{"as_of":"2026-08-17T05:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e4ab9115c9bb8916cbe2328aeb2ef656f18f91ff8268daf43b4a5ff2d530bb3f","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:17:42.424277Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.03100/citation-record","integrity":"/paper/2506.03100/integrity","json":"/paper/2506.03100/citation-record.json","paper":"/paper/2506.03100"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:17:38.500659Z","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.500659Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:888be42ed8ed725e27e90d4b801cddfa1c72d8dd368c1c7e4a62877202add5db","observation_id":"453231b0-dd6c-47f8-97c6-6bd69634cc52","resolution":{"observed_at":"2026-08-07T11:17:38.500659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11511","last_updated":"2023-10-17T18:18:32Z","snapshot_observed_at":"2026-08-12T20:38:07.563701Z","submitted_at":"2023-10-17T18:18:32Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11511","snapshot_observed_at":"2026-08-07T11:17:38.556369Z","title":"Self-RAG : Learning to retrieve, generate, and critique through self-reflection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.556369Z"},"links":{"cited_paper":"/paper/2310.11511","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:7c24408383fc64f56ffc82323f2dbedad46c1ad4ca863b510ea095e07e75e86b","observation_id":"a45a1687-cc6b-472b-a295-d96a8ab9402f","resolution":{"observed_at":"2026-08-07T11:17:38.556369Z","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":"2026-08-07T11:17:46.153650Z","title":null,"venue":null,"work_id":"53df0edd-b235-43d5-b91f-2e9bb223ddaa","year":2021},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.623059Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:dff6cc9226a153656a11dcf767b7aad6714a5d37ac7b85a97caca096fe207ab7","observation_id":"ae6b730b-8b0c-40a9-8b6e-f883b0fa0bb9","resolution":{"observed_at":"2026-08-07T11:17:46.201071Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:38.709435Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.709435Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:2591b0f9920ac7ca8b31a4502c83f095cfeb0c324c7e7d9a02abb3fa32a08d26","observation_id":"c6c3f1ab-e9e0-4cd3-83a2-804af817ac31","resolution":{"observed_at":"2026-08-07T11:17:38.709435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.00051","last_updated":"2017-04-28T03:53:14Z","snapshot_observed_at":"2026-08-14T21:08:52.040409Z","submitted_at":"2017-03-31T20:39:10Z","title":"Reading Wikipedia to Answer Open-Domain Questions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.00051","snapshot_observed_at":"2026-08-07T11:17:38.785951Z","title":"Reading wikipedia to answer open-domain questions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.785951Z"},"links":{"cited_paper":"/paper/1704.00051","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:b8f3ed2952f8bd55031d823dbd9ba47a5ff177d048cec95ba2a5c671176d12d7","observation_id":"5335d914-4217-4fd5-abad-66813c612fcf","resolution":{"observed_at":"2026-08-07T11:17:38.785951Z","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":"2026-08-07T11:17:45.984424Z","title":"Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation","venue":null,"work_id":"f3dbb56c-830e-42cd-97f2-312393507155","year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.878062Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:4ee6046a83312f792868707899794139192d1ab38d4a97abe39ed15f93f84934","observation_id":"de69886a-61fa-4b3a-b4d8-f0dd7865cb5b","resolution":{"observed_at":"2026-08-07T11:17:46.038349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:45.827611Z","title":"Exploring the robustness of in-context learning with noisy labels","venue":null,"work_id":"e515c2ca-67ad-4580-8e7e-013c4f71f8e1","year":2025},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:38.932831Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:ed6e0e6c7103382161fb1a2403926ec7864a9cd6a13a9fb966bf748e2c3e6f1b","observation_id":"3b5a508e-e388-40b4-b000-cfe8134fc9b3","resolution":{"observed_at":"2026-08-07T11:17:45.895129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08518","last_updated":"2023-12-16T06:50:09Z","snapshot_observed_at":"2026-08-16T15:48:03.339934Z","submitted_at":"2023-03-15T10:53:49Z","title":"UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08518","snapshot_observed_at":"2026-08-07T11:17:39.040515Z","title":"Uprise: Universal prompt retrieval for improving zero-shot evaluation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.040515Z"},"links":{"cited_paper":"/paper/2303.08518","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:5e489623569516e634840b8899ff218aded52ebd833fae9b8b0a8bf4dfcf26ba","observation_id":"0c486fa1-47fe-41f7-b8d4-bcf6a3a86513","resolution":{"observed_at":"2026-08-07T11:17:39.040515Z","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":"2026-08-07T11:17:39.115206Z","title":"Nearest