{"as_of":"2026-08-20T00:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:34b9e1fe483c5f59656ba739108daa93bcb25340fa0f8a5c30bc107f12e31f93","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T13:43:43.894144Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":12,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:26:55.267840Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-10T01:36:44.287584Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-08-06T19:26:55.267840Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.05633","last_updated":"2025-07-08T03:29:09Z","snapshot_observed_at":"2026-08-17T05:19:49.700474Z","submitted_at":"2025-07-08T03:29:09Z","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T19:26:55.267840Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2507.05633"},"observation_digest":"sha256:4c9cbb8bcf3056a50b77920a70e9b7ab361d98274d2753bf647662e8f91ea62d","observation_id":"f297d411-6a01-4725-af39-c1c639a4e185","resolution":{"observed_at":"2026-08-06T19:26:55.267840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-08-06T18:57:33.567975Z","title":"arXiv preprint arXiv:2501.16214","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.06838","last_updated":"2025-07-10T01:36:33Z","snapshot_observed_at":"2026-08-13T16:13:43.787898Z","submitted_at":"2025-07-09T13:35:36Z","title":"Shifting from Ranking to Set Selection for Retrieval Augmented Generation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:57:33.567975Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2507.06838"},"observation_digest":"sha256:cc49a883e9624a7b27d912b99cfebf86b2ff950a2c4b9d57fa643b5d07201b14","observation_id":"17bca2c9-7134-4c0f-a7fd-39e5efea9a6b","resolution":{"observed_at":"2026-08-06T18:57:33.567975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-08-06T12:53:43.481300Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.21428","last_updated":"2025-07-29T01:42:06Z","snapshot_observed_at":"2026-08-16T07:51:25.442249Z","submitted_at":"2025-07-29T01:42:06Z","title":"MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T12:53:43.481300Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2507.21428"},"observation_digest":"sha256:b033f27d90ff90e3fe8d647152780e383e3a9c09ec015f5c6d4865572241cfe3","observation_id":"334841a3-f66d-411a-893a-351c0f19fe79","resolution":{"observed_at":"2026-08-06T12:53:43.481300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":"2501.16214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-07-10T01:36:44.287584Z","title":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer","venue":"cs.CL","work_id":"1b10a2a3-a782-429f-9bc5-1bbad7050307","year":2025},"citing_paper":{"arxiv_id":"2604.04979","last_updated":"2026-04-04T18:52:44Z","snapshot_observed_at":"2026-08-14T14:28:59.966505Z","submitted_at":"2026-04-04T18:52:44Z","title":"Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-13T17:02:05.875020Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2604.04979"},"observation_digest":"sha256:92c82f08a60e0a29ff9da1b287dabf887505384bbbe490aa1f31f1f2de94bafe","observation_id":"c59ea277-ffa8-48ea-8aab-122907b8ed74","resolution":{"observed_at":"2026-05-13T17:03:01.257759Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":"2501.16214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-07-10T01:36:44.287584Z","title":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer","venue":"cs.CL","work_id":"1b10a2a3-a782-429f-9bc5-1bbad7050307","year":2025},"citing_paper":{"arxiv_id":"2605.27494","last_updated":"2026-05-26T16:50:02Z","snapshot_observed_at":"2026-08-11T08:30:49.776814Z","submitted_at":"2026-05-26T16:50:02Z","title":"Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T17:16:48.588593Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2605.27494"},"observation_digest":"sha256:a8d8de34785f2897ae87ac6c4c71583bafaa803065abbec87849ead886f93575","observation_id":"61e52d36-e7a4-4f8e-bd72-1860bbf21eaf","resolution":{"observed_at":"2026-06-29T17:23:45.110107Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":"2501.16214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-07-10T01:36:44.287584Z","title":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer","venue":"cs.CL","work_id":"1b10a2a3-a782-429f-9bc5-1bbad7050307","year":2025},"citing_paper":{"arxiv_id":"2606.01336","last_updated":"2026-06-19T17:47:34Z","snapshot_observed_at":"2026-08-12T02:25:04.402124Z","submitted_at":"2026-05-31T16:40:36Z","title":"LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-28T17:08:16.011076Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2606.01336"},"observation_digest":"sha256:4916fad961dc9cccbc5015dcbf667a2ff458bdeda16a766670a82cfe20605128","observation_id":"a25c23dd-b5e9-434d-bb9c-ff686a3d2488","resolution":{"observed_at":"2026-06-28T17:12:24.848112Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":"2501.16214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-07-10T01:36:44.287584Z","title":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer","venue":"cs.CL","work_id":"1b10a2a3-a782-429f-9bc5-1bbad7050307","year":2025},"citing_paper":{"arxiv_id":"2606.06906","last_updated":"2026-06-05T04:49:37Z","snapshot_observed_at":"2026-08-02T10:42:01.638389Z","submitted_at":"2026-06-05T04:49:37Z","title":"EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-06-27T22:05:00.537690Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2606.06906"},"observation_digest":"sha256:438de11ae9870f13e958b75248b221b3165e8170dedbdf7d19a772052fce84ab","observation_id":"951d54b7-6930-4b98-82f0-8a8c51139315","resolution":{"observed_at":"2026-07-02T17:17:15.092994Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-07-12T06:11:01.755806Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02911","last_updated":"2026-07-03T03:17:52Z","snapshot_observed_at":"2026-08-15T08:54:54.156680Z","submitted_at":"2026-07-03T03:17:52Z","title":"CoACT: