{"as_of":"2026-08-23T21:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7a2daa640e8338725df4afbda27b4c6d9605e78e4201d27215b5f860b43020cd","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":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":28,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T05:21:55.143151Z","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":"2026-07-02T02:46:29.381896Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-12T05:21:55.143151Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.00546","last_updated":"2024-11-30T17:39:59Z","snapshot_observed_at":"2026-08-19T12:38:36.996989Z","submitted_at":"2024-11-30T17:39:59Z","title":"Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T05:21:55.143151Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2412.00546"},"observation_digest":"sha256:a75121d5b74cff72742f7edbbf1ee565b0969ceb27a96f04e40c6b6f4295f30f","observation_id":"a652a6fc-eca3-43b8-a447-aed2f32c5f19","resolution":{"observed_at":"2026-08-12T05:21:55.143151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-10T13:37:35.368595Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.16302","last_updated":"2025-01-27T18:42:48Z","snapshot_observed_at":"2026-08-14T11:46:29.511845Z","submitted_at":"2025-01-27T18:42:48Z","title":"Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T13:37:35.368595Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2501.16302"},"observation_digest":"sha256:310494bbedf2c52e31b5fd7fdc1a7dbe799c16b16e0383021ffa10eeefd16433","observation_id":"02707339-64c3-410f-b3c3-660c863942df","resolution":{"observed_at":"2026-08-10T13:37:35.368595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-09T12:07:24.107419Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.02464","last_updated":"2025-02-19T22:46:25Z","snapshot_observed_at":"2026-08-15T09:30:15.485365Z","submitted_at":"2025-02-04T16:33:25Z","title":"Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-09T12:07:24.107419Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2502.02464"},"observation_digest":"sha256:fbc5fe112be912693441909faf1301be7590d33b24463bbd397d6e838b549382","observation_id":"f7506bcb-565e-4fbc-bb93-578adde5c86c","resolution":{"observed_at":"2026-08-09T12:07:24.107419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-09T04:08:51.791525Z","title":"Document ranking with a pretrained sequence-to-sequence model","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2502.03699","last_updated":"2025-07-23T21:26:26Z","snapshot_observed_at":"2026-08-17T02:42:06.612301Z","submitted_at":"2025-02-06T01:22:06Z","title":"LLM Alignment as Retriever Optimization: An Information Retrieval Perspective","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T04:08:51.791525Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2502.03699"},"observation_digest":"sha256:95586fa31752e52758b8f62cab8dba074d805f090e83022cad2c879d3a425ede","observation_id":"2d353fc4-1597-4cc9-9813-e0681c393432","resolution":{"observed_at":"2026-08-09T04:08:51.791525Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-08T13:10:56.390855Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.07315","last_updated":"2025-02-23T09:44:00Z","snapshot_observed_at":"2026-08-17T12:21:52.355538Z","submitted_at":"2025-02-11T07:25:57Z","title":"White Hat Search Engine Optimization using Large Language Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T13:10:56.390855Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2502.07315"},"observation_digest":"sha256:8ae8a529293e7aa469b77f4f9b0cb78c110dd8d8b773aa3e9d28b1df8e7bbb40","observation_id":"705153cb-80b8-4d17-8a3f-73a1ebb7b9f7","resolution":{"observed_at":"2026-08-08T13:10:56.390855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-08T16:11:43.197790Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.08662","last_updated":"2025-06-02T04:54:00Z","snapshot_observed_at":"2026-08-18T21:37:50.629904Z","submitted_at":"2025-02-10T09:34:15Z","title":"RoToR: Towards More Reliable Responses for Order-Invariant Inputs","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T16:11:43.197790Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2502.08662"},"observation_digest":"sha256:256130b45065f3da55a1f2f2aa0e3dd6f33720df4b854bca854525d5b6fe9c58","observation_id":"c5e32d7c-4704-4dd7-bb48-ba676604af5e","resolution":{"observed_at":"2026-08-08T16:11:43.197790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2505.14558","last_updated":"2026-04-03T16:04:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-20T16:15:30Z","title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-22T13:52:15.835379Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2505.14558"},"observation_digest":"sha256:9db5e7bcee383a049f85197beb0980f23176c49201804923d3cd05a24be6abbb","observation_id":"dffa41b8-baf1-4539-8644-2005f7acb2e1","resolution":{"observed_at":"2026-05-22T13:54:53.054543Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-07T14:48:09.986880Z","title":"Document