neighbor pattern classification","venue":null,"work_id":null,"year":1967},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.115206Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:f6f88f0c2c5eb73fb3e7af4a9175512e4b37195db076fedffefe9752d5e39b0e","observation_id":"a493d251-38bf-49d2-b6b1-e99e41d2cb69","resolution":{"observed_at":"2026-08-07T11:17:39.115206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00234","last_updated":"2024-10-05T11:47:02Z","snapshot_observed_at":"2026-07-06T14:36:25.690733Z","submitted_at":"2022-12-31T15:57:09Z","title":"A Survey on In-context Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00234","snapshot_observed_at":"2026-08-07T11:17:39.183271Z","title":"A survey for in-context learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.183271Z"},"links":{"cited_paper":"/paper/2301.00234","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:bd42a790f0f5569a74f7d65e8a058687afb6ccc842d6ad45eebe975e4285f003","observation_id":"665515ca-40a5-4881-8ea7-faf5803e9c18","resolution":{"observed_at":"2026-08-07T11:17:39.183271Z","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":"2026-08-07T11:17:45.666960Z","title":"A survey on in-context learning","venue":null,"work_id":"f802e69d-1bbd-4b80-9711-f1f0d4c6dec6","year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.297189Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:5c488f0e85fbf81c92e170ee27d5fd3d2f38151ad772dd91e85270fd524d70f0","observation_id":"c602aa6d-77ec-4ff2-8bc8-af68576c139a","resolution":{"observed_at":"2026-08-07T11:17:45.725354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:39.360691Z","title":"What can transformers learn in-context? a case study of simple function classes","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.360691Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:65db03703e01a3ebed625022b9a08d8c32d94e377b3dd2917ede3cc6449aa992","observation_id":"840fb628-5f38-4624-a3b5-9bf6d78b589f","resolution":{"observed_at":"2026-08-07T11:17:39.360691Z","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":"2503.11842","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:17:43.502976Z","title":"Test-time training provably improves transformers as in-context learners","venue":null,"work_id":"226423da-d666-4c11-90f0-5777f8bf5844","year":2025},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.447458Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:bf2553a670ed068397c0f3b9b8477b4e2fe1b307454e248ca112e04485bca510","observation_id":"2d9aa306-04bc-44ce-a708-e74dd9e788eb","resolution":{"observed_at":"2026-08-07T11:17:43.595950Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07922","last_updated":"2024-08-19T05:46:56Z","snapshot_observed_at":"2026-08-16T15:08:17.593280Z","submitted_at":"2023-08-15T17:59:18Z","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.07922","snapshot_observed_at":"2026-08-07T11:17:39.504967Z","title":"Raven: In-context learning with retrieval-augmented encoder-decoder language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.504967Z"},"links":{"cited_paper":"/paper/2308.07922","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:94dffaec305bcf0d033ad35d5657f7fcefea0dacf52aa307c54d6388ce1f2afd","observation_id":"c0685d4a-5851-48c7-acdd-f77629b34f50","resolution":{"observed_at":"2026-08-07T11:17:39.504967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12661","last_updated":"2023-01-30T04:44:34Z","snapshot_observed_at":"2026-08-16T15:59:17.584326Z","submitted_at":"2023-01-30T04:44:34Z","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12661","snapshot_observed_at":"2026-08-07T11:17:39.603008Z","title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.603008Z"},"links":{"cited_paper":"/paper/2301.12661","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:229e11342d07f87b3ea94b38b85a75b90919b880a2842d668e60c225854553df","observation_id":"5bdfadf8-3fa8-4e56-b3f5-3d7cc433f6a5","resolution":{"observed_at":"2026-08-07T11:17:39.603008Z","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":"2026-08-07T11:17:45.500940Z","title":"On a formula for the product-moment coefficient of any order of a normal frequency distribution in any number of variables","venue":null,"work_id":"8fc6b179-1820-470c-8326-54df8b64fcf8","year":1918},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.650079Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:1617cefda2bc5595c7c383444f9ed1ae4af0e4fe7af838de7f97432228ca0307","observation_id":"e2d01428-8d7e-4927-ab98-25cb0cef8690","resolution":{"observed_at":"2026-08-07T11:17:45.580317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.01282","last_updated":"2021-02-03T09:18:34Z","snapshot_observed_at":"2026-08-13T02:37:51.426086Z","submitted_at":"2020-07-02T17:44:57Z","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.01282","snapshot_observed_at":"2026-08-07T11:17:39.723732Z","title":"Leveraging