha256:d4dac76f9be3197abc24f2ce24c99e460a1d1e4d27df1758fa6144389bfcaa3b","observation_id":"96d92214-4d66-4394-80ea-56d9ecc53c45","resolution":{"observed_at":"2026-05-11T04:54:03.911556Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2301.12652","last_updated":"2023-05-24T05:08:07Z","snapshot_observed_at":"2026-08-17T20:02:13.545674Z","submitted_at":"2023-01-30T04:18:09Z","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","version":4},"reference_index":210,"source":"arxiv_source","source_observed_at":"2026-05-17T12:41:53.833754Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2301.12652"},"observation_digest":"sha256:49384de9a0265b110c9cdcb915d72625a261fff654e3a901aa004a54ae40b42d","observation_id":"5bed0fca-3592-4485-9978-0aaa009533d4","resolution":{"observed_at":"2026-05-17T12:41:54.074982Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2305.16264","last_updated":"2025-06-28T00:00:06Z","snapshot_observed_at":"2026-08-08T06:18:27.640980Z","submitted_at":"2023-05-25T17:18:55Z","title":"Scaling Data-Constrained Language Models","version":5},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-18T01:35:21.150772Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2305.16264"},"observation_digest":"sha256:ba25802c6e7cbf7279b6a8ffd907296ec02d2e3ab74c1733f7a9dc2232052351","observation_id":"86256686-d8c4-4294-8155-b75338026e81","resolution":{"observed_at":"2026-05-18T01:35:21.291905Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2309.07597","last_updated":"2024-09-24T03:01:25Z","snapshot_observed_at":"2026-08-18T00:19:33.067213Z","submitted_at":"2023-09-14T10:57:50Z","title":"C-Pack: Packed Resources For General Chinese Embeddings","version":5},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-13T13:24:32.084878Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2309.07597"},"observation_digest":"sha256:fc54d9987c0d88b6a4b816cc58478f58dd3fc8bfa6bd1717e438fb4222683f70","observation_id":"71154c46-f252-4385-9a5e-2a25c0133e28","resolution":{"observed_at":"2026-05-13T13:24:32.237268Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2401.03563","last_updated":"2024-01-07T18:12:20Z","snapshot_observed_at":"2026-08-13T14:53:53.114971Z","submitted_at":"2024-01-07T18:12:20Z","title":"Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-05-24T04:29:05.113230Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2401.03563"},"observation_digest":"sha256:ed78cdce63a680b4c595378acd8c9f71d116e04333942337debdcdad2746fe2e","observation_id":"63450b7d-c7f6-4347-aaf9-756605d137df","resolution":{"observed_at":"2026-05-24T04:33:53.938592Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2402.03216","last_updated":"2025-12-12T11:26:32Z","snapshot_observed_at":"2026-08-17T15:25:09.479397Z","submitted_at":"2024-02-05T17:26:49Z","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","version":5},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-11T22:39:02.540687Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2402.03216"},"observation_digest":"sha256:3d41df9d782b1b80d6d0bd2d2a4a0f7945baeb9af2f65e1d57158e4d71c3868e","observation_id":"08741de0-3022-4f57-9dcf-09803bdd259b","resolution":{"observed_at":"2026-05-11T22:39:03.394178Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2404.10981","last_updated":"2024-08-23T00:17:02Z","snapshot_observed_at":"2026-08-14T10:51:21.055151Z","submitted_at":"2024-04-17T01:27:42Z","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","version":2},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-05-24T02:15:05.379583Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2404.10981"},"observation_digest":"sha256:166d3ef85d87979c5daad6ef951ac569ce035621fc836a8663e8ccf13945d17c","observation_id":"0aee197b-7a0b-4af3-855f-7a6cb7f46256","resolution":{"observed_at":"2026-05-24T02:15:55.525831Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2407.12580","last_updated":"2024-07-17T14:04:12Z","snapshot_observed_at":"2026-08-17T17:47:50.871594Z","submitted_at":"2024-07-17T14:04:12Z","title":"E5-V: Universal Embeddings with Multimodal Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-16T22:52:20.935555Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2407.12580"},"observation_digest":"sha256:8b9b9cd13d3c52a509a8b2f2367186c3f6a43044f97d0148629efd133c2a3938","observation_id":"aa1c4960-6447-4ac5-86cb-1bb3655fda06","resolution":{"observed_at":"2026-05-16T22:52:20.985589Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2410.05229","last_updated":"2025-08-27T16:24:39Z","snapshot_observed_at":"2026-08-16T08:54:56.543625Z","submitted_at":"2024-10-07T17:36:37Z","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","version":2},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-05-15T00:42:11.891829Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