{"as_of":"2026-08-23T10:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:74f51ef2fa23c0a2163ebcd3fa3cc6429176eef4bd2dc433bfe8620f08bcf1ce","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":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":34,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:38:49.181497Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":7,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-12T05:59:37.181897Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.19710","last_updated":"2024-11-29T13:57:07Z","snapshot_observed_at":"2026-08-19T23:46:27.758013Z","submitted_at":"2024-11-29T13:57:07Z","title":"Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T05:59:37.181897Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2411.19710"},"observation_digest":"sha256:8e93208a6d087e837b221a7e8d8e94855d8a42353f4ee09757f6f7c718046961","observation_id":"6af5e794-66ab-454c-921e-0577aeb7cb3d","resolution":{"observed_at":"2026-08-12T05:59:37.181897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-11T15:48:28.376816Z","title":null,"venue":null,"work_id":null,"year":2024},"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":30,"source":"arxiv_source","source_observed_at":"2026-08-11T15:48:28.376816Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2412.10684"},"observation_digest":"sha256:6601f744f6e63529170fef6a99d2f5df580f6a0e18dd105b11f7259d21d62709","observation_id":"594c925f-8442-46e3-a518-89f97c87f13e","resolution":{"observed_at":"2026-08-11T15:48:28.376816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-11T12:09:42.972011Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.14581","last_updated":"2024-12-19T07:01:25Z","snapshot_observed_at":"2026-08-14T18:19:58.251936Z","submitted_at":"2024-12-19T07:01:25Z","title":"CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T12:09:42.972011Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2412.14581"},"observation_digest":"sha256:7bd5a12628f8e80e1387cb9bb5ea7e85c6f2335453e67f8cfcdedc05528a539a","observation_id":"1eb92eb6-2187-4ce3-a7f0-5e446d87feae","resolution":{"observed_at":"2026-08-11T12:09:42.972011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-11T10:46:47.662008Z","title":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16311","last_updated":"2025-06-02T22:52:12Z","snapshot_observed_at":"2026-08-14T15:53:21.597306Z","submitted_at":"2024-12-20T19:49:12Z","title":"HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T10:46:47.662008Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2412.16311"},"observation_digest":"sha256:f86051599cc0143706395817ed11c6d7743161210070e8c41ff2763e51d023df","observation_id":"29be246e-9a30-4ad4-b892-aa64b5642650","resolution":{"observed_at":"2026-08-11T10:46:47.662008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-10T21:56:58.752186Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03468","last_updated":"2025-01-07T01:52:56Z","snapshot_observed_at":"2026-08-14T15:34:54.710794Z","submitted_at":"2025-01-07T01:52:56Z","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T21:56:58.752186Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2501.03468"},"observation_digest":"sha256:f5e2f29f1013b9e0e17839bdcd4de59f7bba966b5ed807bffed4bea3fbc98065","observation_id":"0fcdd5c3-73e3-469a-a3a6-b741816e5b6f","resolution":{"observed_at":"2026-08-10T21:56:58.752186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-10T20:57:29.199013Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06699","last_updated":"2025-01-12T03:32:12Z","snapshot_observed_at":"2026-08-17T16:50:39.006447Z","submitted_at":"2025-01-12T03:32:12Z","title":"Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T20:57:29.199013Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2501.06699"},"observation_digest":"sha256:ca0bbf5a2ed9fe2544651e71ebe640179bde5bbe7e5f720aca8ba4970deb0f1e","observation_id":"fb071010-e69c-4dc5-beaf-38d8f7b88ca4","resolution":{"observed_at":"2026-08-10T20:57:29.199013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-10T19:35:27.938893Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.09928","last_updated":"2025-01-17T02:48:29Z","snapshot_observed_at":"2026-08-16T17:20:03.153034Z","submitted_at":"2025-01-17T02:48:29Z","title":"Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T19:35:27.938893Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2501.09928"},"observation_digest":"sha256:efbd30f2b823cb87c18b5c914df101e83487eec93e6ff95fa22afb58d5550d60","observation_id":"668a4ea3-b800-4d54-9ec7-666234fe7de9","resolution":{"observed_at":"2026-08-10T19:35:27.938893