Action-Preserving Observation Compression for Coding Agents","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-12T06:11:01.755806Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2607.02911"},"observation_digest":"sha256:169ee859d71f0509a0758beb6f675c0fe69cf643dc8d5114d2186551e1da34ba","observation_id":"c5d0c930-6cb7-45bd-b2fc-4dd788eea1ac","resolution":{"observed_at":"2026-07-12T06:11:01.755806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":"2501.16214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-07-10T01:36:44.287584Z","title":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer","venue":"cs.CL","work_id":"1b10a2a3-a782-429f-9bc5-1bbad7050307","year":2025},"citing_paper":{"arxiv_id":"2607.08032","last_updated":"2026-07-09T01:15:03Z","snapshot_observed_at":"2026-08-18T23:35:57.173534Z","submitted_at":"2026-07-09T01:15:03Z","title":"What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-10T01:26:59.421158Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2607.08032"},"observation_digest":"sha256:8b3d3d9a6338d96c1d07c2ef8f3831e2c65943c1b064a911a7a9058c7e343975","observation_id":"c9fe92aa-596e-47db-b37c-15c3e3e2481b","resolution":{"observed_at":"2026-07-10T01:36:44.288699Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-08-02T14:32:11.918203Z","title":"Provence: Efficient and robust context pruning for retrieval-augmented generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16209","last_updated":"2026-05-10T13:27:01Z","snapshot_observed_at":"2026-08-17T22:13:29.974585Z","submitted_at":"2026-05-10T13:27:01Z","title":"Shapley Context Pruning: A Cooperative Game Perspective for Context Reranking and Pruning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T14:32:11.918203Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2607.16209"},"observation_digest":"sha256:2fa180697832245853d1f3d7d2701ea8c03d57528f1fba17698897674d517e2c","observation_id":"4cb5a356-c2f5-49bc-a8f3-8dddd8d48967","resolution":{"observed_at":"2026-08-02T14:32:11.918203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-08-05T00:23:52.085900Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00765","last_updated":"2026-08-01T16:59:49Z","snapshot_observed_at":"2026-08-14T12:06:05.541264Z","submitted_at":"2026-08-01T16:59:49Z","title":"RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T00:23:52.085900Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2608.00765"},"observation_digest":"sha256:89bee78c66f40bff189a7aeb6a042dfd57043f850fea3a17318bccb4583f7085","observation_id":"ae25228a-d9f5-4f1e-b780-af1907fa5b61","resolution":{"observed_at":"2026-08-05T00:23:52.085900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16214","snapshot_observed_at":"2026-08-06T00:45:24.205509Z","title":"Chirkova, T","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03148","last_updated":"2026-08-04T05:26:25Z","snapshot_observed_at":"2026-08-18T16:46:05.715464Z","submitted_at":"2026-08-04T05:26:25Z","title":"Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T00:45:24.205509Z"},"links":{"cited_paper":"/paper/2501.16214","citing_paper":"/paper/2608.03148"},"observation_digest":"sha256:73f31b0514f7fada829e4a6b26a3b5a356090ef025f46a28979311a30e7777c1","observation_id":"a666322a-f9b9-4548-aa9f-9c44e31583fe","resolution":{"observed_at":"2026-08-06T00:45:24.205509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.16214/citation-record","integrity":"/paper/2501.16214/integrity","json":"/paper/2501.16214/citation-record.json","paper":"/paper/2501.16214"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:41.441058Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:41.441058Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:f508628b9a0e49aa39f1b494ce8575f5a252390d40bf02a89716d88880fcbf1e","observation_id":"9f323af1-3b13-4cea-8ea4-ef6451e97410","resolution":{"observed_at":"2026-08-10T13:43:41.441058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.652847Z","title":"Llama 3 model card","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.652847Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:e0db0bec0c02135a3252910f61a93a3f791b681678ec2812923555af6c4ffeee","observation_id":"876d69a8-818f-436d-a066-f3a494add874","resolution":{"observed_at":"2026-08-10T13:43:43.652847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15805","last_updated":"2024-05-31T14:02:24Z","snapshot_observed_at":"2026-08-16T15:29:51.606768Z","submitted_at":"2023-05-25T07:39:41Z","title":"Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15805","snapshot_observed_at":"2026-08-10T13:43:43.659031Z","title":"Dynamic