2410.05229"},"observation_digest":"sha256:2d5f60d1fd441e8d7e62c8802a2fb3cda8b817c61836c25b81c6618fa1d64c2e","observation_id":"5e9c58fc-4b2d-4836-a973-706a81912c66","resolution":{"observed_at":"2026-05-15T00:42:12.072713Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2410.10594","last_updated":"2025-03-02T01:19:51Z","snapshot_observed_at":"2026-08-13T17:45:25.269133Z","submitted_at":"2024-10-14T15:04:18Z","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-16T15:37:25.781240Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2410.10594"},"observation_digest":"sha256:8d4e266f41a64a805132eee7d3a9825cced20dceeb982cc381e4195d5ea843a8","observation_id":"b36cc0c2-9875-4336-8945-83407a0d679e","resolution":{"observed_at":"2026-05-16T15:37:25.918229Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-12T18:44:55.062960Z","title":"Sgpt: Gpt sentence embeddings for semantic search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.12584","last_updated":"2025-06-08T06:36:03Z","snapshot_observed_at":"2026-08-16T12:21:05.949537Z","submitted_at":"2024-11-18T07:55:54Z","title":"Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T18:44:55.062960Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2411.12584"},"observation_digest":"sha256:9028d28e44d5949db2088d87b61c9726f37a306553842c47e1f5ca9bc7310ec9","observation_id":"a59c5344-c222-4296-b086-24b43976d90a","resolution":{"observed_at":"2026-08-12T18:44:55.062960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-12T05:16:44.319482Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.00600","last_updated":"2024-11-30T22:22:26Z","snapshot_observed_at":"2026-08-13T04:13:02.295187Z","submitted_at":"2024-11-30T22:22:26Z","title":"DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T05:16:44.319482Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.00600"},"observation_digest":"sha256:d2d87264f0da7daca9bab0631b0ae04bbc51d33aadb49ce24ded82971743e061","observation_id":"7219c10b-52f0-4ec0-b832-6ba023706605","resolution":{"observed_at":"2026-08-12T05:16:44.319482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-11T17:34:07.766721Z","title":"SGPT: GPT sentence embeddings for semantic search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08873","last_updated":"2024-12-12T02:13:53Z","snapshot_observed_at":"2026-08-16T19:00:11.548246Z","submitted_at":"2024-12-12T02:13:53Z","title":"Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning model","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T17:34:07.766721Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.08873"},"observation_digest":"sha256:1b65bd0614cc353a8535bcfb0f3a78d472f49a0c396bdac6a2d7c1a3405db4f0","observation_id":"c3665ea1-2849-4414-a2c7-73cc427fb723","resolution":{"observed_at":"2026-08-11T17:34:07.766721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-11T15:48:27.997352Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.10684","last_updated":"2024-12-14T05:06:43Z","snapshot_observed_at":"2026-08-13T12:49:37.962352Z","submitted_at":"2024-12-14T05:06:43Z","title":"Inference Scaling for Bridging Retrieval and Augmented Generation","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T15:48:27.997352Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.10684"},"observation_digest":"sha256:6e0334a0c3a10c1dd14db444ba305e9701bad88ad5a5b7c9f41102251c26f172","observation_id":"f20c4578-99de-463c-a00d-6c75107f9500","resolution":{"observed_at":"2026-08-11T15:48:27.997352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-11T15:20:47.209922Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11087","last_updated":"2024-12-15T07:09:02Z","snapshot_observed_at":"2026-08-16T18:59:59.725410Z","submitted_at":"2024-12-15T07:09:02Z","title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-11T15:20:47.209922Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.11087"},"observation_digest":"sha256:6691da3a02458a3dac9e8bc9efd17d0534f5ed4112344060f975f13c5fe9cf3f","observation_id":"8cbbff1d-dbc6-4e95-84c2-f9d74f256452","resolution":{"observed_at":"2026-08-11T15:20:47.209922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-11T13:59:01.804625Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.12591","last_updated":"2025-07-25T09:22:04Z","snapshot_observed_at":"2026-08-17T03:32:19.895448Z","submitted_at":"2024-12-17T06:48:24Z","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","version":2},"reference_index":118,"source":"pdf_text","source_observed_at":"2026-08-11T13:59:01.804625Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.12591"},"observation_digest":"sha256:dcf26ef8329dd0f70507c919869dac1fd9f684da6f371a3282926dafcee8a13d","observation_id":"b47dbdf4-c792-4781-b28c-5d1e5cb9fd39","resolution":{"observed_at":"2026-08-11T13:59:01.804625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-11T10:29:26.630537Z","title":"arXiv