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-10T17:47:46.190878Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.11929","last_updated":"2025-01-21T07:07:58Z","snapshot_observed_at":"2026-08-17T17:38:07.613765Z","submitted_at":"2025-01-21T07:07:58Z","title":"ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T17:47:46.190878Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2501.11929"},"observation_digest":"sha256:3a7dd5daa0417161a2ff60f86218e20827f761e56838cbbe65fd9b15020ba4b2","observation_id":"f1bcf714-7d98-4333-8263-52cce4989032","resolution":{"observed_at":"2026-08-10T17:47:46.190878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-08T19:28:43.617686Z","title":"Crag–comprehensive rag benchmark","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.05431","last_updated":"2025-02-12T13:54:01Z","snapshot_observed_at":"2026-08-18T14:04:44.954866Z","submitted_at":"2025-02-08T03:41:16Z","title":"APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T19:28:43.617686Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2502.05431"},"observation_digest":"sha256:e68f4a47a61597784a21ccc68ac4eb50161a1a8ad7bd933dac481735b0c302b1","observation_id":"b01b69e4-0a6b-49d4-833d-391e8b0a428a","resolution":{"observed_at":"2026-08-08T19:28:43.617686Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-11T11:17:48.482205Z","title":"Crag–comprehensive rag benchmark","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.15690","last_updated":"2024-12-20T08:03:12Z","snapshot_observed_at":"2026-08-17T12:00:27.948532Z","submitted_at":"2024-12-20T08:03:12Z","title":"Level-Navi Agent: A Framework and benchmark for Chinese Web Search Agents","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T11:17:48.482205Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2502.15690"},"observation_digest":"sha256:085f7cbe6a77a90be0399bd856f5c466fdec459c45933d61753c5bcb70721fbf","observation_id":"287f1808-c00f-465b-ae5f-21dd81bc3c73","resolution":{"observed_at":"2026-08-11T11:17:48.482205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-16T11:38:49.181497Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.15068","last_updated":"2025-04-21T12:55:06Z","snapshot_observed_at":"2026-08-17T00:44:54.372060Z","submitted_at":"2025-04-21T12:55:06Z","title":"The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T11:38:49.181497Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2504.15068"},"observation_digest":"sha256:635e3d93efe68490e9e7de0e92cf470b96340093c8081cd70abc8a1f3dadda1f","observation_id":"4d46a182-df56-4d52-8266-5c9aa723d128","resolution":{"observed_at":"2026-08-16T11:38:49.181497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2504.19678","last_updated":"2026-03-06T19:01:27Z","snapshot_observed_at":"2026-08-20T06:16:20.613961Z","submitted_at":"2025-04-28T11:08:22Z","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","version":2},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-15T02:57:37.873567Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2504.19678"},"observation_digest":"sha256:de07e4203a296d373ed7de91336e56bc87e56bed3d18f9ed78bab267be170eec","observation_id":"60cce34f-dfef-4bfb-a339-929dd03b08c3","resolution":{"observed_at":"2026-05-15T02:57:38.347248Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-16T05:52:50.594834Z","title":"CRAG – comprehensive RAG benchmark","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.20119","last_updated":"2025-05-01T13:03:37Z","snapshot_observed_at":"2026-08-17T19:46:38.442290Z","submitted_at":"2025-04-28T08:22:19Z","title":"Can LLMs Be Trusted for Evaluating RAG Systems? A Survey of Methods and Datasets","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T05:52:50.594834Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2504.20119"},"observation_digest":"sha256:74550c2b6060cc4ab6e82268dd98bfc51277c59fe0d47f95f0e786cde5815f8b","observation_id":"99c2ea8c-678c-4857-8c58-56dff351cb75","resolution":{"observed_at":"2026-08-16T05:52:50.594834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-15T22:43:06.070052Z","title":"Crag–comprehensive rag benchmark,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.06579","last_updated":"2025-05-10T09:36:28Z","snapshot_observed_at":"2026-08-18T03:47:09.424279Z","submitted_at":"2025-05-10T09:36:28Z","title":"POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:43:06.070052Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2505.06579"},"observation_digest":"sha256:b6aa7a2780f7c2d7adccbe5ecbfc1047d78e63f80bcb350dcf17ef32dd8c7797","observation_id":"0120c2b2-b5e2-435d-968c-8deb9ae8b200","resolution":{"observed_at":"2026-08-15T22:43:06.070052Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-15T21:30:18.871545Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11545","last_updated":"2025-05-14T19:39:46Z","snapshot_observed_at":"2026-08-19T12:32:14.122695Z","submitted_at":"2025-05-14T19:39:46Z","title":"TARGET: Benchmarking Table Retrieval for Generative Tasks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T21:30:18.871545Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2505.11545"},"observation_digest":"sha256:f66833e3d931a3e372c43f03c9d3818214b0057a1dc13fafbf70a66446268aba","observation_id":"453dfa8e-19e0-4171-b688-c5506294ce34","resolution":{"observed_at":"2026-08-15T21:30:18.871545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-07T13:59:50.459606Z","title":"Crag – comprehensive rag benchmark","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20266","last_updated":"2025-05-26T17:43:13Z","snapshot_observed_at":"2026-08-20T08:17:20.128655Z","submitted_at":"2025-05-26T17:43:13Z","title":"syftr: Pareto-Optimal Generative AI","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T13:59:50.459606Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2505.20266"},"observation_digest":"sha256:804f2884d19faa2684a6bf8571646a89478d8068dd0dd63d2fca3b859ea6ed7e","observation_id":"d5294252-475f-471f-8dac-589823b062df","resolution":{"observed_at":"2026-08-07T13:59:50.459606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T10:34:46.822448Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03934","last_updated":"2025-09-04T06:50:47Z","snapshot_observed_at":"2026-08-12T12:45:12.895598Z","submitted_at":"2025-09-04T06:50:47Z","title":"SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-05T10:34:46.822448Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2509.03934"},"observation_digest":"sha256:992243b181ab6bf300ffe17ca3a1ccc3730c10cc23e47c11bb033d75c6f2bc36","observation_id":"3c0e4c43-0d7d-4dcb-9529-2ad2f433b79c","resolution":{"observed_at":"2026-08-05T10:34:46.822448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T06:02:10.472186Z","title":"InProceedings of the 2023 Con- ference on Empirical Methods in Natural Language Processing, pages 5778–5791","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.04716","last_updated":"2025-09-05T00:06:00Z","snapshot_observed_at":"2026-08-18T22:46:41.290175Z","submitted_at":"2025-09-05T00:06:00Z","title":"KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T06:02:10.472186Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2509.04716"},"observation_digest":"sha256:b9c26d4c4a28ca6adfd56a0caa1b3d81dd330cd3ea64887721e48e54fe33e113","observation_id":"dd90ed67-fff3-4a81-8b1a-591b46028348","resolution":{"observed_at":"2026-08-05T06:02:10.472186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-03T10:04:19.150973Z","title":"Crag–comprehensive rag benchmark,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.11443","last_updated":"2026-07-14T08:20:53Z","snapshot_observed_at":"2026-08-17T08:47:58.324065Z","submitted_at":"2026-01-16T17:07:01Z","title":"Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T10:04:19.150973Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2601.11443"},"observation_digest":"sha256:ef893cf70b7648380c022b371c5b23f1ecde770cd06c6ed8a38a3d7cfd83125f","observation_id":"ce49d483-b003-4e76-a296-80c9ce0b3067","resolution":{"observed_at":"2026-08-03T10:04:19.150973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-07-14T20:48:19.312615Z","title":"arXiv preprint arXiv:2406.04744 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.06210","last_updated":"2026-06-08T08:25:07Z","snapshot_observed_at":"2026-08-12T12:10:16.143127Z","submitted_at":"2026-03-16T08:33:10Z","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-14T20:48:19.312615Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2604.06210"},"observation_digest":"sha256:1cf3ce87853aedfbd2a441eac97bb36610c777a95d63948f5330e474753204de","observation_id":"7c711c9c-7c9b-4b64-951a-98a7172bb13f","resolution":{"observed_at":"2026-07-14T20:48:19.312615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2604.06211","last_updated":"2026-04-18T00:13:59Z","snapshot_observed_at":"2026-08-13T10:58:09.504122Z","submitted_at":"2026-03-16T11:10:29Z","title":"Illocutionary Explanation Planning for Source-Faithful Explanations in Retrieval-Augmented Language