ranking with a pretrained sequence-to-sequence model","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2505.17552","last_updated":"2025-05-30T09:21:07Z","snapshot_observed_at":"2026-08-18T21:36:58.575493Z","submitted_at":"2025-05-23T06:56:55Z","title":"Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T14:48:09.986880Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2505.17552"},"observation_digest":"sha256:a41458f14631df067272a5c0dd618141225b598a950ede8d890b86b4f86f1ada","observation_id":"4529e7b0-debf-4d4d-874c-3a16056906ab","resolution":{"observed_at":"2026-08-07T14:48:09.986880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-07T13:08:55.264481Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.22584","last_updated":"2025-05-28T16:56:41Z","snapshot_observed_at":"2026-08-13T01:49:52.632752Z","submitted_at":"2025-05-28T16:56:41Z","title":"DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T13:08:55.264481Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2505.22584"},"observation_digest":"sha256:f203bafd8763def0c4f93e6ba93cbbf2c819b4f210c0e3226af7f0a4b0fdbf14","observation_id":"5f5dffdb-be6c-47cd-bc9b-44357e612e7f","resolution":{"observed_at":"2026-08-07T13:08:55.264481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-07T12:35:31.216580Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.24643","last_updated":"2025-05-30T14:29:55Z","snapshot_observed_at":"2026-08-18T02:43:05.391954Z","submitted_at":"2025-05-30T14:29:55Z","title":"Are Optimal Algorithms Still Optimal? Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:31.216580Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2505.24643"},"observation_digest":"sha256:301ec799ca53c80577b5ad0a5c966acb69b3982743a61d91952bd9c2ba2d1630","observation_id":"b8defab9-4347-41c6-8c6c-779ecc21e298","resolution":{"observed_at":"2026-08-07T12:35:31.216580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-07T10:38:18.343708Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04760","last_updated":"2025-06-05T08:44:34Z","snapshot_observed_at":"2026-08-19T07:19:37.850746Z","submitted_at":"2025-06-05T08:44:34Z","title":"Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:38:18.343708Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2506.04760"},"observation_digest":"sha256:bb8f0e572bc477f50419c0326a4ecf18be6a53619deba2fbb26f893085c93315","observation_id":"2b6703d5-6fe5-42d2-93bc-1c4d1abc8eb7","resolution":{"observed_at":"2026-08-07T10:38:18.343708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-07T00:51:21.168054Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.12494","last_updated":"2025-06-30T05:45:43Z","snapshot_observed_at":"2026-08-14T15:35:37.096741Z","submitted_at":"2025-06-14T13:16:31Z","title":"FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T00:51:21.168054Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2506.12494"},"observation_digest":"sha256:3a5fdab181754a7e63c8087cbe1e4166c7e44de6899537de981d3f176b94eab0","observation_id":"72d2d520-daab-4d61-afba-f5970a2dbd57","resolution":{"observed_at":"2026-08-07T00:51:21.168054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-06T10:33:12.406255Z","title":"Nogueira, Z","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2507.23669","last_updated":"2025-07-31T15:48:12Z","snapshot_observed_at":"2026-08-20T04:24:28.814213Z","submitted_at":"2025-07-31T15:48:12Z","title":"Automating AI Failure Tracking: Semantic Association of Reports in AI Incident Database","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T10:33:12.406255Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2507.23669"},"observation_digest":"sha256:28a4a6f1484e53ca6eee8640bf2baf416c540518d94e741acf21c3e91f379b77","observation_id":"ddca7cbe-8efc-4413-b2ec-a22ae5bfc645","resolution":{"observed_at":"2026-08-06T10:33:12.406255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-05T17:15:15.333064Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.16757","last_updated":"2025-08-22T19:30:04Z","snapshot_observed_at":"2026-08-17T01:16:21.168623Z","submitted_at":"2025-08-22T19:30:04Z","title":"How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T17:15:15.333064Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2508.16757"},"observation_digest":"sha256:4aead19ee0d16ad73592274ecfa38ffaed2f47e515433b1321ccdac3613bfd1f","observation_id":"a07b3e0e-c406-4a0f-aa7f-7b44a461ea40","resolution":{"observed_at":"2026-08-05T17:15:15.333064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2509.00303","last_updated":"2026-05-19T23:05:35Z","snapshot_observed_at":"2026-08-12T20:36:40.417159Z","submitted_at":"2025-08-30T01:44:36Z","title":"Access