context pruning for efficient and interpretable autoregressive transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.659031Z"},"links":{"cited_paper":"/paper/2305.15805","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:4e045a36692252b92342b341c144df79150a179fbe4902d09a0647de662ead0e","observation_id":"9ccb1e32-6ca0-4ac1-8990-c23d71881605","resolution":{"observed_at":"2026-08-10T13:43:43.659031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03187","last_updated":"2024-03-05T18:22:33Z","snapshot_observed_at":"2026-08-19T16:49:30.767424Z","submitted_at":"2024-03-05T18:22:33Z","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03187","snapshot_observed_at":"2026-08-10T13:43:43.664863Z","title":"Reliable, adaptable, and attributable language models with retrieval","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.664863Z"},"links":{"cited_paper":"/paper/2403.03187","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:7e7da064e0e6b1dead775005107809637ed2e48062fad88ddcbb38e5d5348bee","observation_id":"9a73f5c3-fdf8-4195-a132-df8bffab480e","resolution":{"observed_at":"2026-08-10T13:43:43.664863Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03216","last_updated":"2025-12-12T11:26:32Z","snapshot_observed_at":"2026-08-17T15:25:09.479397Z","submitted_at":"2024-02-05T17:26:49Z","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03216","snapshot_observed_at":"2026-08-10T13:43:43.670829Z","title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation, 2024 a","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.670829Z"},"links":{"cited_paper":"/paper/2402.03216","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:43af584ce2d1cc9471beadc87b4fc29be9fefec697317ffec2ab33c02615cdc5","observation_id":"a9a4d413-c828-4262-bf09-e115b3608bfc","resolution":{"observed_at":"2026-08-10T13:43:43.670829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.677349Z","title":"Benchmarking large language models in retrieval-augmented generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.677349Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:b779b6c0dc0506ab9089e22cf505b464c918dffbbaa26e415c6de71b092df53b","observation_id":"f36f2ebc-6cb7-47e9-872f-7051129ab909","resolution":{"observed_at":"2026-08-10T13:43:43.677349Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.660398Z","title":null,"venue":null,"work_id":"0c1b490b-aa5a-410f-bddb-e606d64ef03d","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.682333Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:4600798f0566811357ab9d7c6564c9defdb2bf6ba37007c50dc9c928a9b2b587","observation_id":"d728e02c-26d6-4e2b-8221-b971e31f7ec6","resolution":{"observed_at":"2026-08-10T13:43:44.664208Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.686890Z","title":"Adapting language models to compress contexts","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.686890Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1cf33354fcfc4556c4fe8c8900c45a14e61db0de7f59754db7207bc01350a86c","observation_id":"bc4771bf-9d0f-4fa7-bbc6-c248b969502e","resolution":{"observed_at":"2026-08-10T13:43:43.686890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.690362Z","title":"Decontextualization: Making sentences stand-alone","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.690362Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:3e1594078986c41a641d5faee21b128fef62c96cd0dbe583fd3d14af73f4fed6","observation_id":"0c4d0884-609e-46b6-962e-2f772eb302ea","resolution":{"observed_at":"2026-08-10T13:43:43.690362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.693663Z","title":"Clark, Eunsol Choi, Michael Collins, Dan Garrette, Tom Kwiatkowski, Vitaly Nikolaev, and Jennimaria Palomaki","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.693663Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:ccc4109ab0c9c06c177a03ae07329c1b3e0f4848694e1d7f5b6b02ee7bca7d18","observation_id":"c3fc3029-da5b-40c5-8061-25faf0a97abe","resolution":{"observed_at":"2026-08-10T13:43:43.693663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.07820","last_updated":"2020-03-18T16:56:56Z","snapshot_observed_at":"2026-08-10T13:25:09.780441Z","submitted_at":"2020-03-17T17:12:36Z","title":"Overview of the TREC 2019 deep learning track","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.07820","snapshot_observed_at":"2026-08-10T13:43:43.697457Z","title":"Voorhees","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.697457Z"},"links":{"cited_paper":"/paper/2003.07820","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:dbe80519421a26b59c84485529b64e6c75c2b1ec7b8811e8c77e8fcdfe31890a","observation_id":"d36d24ff-09bd-4a8c-9f9e-1232b403f63e","resolution":{"observed_at":"2026-08-10T13:43:43.697457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.701595Z","title":"Ms marco: Benchmarking ranking models in the large-data