preprint arXiv:2202.08904 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16615","last_updated":"2025-04-09T14:08:58Z","snapshot_observed_at":"2026-08-16T20:46:17.223535Z","submitted_at":"2024-12-21T13:19:15Z","title":"Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T10:29:26.630537Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.16615"},"observation_digest":"sha256:8eee7a914bc388b521cad3f71f8573ff38a8f0de85f9a49d8ff36d735731afae","observation_id":"034e44b8-85ed-4cec-b30b-f3e4f0254cf7","resolution":{"observed_at":"2026-08-11T10:29:26.630537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-11T01:03:28.362818Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19048","last_updated":"2025-01-23T16:01:22Z","snapshot_observed_at":"2026-08-14T12:39:51.256172Z","submitted_at":"2024-12-26T04:05:28Z","title":"Jasper and Stella: distillation of SOTA embedding models","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-11T01:03:28.362818Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2412.19048"},"observation_digest":"sha256:82fdbd893b2717d49cc7fcfe507ba7bde263b7d37006ff49a67ae230905a407d","observation_id":"6ce23c6c-bbad-4c38-9e8f-b4ea6231b7ef","resolution":{"observed_at":"2026-08-11T01:03:28.362818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-10T14:32:37.971227Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15245","last_updated":"2025-01-25T15:27:40Z","snapshot_observed_at":"2026-08-17T19:44:46.569532Z","submitted_at":"2025-01-25T15:27:40Z","title":"ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T14:32:37.971227Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2501.15245"},"observation_digest":"sha256:01bdde2e834002b45c6e7031e7e402e6b4bd6445955ef89dcc84aec93477bfd6","observation_id":"7b2b514f-6c74-4bcd-898b-5372e29ae7c9","resolution":{"observed_at":"2026-08-10T14:32:37.971227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-16T05:16:41.468412Z","title":"Sgpt: Gpt sentence embeddings for semantic search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21239","last_updated":"2025-04-30T00:28:32Z","snapshot_observed_at":"2026-08-16T18:40:13.764415Z","submitted_at":"2025-04-30T00:28:32Z","title":"Memorization and Knowledge Injection in Gated LLMs","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-16T05:16:41.468412Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2504.21239"},"observation_digest":"sha256:34aeb963bca3193619ba49c1daadbb70a79bcd1ea61d1e48ef6a0a8a5f2ac424","observation_id":"46f70e97-56fe-482e-9418-060547062790","resolution":{"observed_at":"2026-08-16T05:16:41.468412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-15T20:36:12.506398Z","title":"Sgpt: Gpt sentence embeddings for semantic search.arXiv preprint arXiv:2202.08904, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12535","last_updated":"2025-05-18T20:26:55Z","snapshot_observed_at":"2026-08-15T20:29:16.033844Z","submitted_at":"2025-05-18T20:26:55Z","title":"Framework of Voting Prediction of Parliament Members","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:36:12.506398Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2505.12535"},"observation_digest":"sha256:d6f826e0da7363a361d66f0e50d9ede2ef82b063a4c8438808c0306da0b9238c","observation_id":"856edb02-a9a3-4ea6-9d63-01082cde6c23","resolution":{"observed_at":"2026-08-15T20:36:12.506398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-15T20:31:59.041137Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.12731","last_updated":"2025-05-25T13:03:54Z","snapshot_observed_at":"2026-08-16T13:37:19.640411Z","submitted_at":"2025-05-19T05:39:38Z","title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T20:31:59.041137Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2505.12731"},"observation_digest":"sha256:a48b1a94090794aa13ba5842cd1bbad2c2b2ff57c7bf8123486bd7aec8ee1697","observation_id":"1f8b3c63-c403-4184-b8ac-b677c3cfba6a","resolution":{"observed_at":"2026-08-15T20:31:59.041137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-07T15:08:12.708792Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17136","last_updated":"2025-05-22T05:21:31Z","snapshot_observed_at":"2026-08-09T03:48:20.204984Z","submitted_at":"2025-05-22T05:21:31Z","title":"Foundation Models for Geospatial Reasoning: Assessing Capabilities of Large Language Models in Understanding Geometries and Topological Spatial Relations","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-07T15:08:12.708792Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2505.17136"},"observation_digest":"sha256:956b247eca3a4af747c28ba35216a29139a212580dc62bc599a211c37d0208ec","observation_id":"26bfd8fb-7f95-4ff1-ad71-76ea354e4c32","resolution":{"observed_at":"2026-08-07T15:08:12.708792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-07T11:56:18.715900Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.01074","last_updated":"2025-06-01T16:24:13Z","snapshot_observed_at":"2026-08-15T04:49:33.544748Z","submitted_at":"2025-06-01T16:24:13Z","title":"How