Models","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-15T10:39:11.866574Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2604.06211"},"observation_digest":"sha256:5ee6798eaf6615ea7d1d29730d4bc5b2bd748a733cb62b6d0b011ab48c2b7cb6","observation_id":"35b90dc3-6c27-4630-b941-9fffb17328ee","resolution":{"observed_at":"2026-05-15T10:39:56.816140Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2604.16310","last_updated":"2026-01-30T15:32:14Z","snapshot_observed_at":"2026-07-06T23:03:39.351412Z","submitted_at":"2026-01-30T15:32:14Z","title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-16T09:13:55.204404Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2604.16310"},"observation_digest":"sha256:7ad2c9390f25aaf9e2395a481621cae55f6ef77486050364a4c226df7affbf0a","observation_id":"3d4646f7-471b-476d-8bc6-4df023de6828","resolution":{"observed_at":"2026-05-16T09:17:40.151113Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2604.20850","last_updated":"2026-02-13T21:02:53Z","snapshot_observed_at":"2026-07-06T23:07:31.559812Z","submitted_at":"2026-02-13T21:02:53Z","title":"Association Is Not Similarity: Learning Corpus-Specific Associations for Multi-Hop Retrieval","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-15T22:00:12.332167Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2604.20850"},"observation_digest":"sha256:a1f1a97a87c5b6e3ea545fa84efadfd06b49807958399ca8592c76dbb574d57c","observation_id":"476d7289-a649-4724-a524-d88da1a47d77","resolution":{"observed_at":"2026-05-15T22:00:21.002554Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2604.26176","last_updated":"2026-06-08T13:50:43Z","snapshot_observed_at":"2026-08-02T20:48:08.415798Z","submitted_at":"2026-04-28T23:46:47Z","title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-07T13:49:52.951086Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2604.26176"},"observation_digest":"sha256:4000c20cbc817435adf9f0ed4db5f42e763c70c38b6ec41c8d85c532f728bddf","observation_id":"65f5d2ae-d910-4ff8-97ef-eb7544f1c6fe","resolution":{"observed_at":"2026-05-12T08:46:26.160828Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2604.26176","last_updated":"2026-06-08T13:50:43Z","snapshot_observed_at":"2026-08-02T20:48:08.415798Z","submitted_at":"2026-04-28T23:46:47Z","title":"CacheRAG: A Semantic Caching System for Retrieval-Augmented Generation in Knowledge Graph Question Answering","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-01T08:29:56.762672Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2604.26176"},"observation_digest":"sha256:036576d5453a4530217aaa83516f5c0a572166fb61e3d49c22de2f077ede2f77","observation_id":"b7a58033-d99f-4fd8-908a-7586bf3667f8","resolution":{"observed_at":"2026-07-01T08:35:33.679344Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2606.05415","last_updated":"2026-06-03T20:28:36Z","snapshot_observed_at":"2026-08-16T17:16:49.158378Z","submitted_at":"2026-06-03T20:28:36Z","title":"Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T05:58:25.764539Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2606.05415"},"observation_digest":"sha256:814ea625ec742b1b741133a38ebb9c8f909ae3917a5af18237663afb2e3df9d1","observation_id":"0c6e3fe6-6d70-42c4-97bd-3dda1c06585c","resolution":{"observed_at":"2026-07-02T08:36:47.827653Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2606.30062","last_updated":"2026-06-29T09:55:01Z","snapshot_observed_at":"2026-08-15T06:39:38.795799Z","submitted_at":"2026-06-29T09:55:01Z","title":"Little Brains, Big Feats: Exploring Compact Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-30T06:18:11.792566Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2606.30062"},"observation_digest":"sha256:3fac7ac2d3018d9be8ee89bce47104a06111d0c24d5a08de84eafdd3e081e415","observation_id":"8c49d304-24b3-4463-9e52-5378c1572818","resolution":{"observed_at":"2026-06-30T06:24:19.358634Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":"2406.04744","doi":"10.48550/arxiv.2406.04744","metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"CRAG – comprehensive RAG benchmark.arXiv preprint arXiv:2406.04744","venue":"arXiv (Cornell University)","work_id":"31ae2125-c349-4f62-a361-3c54c6521017","year":2024},"citing_paper":{"arxiv_id":"2606.30306","last_updated":"2026-06-29T13:47:42Z","snapshot_observed_at":"2026-08-17T00:44:04.699064Z","submitted_at":"2026-06-29T13:47:42Z","title":"Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-30T03:44:51.320606Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2606.30306"},"observation_digest":"sha256:ae06010e8ee7b05484ca70b1ed688341aa500b95dfe9917cc7e975ead94268c5","observation_id":"e28a16f0-e3b7-4821-bd47-74eb4274b3a1","resolution":{"observed_at":"2026-07-01T15:15:48.367889Z","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":"2026-07-15T19:20:22.170486+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-15T19:20:22.170486+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-07-14T11:20:09.244925Z","title":"arXiv