regime","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.701595Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1aad9e2f3ee722a14d59231780c2d57cd0d4a972f4a435d825b70887c5eea25a","observation_id":"24bd1a38-60c6-46e6-96e8-7775c18a90e9","resolution":{"observed_at":"2026-08-10T13:43:43.701595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.705293Z","title":"Flashattention-2: Faster attention with better parallelism and work partitioning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.705293Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:466c9d208ea4f68dbc6a4bc465adeb673f1598392afe0fd0fffe830ed362de9c","observation_id":"b2ca54ed-aac4-42d4-9a0d-45f94adab2ac","resolution":{"observed_at":"2026-08-10T13:43:43.705293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.637567Z","title":"Multi-step retriever-reader interaction for scalable open-domain question answering","venue":null,"work_id":"2ed573b0-8eb1-4299-8953-7eedcd8bba0e","year":2019},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.709554Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:e7b6fd26c1e35453e92a4e8bbe9a93b6754f7b37b2ecaf2f6900cec8fcef7787","observation_id":"2edf021e-c0f6-45a6-8be8-8d03b3e9560c","resolution":{"observed_at":"2026-08-10T13:43:44.642749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.acl-long.557","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.019768Z","title":"S yllabus QA : A course logistics question answering dataset","venue":null,"work_id":"30357523-74a2-4210-926a-ad89eacdd143","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.712943Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:fb988dc1c0289140442adb21e543bad93ebbe0f323a8a9fb6f7bf07ea9873bf7","observation_id":"e078e2b7-7ae8-49e0-ba2a-58853f8e9a9d","resolution":{"observed_at":"2026-08-10T13:43:44.024491Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.624112Z","title":"In-context autoencoder for context compression in a large language model","venue":null,"work_id":"99665eae-6053-4a0b-8a73-c9837c18191d","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.716709Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:a0218bab1091f7e31e315c7fbde207017187740d931b3d039d43257882b389dd","observation_id":"fa69091d-33d5-403d-98c3-36acd68f9d29","resolution":{"observed_at":"2026-08-10T13:43:44.628189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.612726Z","title":"Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing, 2021 a","venue":null,"work_id":"486a12ef-6b9a-4183-8521-8104964777cd","year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.720245Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:f0065fd394dd2dad4aeda8fc4b00f8c5704c20d9b6dfc705a8f93760ea265841","observation_id":"1d8efd84-cabb-4f80-a4d6-d29e43a45b0f","resolution":{"observed_at":"2026-08-10T13:43:44.616705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.599692Z","title":"\\ DEBERTA \\ : \\ DECODING \\ - \\ enhanced \\ \\ bert \\ \\ with \\ \\ disentangled \\ \\ attention \\","venue":null,"work_id":"2fd18cd2-642b-4247-a285-ad98dbe926a5","year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.723655Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:02344cad6594c9cc29bd23762e0158905b77837fe841fef586f8ae7212a299e1","observation_id":"b22ebd61-bd80-421c-bbcf-3744556a92d3","resolution":{"observed_at":"2026-08-10T13:43:44.604202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02666","last_updated":"2021-01-22T16:24:52Z","snapshot_observed_at":"2026-08-16T19:15:32.227374Z","submitted_at":"2020-10-06T12:35:53Z","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02666","snapshot_observed_at":"2026-08-10T13:43:43.727410Z","title":"Improving efficient neural ranking models with cross-architecture knowledge distillation, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.727410Z"},"links":{"cited_paper":"/paper/2010.02666","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:daa26b7c16c6fea10d89c1b0a297dcb4bc270cf9b9a0699bbc7ff5504914a240","observation_id":"d3340bd8-c50f-4fe2-b6c4-4222f8ea5d1f","resolution":{"observed_at":"2026-08-10T13:43:43.727410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09040","last_updated":"2025-07-16T09:39:02Z","snapshot_observed_at":"2026-08-18T09:37:27.110698Z","submitted_at":"2024-03-14T02:26:31Z","title":"RAGGED: Towards Informed Design of Scalable and Stable RAG Systems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09040","snapshot_observed_at":"2026-08-10T13:43:43.731379Z","title":"Ragged: Towards informed design of retrieval augmented generation systems","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.731379Z"},"links":{"cited_paper":"/paper/2403.09040","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:50d0792c9c1b86efccf37a726942b6124a2410afd7beced433bd9794b506075f","observation_id":"11b844dd-1902-4c7a-b06c-bc4c687962e5","resolution":{"observed_at":"2026-08-10T13:43:43.731379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.735547Z","title":"DSLR : Document refinement with sentence-level re-ranking and reconstruction to enhance retrieval-augmented generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.735547Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:4e78243cd60a4f5ceccb0187c9368e851e232e956ae1972f8ca64d291aa93c1e","observation_id":"919528fb-8509-47e8-b126-73bc02b36fc0","resolution":{"observed_at":"2026-08-10T13:43:43.735547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.03299","last_updated":"2022-11-16T16:38:18Z","snapshot_observed_at":"2026-08-13T00:16:02.335397Z","submitted_at":"2022-08-05T17:39:22Z","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.03299","snapshot_observed_at":"2026-08-10T13:43:43.740364Z","title":"Atlas: Few -shot Learning with Retrieval Augmented Language Models , November 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.740364Z"},"links":{"cited_paper":"/paper/2208.03299","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:a21657fd388d3c9b1929bb6ec9bb5125b89ae031e5af7081ab5b6808888aebd8","observation_id":"3fabb209-202f-4b25-a0de-04a9e3793dfb","resolution":{"observed_at":"2026-08-10T13:43:43.740364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.744928Z","title":"LLML ingua: Compressing prompts for accelerated inference of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.744928Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:d6ddb9907cd6e130bd565dc1af26d5b04700d63745fade7abb921852bb9ba40b","observation_id":"81928140-c9d2-4823-b8b4-a5b21e884b81","resolution":{"observed_at":"2026-08-10T13:43:43.744928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.580916Z","title":"L ong LLML ingua: Accelerating and enhancing LLM s in long context scenarios via prompt compression","venue":null,"work_id":"bb227fe7-423f-4659-b94f-f3c14a6e6d47","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.749075Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1deac3ed2408273301a7d3f4bf1399fc35a83a2be9ed3f6b6457b55ef47beae2","observation_id":"90d1f8be-42c6-41a9-9df9-4b71b73e8113","resolution":{"observed_at":"2026-08-10T13:43:44.585492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.568941Z","title":"Solar 10.7b: Scaling large language models with simple yet effective depth up-scaling, 2023","venue":null,"work_id":"c54be473-56d0-49cf-910e-d9203b9119fb","year":null},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.752426Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:b670bd149fd44a091f31c7f6d2f34b8e4bd16f2fe0bd39b430968538d833258b","observation_id":"d08e8726-92e5-474a-aeca-20b0100c4763","resolution":{"observed_at":"2026-08-10T13:43:44.573396Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.756615Z","title":"Natural questions: a benchmark for question answering research","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.756615Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:bfaeeec4f7262a6f00b320a14f8d8f5a4d135b4deed4d2fa3f307ed1a05edda4","observation_id":"ef941511-7690-4aff-9858-541c3429426a","resolution":{"observed_at":"2026-08-10T13:43:43.756615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.761329Z","title":"Gonzalez, Hao Zhang, and Ion Stoica","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.761329Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:390222c9b7ac56f5ebf50ec91312f5e4a21932d03270b4662dc972117e3b26af","observation_id":"49a47dd4-81dc-4bad-b275-a6c7b2946b4e","resolution":{"observed_at":"2026-08-10T13:43:43.761329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.545420Z","title":"LangChain Documentation","venue":null,"work_id":"df807e2c-5c41-4926-9cfc-d359b6d66c90","year":null},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.770387Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:bd2e79b9e9f8bcc1a2bc15023f75a92b6457fa49ae13dd18d5cc795105e1b832","observation_id":"28d7a8e0-21db-46fb-b9ec-7a75d192f929","resolution":{"observed_at":"2026-08-10T13:43:44.548828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12574","last_updated":"2023-02-24T10:58:31Z","snapshot_observed_at":"2026-08-16T15:52:59.384963Z","submitted_at":"2023-02-24T10:58:31Z","title":"Naver Labs Europe (SPLADE) @ TREC Deep Learning 2022","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12574","snapshot_observed_at":"2026-08-10T13:43:43.774912Z","title":"Naver labs europe (splade) @ trec deep learning 2022, 2023","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.774912Z"},"links":{"cited_paper":"/paper/2302.12574","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:3edb73756e3d714db613955c348d38bb99e8381ba7229feeb2b2a0fd25d8b64a","observation_id":"7f4527cc-7f8a-4124-b4d3-dcbd19a8a72f","resolution":{"observed_at":"2026-08-10T13:43:43.774912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.534589Z","title":"Splade-v3: New baselines for splade, 2024","venue":null,"work_id":"1384e175-654d-43ec-8511-d71261d76656","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.779844Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:4b33f69b2dbc5d30599bb7d53cdeb2cc86aee78fb3e78a7c20e2c9a9edf2d6de","observation_id":"24dae181-a43f-4d6f-8577-9ac3b1807a9a","resolution":{"observed_at":"2026-08-10T13:43:44.538299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.522929Z","title":"Retrieval- Augmented Generation for Knowledge - Intensive NLP