Programming Concepts and Neurons Are Shared in Code Language Models","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T11:56:18.715900Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2506.01074"},"observation_digest":"sha256:0314f44b2e5229d3b1b8b5cb337228f7bfcad23ba408931f9fb8770c6b03a4fe","observation_id":"aff85913-1a16-4146-9d7a-ade1bfca5968","resolution":{"observed_at":"2026-08-07T11:56:18.715900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-07T11:49:14.117542Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.01435","last_updated":"2025-06-02T08:50:38Z","snapshot_observed_at":"2026-08-15T09:57:01.401234Z","submitted_at":"2025-06-02T08:50:38Z","title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T11:49:14.117542Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2506.01435"},"observation_digest":"sha256:dfdcddbd023fc826745249ae5b6a62306a128361e948a21687ea3b0df99f352b","observation_id":"3660d1ea-cc2f-4db8-b680-ee3624f9cfcd","resolution":{"observed_at":"2026-08-07T11:49:14.117542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-07T05:18:26.603511Z","title":"Sgpt: Gpt sentence embeddings for se- mantic search.arXiv preprint arXiv:2202.08904,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.08354","last_updated":"2026-05-28T08:13:47Z","snapshot_observed_at":"2026-08-10T06:36:57.892160Z","submitted_at":"2025-06-10T02:11:42Z","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T05:18:26.603511Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2506.08354"},"observation_digest":"sha256:6d60b9e14cb464137e4f04e4c62f0ca61d5a6d28782ffde52527c9d9a2c11e64","observation_id":"42c06864-583b-4db2-b520-27bbe4b053a3","resolution":{"observed_at":"2026-08-07T05:18:26.603511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-07T01:03:45.996887Z","title":"Sgpt: Gpt sentence embeddings for se- mantic search.arXiv preprint arXiv:2202.08904,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12149","last_updated":"2025-06-13T18:08:54Z","snapshot_observed_at":"2026-08-16T02:03:45.147473Z","submitted_at":"2025-06-13T18:08:54Z","title":"Maximally-Informative Retrieval for State Space Model Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T01:03:45.996887Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2506.12149"},"observation_digest":"sha256:b3d780ce7d8cd5559887e2ea4a158c15cbfc0ecd755580d535859a5d59cc5656","observation_id":"44e5e7e5-209f-4799-a32c-15fde8f20cb3","resolution":{"observed_at":"2026-08-07T01:03:45.996887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-07T13:18:31.986084Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.15697","last_updated":"2025-05-28T09:28:39Z","snapshot_observed_at":"2026-08-14T08:12:28.128149Z","submitted_at":"2025-05-28T09:28:39Z","title":"DeepRTL2: A Versatile Model for RTL-Related Tasks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T13:18:31.986084Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2506.15697"},"observation_digest":"sha256:76ee0683884543681babbe2f3edd636fab9a161173300b9885ec96e442df80c6","observation_id":"0094b706-ad47-4201-8aaf-3f26712c8e47","resolution":{"observed_at":"2026-08-07T13:18:31.986084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-15T20:05:22.758107Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.21579","last_updated":"2025-06-16T13:27:06Z","snapshot_observed_at":"2026-08-17T11:11:36.144227Z","submitted_at":"2025-06-16T13:27:06Z","title":"LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:05:22.758107Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2506.21579"},"observation_digest":"sha256:7044f5fd9099a381c31713e6a8f0a7b52d3859a5584c8b8b74bb38ebc904b6bf","observation_id":"7736b3b5-28c1-4b19-951d-654a16101178","resolution":{"observed_at":"2026-08-15T20:05:22.758107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2507.00994","last_updated":"2026-05-05T08:00:08Z","snapshot_observed_at":"2026-08-17T01:19:17.344110Z","submitted_at":"2025-07-01T17:45:48Z","title":"Should We Still Pretrain Encoders with Masked Language