preprint arXiv:2406.04744 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.10491","last_updated":"2026-07-11T21:56:15Z","snapshot_observed_at":"2026-08-22T21:04:20.812581Z","submitted_at":"2026-07-11T21:56:15Z","title":"EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-07-14T11:20:09.244925Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2607.10491"},"observation_digest":"sha256:e2c007d42b2a23cd1f6ea3cef0e940413df69a819adc6c3566459b4b0173a874","observation_id":"a17cdbb3-b928-464a-aaf1-c367b2f1d998","resolution":{"observed_at":"2026-07-14T11:20:09.244925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-01T14:35:29.984858Z","title":"2406.04744 , archivePrefix=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26497","last_updated":"2026-07-31T12:57:39Z","snapshot_observed_at":"2026-08-10T01:08:17.322193Z","submitted_at":"2026-07-29T05:46:11Z","title":"BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-01T14:35:29.984858Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2607.26497"},"observation_digest":"sha256:5eb2286f5d3f8c2ea6e258088ec8a626e06c9b9e7a3689f9e2442beec13950e5","observation_id":"43836596-31a1-453c-8e37-28cea0a906bf","resolution":{"observed_at":"2026-08-01T14:35:29.984858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-03T01:45:04.183044Z","title":"2406.04744 , archivePrefix=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26497","last_updated":"2026-07-31T12:57:39Z","snapshot_observed_at":"2026-08-10T01:08:17.322193Z","submitted_at":"2026-07-29T05:46:11Z","title":"BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms","version":3},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-03T01:45:04.183044Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2607.26497"},"observation_digest":"sha256:a126ecf5cb8151cc8920ab9e8a65d934cf70975da56d387749615c45f8c3a21f","observation_id":"20290a4a-7acd-4bfd-9520-f6c4330ef833","resolution":{"observed_at":"2026-08-03T01:45:04.183044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-15T15:29:09.036179Z","title":"CRAG – comprehensive RAG benchmark","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.27353","last_updated":"2026-07-29T18:09:17Z","snapshot_observed_at":"2026-08-22T11:36:09.497474Z","submitted_at":"2026-07-29T18:09:17Z","title":"LayerRAG-Bench: A Cross-Layer Reliability Benchmark for Agentic Retrieval-Augmented Generation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T15:29:09.036179Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2607.27353"},"observation_digest":"sha256:e7bcf69839359022942e3bfab9c4c3b161248a82532291b50963469f4153635c","observation_id":"928f39f1-145c-4d55-8787-8d17ba914d47","resolution":{"observed_at":"2026-08-15T15:29:09.036179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-04T22:55:34.022856Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.01684","last_updated":"2026-08-03T04:18:31Z","snapshot_observed_at":"2026-08-17T14:05:08.138252Z","submitted_at":"2026-08-03T04:18:31Z","title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T22:55:34.022856Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2608.01684"},"observation_digest":"sha256:0706c0492ba25a512db9d81538ff8715de6a2f2ebfa441d99f028bf880443cd0","observation_id":"b723d179-826a-4f5f-b1e6-67a4452514f1","resolution":{"observed_at":"2026-08-04T22:55:34.022856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04744","snapshot_observed_at":"2026-08-15T14:54:16.090081Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03451","last_updated":"2026-08-04T10:48:11Z","snapshot_observed_at":"2026-08-19T18:03:12.792024Z","submitted_at":"2026-08-04T10:48:11Z","title":"DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T14:54:16.090081Z"},"links":{"cited_paper":"/paper/2406.04744","citing_paper":"/paper/2608.03451"},"observation_digest":"sha256:621208f67091c02be8c2a9463ef391c487921c84f827a7e3ae478c6c59174c5e","observation_id":"0ac45e1f-8045-4121-930e-def489e75e2b","resolution":{"observed_at":"2026-08-15T14:54:16.090081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.04744/citation-record","integrity":"/paper/2406.04744/integrity","json":"/paper/2406.04744/citation-record.json","paper":"/paper/2406.04744"},"outbound":[],"paper":{"arxiv_id":"2406.04744","last_updated":"2024-11-01T05:30:17Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T17:20:20.539409Z","submitted_at":"2024-06-07T08:43:07Z","title":"CRAG -- Comprehensive RAG Benchmark"},"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 34 inbound Pith citation observations for arXiv:2406.04744."}