Tasks","venue":null,"work_id":"c533de49-41c5-46e9-b779-ce77a2194b8b","year":2020},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.784111Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:d2f55d4f36101cabcdfa268b9a7f950348030d8d9858abafb1fb17ec6864dc9a","observation_id":"f193502c-e30d-4fef-84df-1fea6a6bd496","resolution":{"observed_at":"2026-08-10T13:43:44.526717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.788124Z","title":"Compressing context to enhance inference efficiency of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.788124Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:b7aaa83988e58ca7feba3faa9fe040d9ff5405885993228df50aed89ab3f3b18","observation_id":"1d6abf8c-dfac-4128-aad2-01e742e150b0","resolution":{"observed_at":"2026-08-10T13:43:43.788124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.792235Z","title":"Pyserini: A python toolkit for reproducible information retrieval research with sparse and dense representations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.792235Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1cbfd1a0197917f9a704f11684a861ada1cd7c4d53dff8d4881113d41e16a9d9","observation_id":"83015a25-b2b4-4fdd-a77d-681a0d40158d","resolution":{"observed_at":"2026-08-10T13:43:43.792235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.511860Z","title":"RA - DIT : Retrieval-augmented dual instruction tuning","venue":null,"work_id":"2813ea41-c372-463d-ae0b-804d9bfb28c2","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.795815Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:71d210240ac89cf141390a0a437ea8084ed00a75782f7a15bb6067a7028a577e","observation_id":"f20e400d-4762-4a54-bc67-d1af94093e48","resolution":{"observed_at":"2026-08-10T13:43:44.515674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.500510Z","title":"Pisco: Pretty simple compression for retrieval-augmented generation","venue":null,"work_id":"e4b03c3e-4888-478f-bd59-6f6a4ddb406a","year":2025},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.799754Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:95371970abc7a6be85e5d021f0add055a343a7cba09ef02af6db9728645ba0c2","observation_id":"d34049d2-560d-4a55-add0-38e922bc6164","resolution":{"observed_at":"2026-08-10T13:43:44.504289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.acl-long.54","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.995415Z","title":"When not to trust language models: Investigating effectiveness of parametric and non-parametric memories","venue":null,"work_id":"e5772db1-d931-4d71-94f0-05735b9d3671","year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.807488Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:be36670881cf5463c054c0225de49e2e21b3f1a2bdc523ac318f0f6b95a2dc15","observation_id":"0a727486-1d1e-4c12-bffe-1d7e897ac772","resolution":{"observed_at":"2026-08-10T13:43:43.998869Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09636","last_updated":"2024-07-23T17:55:30Z","snapshot_observed_at":"2026-08-18T11:14:41.086889Z","submitted_at":"2024-03-14T17:59:26Z","title":"Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09636","snapshot_observed_at":"2026-08-10T13:43:43.814854Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.814854Z"},"links":{"cited_paper":"/paper/2403.09636","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:815972adad1edd13f077e9dfee5d1d5aa586f3ed7c059c76025e93def5386633","observation_id":"f69b1452-feb0-4910-b4e3-6dc32ed2a7bb","resolution":{"observed_at":"2026-08-10T13:43:43.814854Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.818813Z","title":"Overview of BioASQ 2023: The Eleventh BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering, pp.\\ 227--250","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.818813Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:a4884d6a9b850e61ef0072da6ccba3056b5b072863667ffee9705fb8a6b4d2ac","observation_id":"c994c798-8521-4b4d-9b25-14964579f090","resolution":{"observed_at":"2026-08-10T13:43:43.818813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.489115Z","title":"Ms marco: A human generated machine reading comprehension dataset","venue":null,"work_id":"9f66e577-906a-4892-85fc-353a3ef77998","year":2016},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.822672Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:d49f7f41a2daa2d393ae213a34332d0c1c7695130942684cc36d0a343ea5c1bc","observation_id":"fade1b07-7464-49d2-975a-f8cc4e24ab56","resolution":{"observed_at":"2026-08-10T13:43:44.492956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.825851Z","title":"Passage re-ranking with bert, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.825851Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:ca1ba90207146ad992498132087bd0dd945671049e2fa45c51f709e31822e108","observation_id":"ac244822-55f6-43b6-bdfb-25a2b5ce77a3","resolution":{"observed_at":"2026-08-10T13:43:43.825851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.473504Z","title":"Vicky Zhao, Lili Qiu, and Dongmei