Modeling?","version":4},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-19T06:31:37.201344Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2507.00994"},"observation_digest":"sha256:97b4bb05ffacd82bfc9d24ae66a4410d0409919e5e1b4e2c0f2ec90e7bccfe52","observation_id":"eb9de2b0-092b-4538-83b6-4449d216415e","resolution":{"observed_at":"2026-05-19T06:32:07.676641Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-06T15:50:39.050730Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.14900","last_updated":"2025-07-23T14:32:32Z","snapshot_observed_at":"2026-08-17T23:01:22.734144Z","submitted_at":"2025-07-20T10:23:22Z","title":"From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T15:50:39.050730Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2507.14900"},"observation_digest":"sha256:136b9d9bf9ff5e165680f58965c1b32a9c99f4c9a2b4745e86bc2a89a51ab225","observation_id":"27301393-2fec-4210-81ed-03f4032aba43","resolution":{"observed_at":"2026-08-06T15:50:39.050730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2507.23386","last_updated":"2026-05-02T08:43:04Z","snapshot_observed_at":"2026-08-15T03:34:22.343885Z","submitted_at":"2025-07-31T10:01:11Z","title":"Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-19T02:19:20.792488Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2507.23386"},"observation_digest":"sha256:02e519b73c19edd9db6b0a7e4bef4fa6d6e5527336dad3acdd9d017ea9cf064a","observation_id":"c5ee6d93-c473-4458-95bf-c8f144b46676","resolution":{"observed_at":"2026-05-19T02:21:59.315206Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-05T19:49:50.951796Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.11779","last_updated":"2025-08-15T19:05:57Z","snapshot_observed_at":"2026-08-15T16:42:11.680725Z","submitted_at":"2025-08-15T19:05:57Z","title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T19:49:50.951796Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2508.11779"},"observation_digest":"sha256:2ea188239fbc9d0628f0740a982c051fca301cf65a806b76a9c6fae8741b1f27","observation_id":"03998d73-bf24-4c42-ad87-6b7fd8de203c","resolution":{"observed_at":"2026-08-05T19:49:50.951796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-15T17:25:07.498163Z","title":"Muennighoff","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.12769","last_updated":"2025-08-20T08:11:10Z","snapshot_observed_at":"2026-08-17T19:42:10.109951Z","submitted_at":"2025-08-18T09:43:07Z","title":"CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T17:25:07.498163Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2508.12769"},"observation_digest":"sha256:0aad76386f0a824ce52abfd2754a61c3d72d1e0cf3c433d3e4d1da56b360b551","observation_id":"9380fdbd-e4a6-4087-baaa-b0509e911cc1","resolution":{"observed_at":"2026-08-15T17:25:07.498163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-05T13:16:26.789418Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00842","last_updated":"2025-08-31T13:24:48Z","snapshot_observed_at":"2026-08-10T10:00:21.871402Z","submitted_at":"2025-08-31T13:24:48Z","title":"Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-05T13:16:26.789418Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2509.00842"},"observation_digest":"sha256:e0520eebf1d648107dd0568b78a83f12206241bf114fdfc8efc32f34df3d2747","observation_id":"09b06ec1-b377-411c-9d67-8738e05ed4f7","resolution":{"observed_at":"2026-08-05T13:16:26.789418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-15T16:32:08.522684Z","title":"Sgpt: Gpt sentence embeddings for semantic search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.04442","last_updated":"2025-09-04T17:59:06Z","snapshot_observed_at":"2026-08-16T04:25:40.473764Z","submitted_at":"2025-09-04T17:59:06Z","title":"Delta Activations: A Representation for Finetuned Large Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T16:32:08.522684Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2509.04442"},"observation_digest":"sha256:5219a172343535e323d552faf7a266192415ba22bd4e7a9785a5dd23e082a3e1","observation_id":"de136e09-f7bd-47a6-8606-0ce3b6abd8da","resolution":{"observed_at":"2026-08-15T16:32:08.522684Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-05T05:14:15.051689Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05691","last_updated":"2025-09-06T11:44:26Z","snapshot_observed_at":"2026-08-13T14:14:40.815703Z","submitted_at":"2025-09-06T11:44:26Z","title":"Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T05:14:15.051689Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2509.05691"},"observation_digest":"sha256:7733dc1c677273c90aa94d72de6d5d45be3f58ffb7e6f45ba365cd81b7cccb29","observation_id":"b49bf0eb-1a14-403a-803a-80f3b37c37b2","resolution":{"observed_at":"2026-08-05T05:14:15.051689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-04T23:33:41.675399Z","title":"Sgpt: Gpt sentence embeddings for semantic search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.06524","last_updated":"2025-09-08T10:30:58Z","snapshot_observed_at":"2026-08-16T02:46:12.661756Z","submitted_at":"2025-09-08T10:30:58Z","title":"LAMDAS: LLM as an Implicit Classifier for Domain-specific Data