Paths for Efficient Ordering with Large Language Models","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-21T22:32:23.352584Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2509.00303"},"observation_digest":"sha256:564eef60b98d5c7bba105cf7a589d7e07b72e32760ef2fe33119f174801fabd2","observation_id":"15b4e679-2416-42b5-8a74-f0360d47624f","resolution":{"observed_at":"2026-05-21T22:34:24.259960Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-05T10:44:10.539618Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03787","last_updated":"2025-09-04T00:45:58Z","snapshot_observed_at":"2026-08-22T09:09:46.965070Z","submitted_at":"2025-09-04T00:45:58Z","title":"Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T10:44:10.539618Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2509.03787"},"observation_digest":"sha256:39f846e5baf828a6da8cd586bd0db5b9b172898d34a8c3d1efa3a2e2b85e9998","observation_id":"08a32764-1db1-437f-a151-8f30f5c942ea","resolution":{"observed_at":"2026-08-05T10:44:10.539618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-08-04T23:02:46.511447Z","title":"Document ranking with a pretrained sequence-to- sequence model.arXiv preprint arXiv:2003.06713,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.06855","last_updated":"2025-09-08T16:23:44Z","snapshot_observed_at":"2026-08-06T11:22:19.306837Z","submitted_at":"2025-09-08T16:23:44Z","title":"Seeing the Forest Through the Trees: Knowledge Retrieval for Streamlining Particle Physics Analysis","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T23:02:46.511447Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2509.06855"},"observation_digest":"sha256:26e71e8454a2e70af143ff8c1ba5db562b7cfd5e2d9d23cc46ced0132539cea9","observation_id":"9e76afbe-469d-4701-ad38-d35b3aacb4da","resolution":{"observed_at":"2026-08-04T23:02:46.511447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2603.04816","last_updated":"2026-04-18T16:07:53Z","snapshot_observed_at":"2026-08-11T02:53:17.437551Z","submitted_at":"2026-03-05T05:03:07Z","title":"Scaling Laws for Cross-Encoder Reranking","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-15T16:09:58.328527Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2603.04816"},"observation_digest":"sha256:895af9d57852f860fb1ec88a6cefa72d0a7f9bf2e0804eff225a451b719a5063","observation_id":"5626f098-3793-4193-889c-b339e99d34c2","resolution":{"observed_at":"2026-05-15T16:10:09.218634Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.04734","last_updated":"2026-04-28T06:44:06Z","snapshot_observed_at":"2026-08-15T20:06:06.518993Z","submitted_at":"2026-04-06T15:02:35Z","title":"Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T20:07:39.225282Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.04734"},"observation_digest":"sha256:c2556c3f1e63f133310fc86a3ba097e9894890dc6df77431d18daf8b76105da8","observation_id":"2619306c-b8e4-4066-8fd7-71e6c188ea8d","resolution":{"observed_at":"2026-05-10T22:15:48.240321Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.08834","last_updated":"2026-04-10T00:16:31Z","snapshot_observed_at":"2026-08-17T08:36:35.667086Z","submitted_at":"2026-04-10T00:16:31Z","title":"BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T17:52:56.417908Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.08834"},"observation_digest":"sha256:91f6134c7141587d50b94d103dcc2bdae68ed72f507a12610b251eb5cfc3853a","observation_id":"90f6962a-8f09-40b4-9afd-4f164505e2f6","resolution":{"observed_at":"2026-05-11T05:55:57.767058Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.15186","last_updated":"2026-04-16T16:15:29Z","snapshot_observed_at":"2026-08-11T14:14:11.088453Z","submitted_at":"2026-04-16T16:15:29Z","title":"Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T09:52:40.057014Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.15186"},"observation_digest":"sha256:a8deaecc5d986fbd6d1d71108b6749eb2b0285fde105dfc9353eaa5808bd1f39","observation_id":"186f940d-258f-4379-86e5-db8ae1da9eec","resolution":{"observed_at":"2026-05-10T09:59:03.468247Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.17237","last_updated":"2026-05-19T06:36:57Z","snapshot_observed_at":"2026-08-11T11:59:37