Zhang","venue":null,"work_id":"6a1f9c04-a0b7-4f23-b2b8-6ad6431820cb","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.830504Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:a543c1f7d164af19b109f994cd18c5f8baf50b05f43a7b94cbb7945bbab380b9","observation_id":"02e0ec73-9710-4e2e-bc27-4126091716e8","resolution":{"observed_at":"2026-08-10T13:43:44.477109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.463403Z","title":"PyTorch: an imperative style, high-performance deep learning library","venue":null,"work_id":"7a15e60c-9ee3-46f4-b150-161ca7e946c4","year":2019},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.834108Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:56e91a21d5e0ed96491a873c7768cfda750a4faf98a67f67cb4d001f176f79cd","observation_id":"83614b84-4de1-46bd-9098-0e839d6b9896","resolution":{"observed_at":"2026-08-10T13:43:44.466559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2024.findings-emnlp.449","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.974404Z","title":"BERGEN : A benchmarking library for retrieval-augmented generation","venue":null,"work_id":"17628dca-7fe9-422d-9b22-e1146c0f57bf","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.836983Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:09c65842dcb7ff6e2389674d305eb6edd2ded83bd84e816cd15fb3f0976d1252","observation_id":"28d8a173-472f-40c7-9b88-d29159568c33","resolution":{"observed_at":"2026-08-10T13:43:43.978462Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09252","last_updated":"2024-10-29T17:34:54Z","snapshot_observed_at":"2026-08-16T13:34:45.741915Z","submitted_at":"2024-07-12T13:30:44Z","title":"Context Embeddings for Efficient Answer Generation in RAG","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09252","snapshot_observed_at":"2026-08-10T13:43:43.840373Z","title":"Context embeddings for efficient answer generation in rag, 2024 b","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.840373Z"},"links":{"cited_paper":"/paper/2407.09252","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1258d4254846f9ed2528993523ca5e7118ede1ae2dabf11f2550b64253e8597e","observation_id":"e4dd6d9d-c3a6-421a-a4dd-222a7cebfd27","resolution":{"observed_at":"2026-08-10T13:43:43.840373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/p19-1436","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.958462Z","title":"Real-time open-domain question answering with dense-sparse phrase index","venue":null,"work_id":"7887cfe3-1213-4f44-b20a-db4b4b19fec0","year":2019},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.844694Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:296459de2b6115d8cae485aa977e08e0d02fdbfef4f53572ab657f2bd186a427","observation_id":"6a21f21a-a96b-44b7-9c67-b2abaa0fec7a","resolution":{"observed_at":"2026-08-10T13:43:43.965454Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.12035","last_updated":"2022-10-17T14:08:37Z","snapshot_observed_at":"2026-08-18T02:27:47.037722Z","submitted_at":"2022-05-24T12:43:04Z","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.12035","snapshot_observed_at":"2026-08-10T13:43:43.849630Z","title":"Retromae: Pre-training retrieval-oriented language models via masked auto-encoder","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.849630Z"},"links":{"cited_paper":"/paper/2205.12035","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:70221e6c5c8a92178aca2e6008a923904dd20388e0d75ce152c2783cfd008716","observation_id":"52fa9d98-75da-47a9-b018-3aa203ff4094","resolution":{"observed_at":"2026-08-10T13:43:43.849630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.853130Z","title":"BEIR : A heterogeneous benchmark for zero-shot evaluation of information retrieval models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.853130Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:5105c70dfdcf5d7960a5614a552c27bee05bbbbb81a80c0ffb73270ba6e71ca3","observation_id":"a1905fb6-b563-4786-8d8d-2ac0d095e445","resolution":{"observed_at":"2026-08-10T13:43:43.853130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.856373Z","title":"Llama 2: Open foundation and fine-tuned chat models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.856373Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1993201426aaa7e4e144c93c0941cbda7870e0a8bda8be676a2316be68246d33","observation_id":"c3f58978-4fa5-40f5-be0a-2bf3bfe60b7e","resolution":{"observed_at":"2026-08-10T13:43:43.856373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.08377","last_updated":"2023-11-14T18:41:54Z","snapshot_observed_at":"2026-08-16T14:43:20.161445Z","submitted_at":"2023-11-14T18:41:54Z","title":"Learning to Filter Context for Retrieval-Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.08377","snapshot_observed_at":"2026-08-10T13:43:43.860281Z","title":"Learning to filter context for retrieval-augmented generation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.860281Z"},"links":{"cited_paper":"/paper/2311.08377","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1d494a02feb6fa077f5e5accca71ace58a1f7d990b07210257da5af8174887c6","observation_id":"47756eb7-6981-4968-9279-a6f4e5aed3bd","resolution":{"observed_at":"2026-08-10T13:43:43.860281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.863876Z","title":"Transformers: State-of-the-art natural language