Selection","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T23:33:41.675399Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2509.06524"},"observation_digest":"sha256:f3801fb814ca4aa0e12d96510acbecff33ea2c2c016917883961714b70d3986e","observation_id":"5e28398d-e475-4374-a303-2403924068b6","resolution":{"observed_at":"2026-08-04T23:33:41.675399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2510.07048","last_updated":"2026-04-09T10:25:15Z","snapshot_observed_at":"2026-08-15T04:55:52.162621Z","submitted_at":"2025-10-08T14:16:20Z","title":"Search-R3: Unifying Reasoning and Embedding in Large Language Models","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-18T09:25:06.990685Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2510.07048"},"observation_digest":"sha256:3e45642d69b9c1c18eb2ac2c5a516ea656353d697a3d358383992b0701b2b4f1","observation_id":"6a829270-bbc4-4955-a012-17ee07d520ee","resolution":{"observed_at":"2026-05-18T09:26:10.566813Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-03T05:42:34.849192Z","title":"SGPT: GPT sentence embeddings for semantic search.CoRR, abs/2202.08904,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01572","last_updated":"2026-06-11T07:39:08Z","snapshot_observed_at":"2026-08-07T20:31:28.365208Z","submitted_at":"2026-02-02T03:09:37Z","title":"LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T05:42:34.849192Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2602.01572"},"observation_digest":"sha256:4722161d01ba0420a14878ee60963543343a5a2b37f04aafec54e20fda4152f8","observation_id":"56116c35-93b5-462d-8ad4-e1e0976d4825","resolution":{"observed_at":"2026-08-03T05:42:34.849192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-02T23:11:03.451302Z","title":"Sgpt: Gpt sentence embeddings for semantic search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.14696","last_updated":"2026-06-18T11:23:03Z","snapshot_observed_at":"2026-08-17T14:22:15.774101Z","submitted_at":"2026-02-16T12:33:05Z","title":"A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-02T23:11:03.451302Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2602.14696"},"observation_digest":"sha256:b7d36ee3e573148464487d8426881a950986d1d6f75b60c79a7b286d64032e26","observation_id":"ec196aff-ff46-499c-abbd-f2c52427b0db","resolution":{"observed_at":"2026-08-02T23:11:03.451302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2604.15591","last_updated":"2026-07-28T19:00:01Z","snapshot_observed_at":"2026-08-15T05:19:23.782401Z","submitted_at":"2026-04-17T00:09:01Z","title":"BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T09:29:25.348098Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2604.15591"},"observation_digest":"sha256:c0abb6e94d9239f43f7ab240e129d0e78fb3471c15189c465d49affb3c650b20","observation_id":"c5360ccf-3754-4242-9372-edd5320bf599","resolution":{"observed_at":"2026-05-10T09:33:41.558106Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-02T16:11:35.631613Z","title":"Bioinformatics, 36(4):1234–1240","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.15591","last_updated":"2026-07-28T19:00:01Z","snapshot_observed_at":"2026-08-15T05:19:23.782401Z","submitted_at":"2026-04-17T00:09:01Z","title":"BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T16:11:35.631613Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2604.15591"},"observation_digest":"sha256:fec1b103ccb44dec7daf8095670d175fa278a8300fb782049e46e3ec0457574c","observation_id":"18929184-55eb-40aa-bc6e-38746a239af8","resolution":{"observed_at":"2026-08-02T16:11:35.631613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2604.23336","last_updated":"2026-05-13T17:26:47Z","snapshot_observed_at":"2026-08-15T10:47:45.127687Z","submitted_at":"2026-04-25T14:45:33Z","title":"Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-08T07:23:56.105372Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2604.23336"},"observation_digest":"sha256:078759ffb13b351c4c1fb16705e978e49ce498920877a7a67404997e58c6e4a5","observation_id":"c30d1204-6f33-4de6-abb4-d10ff8a261c3","resolution":{"observed_at":"2026-05-11T21:01:12.003438Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2604.23336","last_updated":"2026-05-13T17:26:47Z","snapshot_observed_at":"2026-08-15T10:47:45.127687Z","submitted_at":"2026-04-25T14:45:33Z","title":"Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-14T21:09:39.821912Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2604.23336"},"observation_digest":"sha256:c8fb5a44f2b7a1c218eb552340a313141187c3a58b383abccfdfea5ef818c613","observation_id":"fa8c8b96-8dd2-4fde-b42e-f68a02249ae5","resolution":{"observed_at":"2026-05-14T21:18:00.282744Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2605.01372","last_updated":"2026-05-02T10:31:01Z","snapshot_observed_at":"2026-08-14T08:13:52.983918Z","submitted_at":"2026-05-02T10:31:01Z","title":"Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