.261094Z","submitted_at":"2026-04-19T03:43:42Z","title":"HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-10T06:36:22.111810Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.17237"},"observation_digest":"sha256:f2becb5ba302f87c1a8407f30d8776ef896d76646d48e6727d7ea81bd33b2542","observation_id":"dba7a289-8e88-42fb-ba93-1be6cb0f9886","resolution":{"observed_at":"2026-05-10T06:36:36.280641Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.22180","last_updated":"2026-04-24T03:11:51Z","snapshot_observed_at":"2026-08-11T06:06:27.398707Z","submitted_at":"2026-04-24T03:11:51Z","title":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-08T10:30:26.342174Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.22180"},"observation_digest":"sha256:b66c166f654fe2dba45d9538efb5f892e447b99554cb23052831d28a0df1321f","observation_id":"a5f69255-79f4-4e16-9a87-c5d04387f4cc","resolution":{"observed_at":"2026-05-11T20:01:10.862560Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.24608","last_updated":"2026-04-27T15:36:54Z","snapshot_observed_at":"2026-08-16T04:13:56.102902Z","submitted_at":"2026-04-27T15:36:54Z","title":"Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-08T02:01:14.533941Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.24608"},"observation_digest":"sha256:d224ac97097f39b236e9bef6e9ada5886b3f051babc4239f548c7facb69b620a","observation_id":"cc256496-3057-4f76-be8c-1619f9d02ad4","resolution":{"observed_at":"2026-05-11T23:01:15.287183Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2604.27202","last_updated":"2026-04-29T21:09:21Z","snapshot_observed_at":"2026-08-11T13:56:31.818773Z","submitted_at":"2026-04-29T21:09:21Z","title":"Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-07T08:55:39.589773Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2604.27202"},"observation_digest":"sha256:a50f35b01c3695ad4be60096373c8d83621097c152be142fb7933e892707421b","observation_id":"11cb5d79-8c7f-4abd-949a-c78eee7ef918","resolution":{"observed_at":"2026-05-12T09:51:29.333213Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2605.01591","last_updated":"2026-05-02T19:26:34Z","snapshot_observed_at":"2026-08-15T05:43:56.796973Z","submitted_at":"2026-05-02T19:26:34Z","title":"Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-09T17:37:56.757376Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2605.01591"},"observation_digest":"sha256:0f1e80952615418e0a74b4821964f5caa3cca3b81432052a9adfd0137a87fc8a","observation_id":"10e66469-5ddd-4ab3-8457-ff5527f948ee","resolution":{"observed_at":"2026-05-11T16:21:06.502072Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2605.30027","last_updated":"2026-05-28T14:50:53Z","snapshot_observed_at":"2026-08-06T11:47:39.586448Z","submitted_at":"2026-05-28T14:50:53Z","title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-29T08:09:41.068000Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2605.30027"},"observation_digest":"sha256:965a68cdc4eab136f51d55e176d03756ceb1948c40388c9bf5037faee504f1ef","observation_id":"65b389a1-168c-4b3b-ad95-a762c64693fe","resolution":{"observed_at":"2026-06-29T08:13:14.976444Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model","version":1},"cited_work":{"arxiv_id":"2003.06713","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.06713","snapshot_observed_at":"2026-07-02T02:46:29.381896Z","title":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin","venue":null,"work_id":"c1fe8c8d-c400-470d-8075-998a546cf680","year":2003},"citing_paper":{"arxiv_id":"2606.03728","last_updated":"2026-06-02T14:48:33Z","snapshot_observed_at":"2026-07-06T23:43:55.632508Z","submitted_at":"2026-06-02T14:48:33Z","title":"Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T10:35:11.989106Z"},"links":{"cited_paper":"/paper/2003.06713","citing_paper":"/paper/2606.03728"},"observation_digest":"sha256:f629e5aad54ad8045591ee9b9fcebeef15f65b8345992d1d30fea3744ca356ad","observation_id":"82924b7b-c1aa-4861-84ad-473a1d20a508","resolution":{"observed_at":"2026-07-02T02:46:29.384175Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2003.06713/citation-record","integrity":"/paper/2003.06713/integrity","json":"/paper/2003.06713/citation-record.json","paper":"/paper/2003.06713"},"outbound":[],"paper":{"arxiv_id":"2003.06713","last_updated":"2020-03-14T22:29:50Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-18T20:12:18.878856Z","submitted_at":"2020-03-14T22:29:50Z","title":"Document Ranking with a Pretrained Sequence-to-Sequence Model"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 28 inbound Pith citation observations for arXiv:2003.06713."}