processing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.863876Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:fad251b9b820e7de82681e2900f4c369b7fdbdfec3f765901e2000d2f9855474","observation_id":"9f5f1073-bc63-40f3-a72d-ab146236aaa8","resolution":{"observed_at":"2026-08-10T13:43:43.863876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:44.433420Z","title":"RECOMP : Improving retrieval-augmented LM s with context compression and selective augmentation","venue":null,"work_id":"1cea9dd8-c79b-4850-819c-3f7c45baf814","year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.867370Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:6f039c05fdf495ad55e19a25bdbe24589cb84321d58f8dbc01c68898c920a341","observation_id":"86cbdcce-d487-47f2-a2d4-bc50905cb500","resolution":{"observed_at":"2026-08-10T13:43:44.437898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.871236Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.871236Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:c24b2d0941c0a87228993ea429b388f1e46fd372535897799921af38433478c4","observation_id":"e29e5fd9-5c97-4f7b-893c-7c2eb6d6d345","resolution":{"observed_at":"2026-08-10T13:43:43.871236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.09014","last_updated":"2024-10-14T12:42:54Z","snapshot_observed_at":"2026-08-16T13:34:52.456403Z","submitted_at":"2024-07-12T06:06:54Z","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.09014","snapshot_observed_at":"2026-08-10T13:43:43.874930Z","title":"Compact: Compressing retrieved documents actively for question answering, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.874930Z"},"links":{"cited_paper":"/paper/2407.09014","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:23a0c4fe05b7e764d366cf07029ac4f78de680bf12aa19022c25016bef2a2fff","observation_id":"23172091-3e84-4033-bc60-768a694c016d","resolution":{"observed_at":"2026-08-10T13:43:43.874930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.878731Z","title":"Making retrieval-augmented language models robust to irrelevant context","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.878731Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:1da8dab155cdebf813df980b3b84f605da08f7e3c6914cff0faa2f2c68321630","observation_id":"2b80af18-95d9-4aec-99c4-7b2a85e80dfb","resolution":{"observed_at":"2026-08-10T13:43:43.878731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16178","last_updated":"2024-05-25T11:10:04Z","snapshot_observed_at":"2026-08-16T13:49:30.019964Z","submitted_at":"2024-05-25T11:10:04Z","title":"Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16178","snapshot_observed_at":"2026-08-10T13:43:43.882119Z","title":"Accelerating inference of retrieval-augmented generation via sparse context selection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.882119Z"},"links":{"cited_paper":"/paper/2405.16178","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:8d92b72257841a6c2aecb196c0869a347e8542a59e5d9485b097dddb85fe3043","observation_id":"1ddcbab2-fe78-44f5-90b2-500113d363a3","resolution":{"observed_at":"2026-08-10T13:43:43.882119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.885712Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.885712Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:c25560bfd2dfc59ef03b379698751fd55aa90cd3cb2fcbfa8f7cb93305240a46","observation_id":"41b491ad-8752-4ded-acd4-7dff19d53fa7","resolution":{"observed_at":"2026-08-10T13:43:43.885712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T13:43:43.890261Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.890261Z"},"links":{"citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:c7f00ce5e0ca683bda2afbaea779f98e517ece3ba946bfb38e75ac55141bfdea","observation_id":"b628030b-56ba-4652-9707-ed6e62bed083","resolution":{"observed_at":"2026-08-10T13:43:43.890261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14251","last_updated":"2023-10-11T05:27:50Z","snapshot_observed_at":"2026-08-19T19:54:57.212265Z","submitted_at":"2023-05-23T17:06:00Z","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14251","snapshot_observed_at":"2026-08-10T13:43:43.894144Z","title":"P` Pq\\| Z5W||Zm O<J-?MQh<= Af U)y ? /`f] aL18IV+ q fJ mh;W iD8#ie+ jkq ._3 kdC`N Y\\މIw -Yw7y>˻kӝ m(4)ɿ HFo_ nƿ#l","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-10T13:43:43.894144Z"},"links":{"cited_paper":"/paper/2305.14251","citing_paper":"/paper/2501.16214"},"observation_digest":"sha256:ad86e242b8381e031e02fee125cbdb46a6da7003470d9cfeb205cfd0843f4a58","observation_id":"46635457-110c-4dc2-97a0-2572c6384806","resolution":{"observed_at":"2026-08-10T13:43:43.894144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.16214","last_updated":"2025-01-27T17:06:56Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T06:16:38.838457Z","submitted_at":"2025-01-27T17:06:56Z","title":"Provence: efficient and robust context pruning for retrieval-augmented generation"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":39,"verified_exact":4,"verified_fuzzy":14},"total_outbound_references":58},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 12 inbound Pith citation observations for arXiv:2501.16214."}