-05-09T15:03:33.323423Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2605.01372"},"observation_digest":"sha256:c4f6186f08f43f53330320f85da7781e02e01df5a00b5d0cba2ed657bfce1791","observation_id":"64bf5e0c-5c99-4483-a0b8-305cba44e054","resolution":{"observed_at":"2026-05-11T16:46:14.740168Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2605.04962","last_updated":"2026-05-06T14:22:34Z","snapshot_observed_at":"2026-08-16T04:45:32.321983Z","submitted_at":"2026-05-06T14:22:34Z","title":"TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-05-08T16:17:51.948423Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2605.04962"},"observation_digest":"sha256:262934e63addf2dc74c35473f11f91bb26a1de690e6bcd2dd5c268e722499a4f","observation_id":"54b1174e-811b-485a-887f-7925e2421203","resolution":{"observed_at":"2026-05-11T18:21:06.658045Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2605.18766","last_updated":"2026-04-12T14:53:56Z","snapshot_observed_at":"2026-08-14T13:23:27.490794Z","submitted_at":"2026-04-12T14:53:56Z","title":"Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-05-21T01:07:54.061446Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2605.18766"},"observation_digest":"sha256:bbe0badbae36b1c65e7e6d223d154fa5c43564c90c2d57562b61811ab0842eb1","observation_id":"00faba44-53ac-4273-8b60-ce4f0a780180","resolution":{"observed_at":"2026-05-21T01:09:20.381554Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2606.00203","last_updated":"2026-05-29T17:29:15Z","snapshot_observed_at":"2026-08-01T03:32:25.296095Z","submitted_at":"2026-05-29T17:29:15Z","title":"DeSQ: Decomposition-based SPARQL Query Generation","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-06-28T22:15:13.878078Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2606.00203"},"observation_digest":"sha256:a84702764d1c19ea9f0b3719df7f3e1d8b0c28b2a928499dcca67997dd8a61ce","observation_id":"e4295039-51c2-4734-a93d-2203139fb1be","resolution":{"observed_at":"2026-07-01T19:36:09.122993Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2606.05858","last_updated":"2026-06-04T08:30:49Z","snapshot_observed_at":"2026-08-05T08:55:18.130915Z","submitted_at":"2026-06-04T08:30:49Z","title":"ReverseEOL: Improving Training-free Text Embeddings via Text Reversal in Decoder-only LLMs","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-06-28T01:44:21.625514Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2606.05858"},"observation_digest":"sha256:15229d4725c938533254e4d4dd8afc5a37bbb9f478bd4638edb2b757bcd4ab6c","observation_id":"bb16ae91-7986-4275-a798-34e4e225a903","resolution":{"observed_at":"2026-07-02T12:56:57.170057Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":"2202.08904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-04T20:00:08.947700Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":"45404afb-6bc9-462c-b308-08ed51352de6","year":2022},"citing_paper":{"arxiv_id":"2606.25674","last_updated":"2026-07-22T12:59:40Z","snapshot_observed_at":"2026-08-02T10:15:52.954015Z","submitted_at":"2026-06-24T10:37:01Z","title":"BitNet Text Embeddings","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-25T20:48:30.687676Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2606.25674"},"observation_digest":"sha256:3c14ac12725e0e0ebdda6a410fa52acb5a145ae5eeb527fcb38f44964b7c03c1","observation_id":"3072619f-77d0-402a-8740-49e461e8bb15","resolution":{"observed_at":"2026-07-04T20:00:08.951461Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-02T10:15:53.815736Z","title":"Sgpt: Gpt sentence embeddings for semantic search.arXiv preprint arXiv:2202.08904, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.25674","last_updated":"2026-07-22T12:59:40Z","snapshot_observed_at":"2026-08-02T10:15:52.954015Z","submitted_at":"2026-06-24T10:37:01Z","title":"BitNet Text Embeddings","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T10:15:53.815736Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2606.25674"},"observation_digest":"sha256:8ae49072c536edaaee57d1ec74d3c18d2f1f67424ee1469ca53a69c60cea1d2f","observation_id":"6a1a9e08-cdc5-497c-a720-c28ca48dea16","resolution":{"observed_at":"2026-08-02T10:15:53.815736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-07-30T20:41:36.268379Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.23507","last_updated":"2026-07-26T07:13:33Z","snapshot_observed_at":"2026-08-14T15:05:38.726614Z","submitted_at":"2026-07-26T07:13:33Z","title":"Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-30T20:41:36.268379Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2607.23507"},"observation_digest":"sha256:e235b1952b798fc47f0a1c9787dad967f0ecf466d06b7e46742153786243c7d0","observation_id":"04495888-35ad-4922-9dc7-14702b88c2b2","resolution":{"observed_at":"2026-07-30T20:41:36.268379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-01T02:03:23.576130Z","title":"8 Niklas Muennighoff","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.25579","last_updated":"2026-07-28T11:05:46Z","snapshot_observed_at":"2026-08-16T23:26:16.285392Z","submitted_at":"2026-07-28T11:05:46Z","title":"IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T02:03:23.576130Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2607.25579"},"observation_digest":"sha256:4cd4b0fcbe02e85aebec02fbb8c6327c8b1d6fc64874bc396edded527eca5778","observation_id":"7a355d62-32de-4570-bfa0-7f564b1602e2","resolution":{"observed_at":"2026-08-01T02:03:23.576130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-04T07:49:39.867194Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.02415","last_updated":"2026-08-03T15:53:49Z","snapshot_observed_at":"2026-08-17T06:34:39.162836Z","submitted_at":"2026-08-03T15:53:49Z","title":"Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-04T07:49:39.867194Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2608.02415"},"observation_digest":"sha256:b8ffa221b352101097827f261b2fcc5f1a2f95794ad71b33a158ea1d0bf645c9","observation_id":"ba5f6f2b-5be3-4be2-85c7-3975fa48852a","resolution":{"observed_at":"2026-08-04T07:49:39.867194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-05T19:06:18.567654Z","title":"2202.08904 , archivePrefix=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.03446","last_updated":"2026-08-04T10:44:40Z","snapshot_observed_at":"2026-08-12T05:01:30.018881Z","submitted_at":"2026-08-04T10:44:40Z","title":"Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment $\\unicode{x2013}$ Is English Enough?","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T19:06:18.567654Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2608.03446"},"observation_digest":"sha256:f7fb0d845afebf90b77a4f2045f711ec65d62afd7139469df067c0907b661ae3","observation_id":"3043d76c-4a3e-4599-a457-a4ead1993035","resolution":{"observed_at":"2026-08-05T19:06:18.567654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-14T04:29:36.417619Z","title":"arXiv preprint arXiv:2202.08904 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08809","last_updated":"2026-08-09T16:45:28Z","snapshot_observed_at":"2026-08-15T02:06:43.724858Z","submitted_at":"2026-08-09T16:45:28Z","title":"Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-14T04:29:36.417619Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2608.08809"},"observation_digest":"sha256:925c1aea2bf56a06d8065cfcea10875cf0076576713891b190488b1100fa1c38","observation_id":"a3228ac9-4669-4fb1-adb6-6b3af7523bbd","resolution":{"observed_at":"2026-08-14T04:29:36.417619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-16T00:14:32.490894Z","title":"Sgpt: Gpt sentence embeddings for semantic search,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.12269","last_updated":"2026-08-12T17:09:14Z","snapshot_observed_at":"2026-08-17T22:34:50.222415Z","submitted_at":"2026-08-12T17:09:14Z","title":"A Cascaded Unsupervised-Supervised NLP Pipeline for Detecting Accusatory Language in Public Procurement","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T00:14:32.490894Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2608.12269"},"observation_digest":"sha256:207c0fbbffc70902b032d24cd36dbf45401811d66fb53e1b88200329a5086005","observation_id":"6dbcc057-de8f-4547-8128-c1ccb812ebf9","resolution":{"observed_at":"2026-08-16T00:14:32.490894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.08904","snapshot_observed_at":"2026-08-15T21:37:01.195989Z","title":"2202.08904 , archivePrefix=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.12875","last_updated":"2026-08-13T06:39:45Z","snapshot_observed_at":"2026-08-17T20:46:30.987373Z","submitted_at":"2026-08-13T06:39:45Z","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T21:37:01.195989Z"},"links":{"cited_paper":"/paper/2202.08904","citing_paper":"/paper/2608.12875"},"observation_digest":"sha256:4ec9990d076454ff217a79fc3ede18e6b5f68182f4d82ce9534bdad49275a06b","observation_id":"16122feb-8240-4bcf-9c15-07e6fc391572","resolution":{"observed_at":"2026-08-15T21:37:01.195989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2202.08904/citation-record","integrity":"/paper/2202.08904/integrity","json":"/paper/2202.08904/citation-record.json","paper":"/paper/2202.08904"},"outbound":[],"paper":{"arxiv_id":"2202.08904","last_updated":"2022-08-05T09:33:10Z","latest_version":5,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T17:20:27.429412Z","submitted_at":"2022-02-17T21:35:56Z","title":"SGPT: GPT Sentence Embeddings for Semantic Search"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 60 inbound Pith citation observations for arXiv:2202.08904."}