passage retrieval with generative models for open domain question answering","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.723732Z"},"links":{"cited_paper":"/paper/2007.01282","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:6e09cfc3ff34dd2e1781a6ca9add0c66a41afe80e6b8eb8417420c5deffc3c69","observation_id":"d8dd8265-2981-4b8d-910e-7a57b831a05f","resolution":{"observed_at":"2026-08-07T11:17:39.723732Z","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":"2026-08-07T11:17:39.810318Z","title":"Atlas: Few-shot learning with retrieval augmented language models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.810318Z"},"links":{"cited_paper":"/paper/2208.03299","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:61784d2300fa297f46cb327352f544a951daf8bdf6b44ba5d94764f1088b7f69","observation_id":"d61b5b7a-5c9b-4a01-b039-7cf6c39b3e1f","resolution":{"observed_at":"2026-08-07T11:17:39.810318Z","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":"2026-08-07T11:17:39.902007Z","title":"T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.902007Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:9ee55bf38a15f518b204fb16916650313f25f934128e1cb9c3f96f7da2785268","observation_id":"ec128c8e-0ae9-46c8-bec4-6310b8f23cce","resolution":{"observed_at":"2026-08-07T11:17:39.902007Z","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":"2026-08-07T11:17:39.983797Z","title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:39.983797Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:03f2e1c8de5ad9c815c0e92d1dbe6fafa11f1f17a7a7b20e8da7716cd5a9dacc","observation_id":"5bb981af-fd87-4946-b411-22fffa6b63c4","resolution":{"observed_at":"2026-08-07T11:17:39.983797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14848","last_updated":"2024-07-10T17:01:37Z","snapshot_observed_at":"2026-08-16T14:17:17.243508Z","submitted_at":"2024-02-19T16:04:53Z","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14848","snapshot_observed_at":"2026-08-07T11:17:40.053099Z","title":"Same task, more tokens: the impact of input length on the reasoning performance of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.053099Z"},"links":{"cited_paper":"/paper/2402.14848","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:002829297c02898a0a371ee55f53ea9c2f9f6d9bae5c7749a76fe61c518012f7","observation_id":"9475e65c-a6be-46b8-a2d2-2305ba6e4f0c","resolution":{"observed_at":"2026-08-07T11:17:40.053099Z","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":"2026-08-07T11:17:40.131615Z","title":"More documents, same length: Isolating the challenge of multiple documents in rag","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.131615Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:cb8add19bc858168b7160c2cbc16bcd0f2e5248c03403e9b83a07ca6a63b22d8","observation_id":"36165c48-c10a-4f71-9ce9-979ac74dabc4","resolution":{"observed_at":"2026-08-07T11:17:40.131615Z","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":"2026-08-07T11:17:45.336435Z","title":"u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt\\","venue":null,"work_id":"abe2c0ac-1954-4839-be69-1833db0c6a41","year":2020},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.191520Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:e3dd9fef6e78647104f9fb2ed079437b6cf2d0db463e3f1e88eeb469eb72aed0","observation_id":"b47f14b3-99be-496d-a913-60ab1a41a104","resolution":{"observed_at":"2026-08-07T11:17:45.430098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:45.199803Z","title":"u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \\","venue":null,"work_id":"4ac6a9f6-7c86-4090-a454-c1ed2a12e767","year":2020},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.287001Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:dbb7f43252ea0f539385832e8a19fabd5afdb1d1628dce70bc1c737672413c38","observation_id":"c4568230-0fe3-4b57-a029-f567d944d674","resolution":{"observed_at":"2026-08-07T11:17:45.269002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:40.369301Z","title":"Making large language models a better foundation for dense retrieval","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.369301Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:05e3bf1aee1c857e820f424bff0a483dcb54105ab4a5c11ea2a8f73678dceafa","observation_id":"552e2383-c110-4de2-a501-79ae26c5c545","resolution":{"observed_at":"2026-08-07T11:17:40.369301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.08635","last_updated":"2024-03-28T06:06:59Z","snapshot_observed_at":"2026-08-16T16:08:03.854853Z","submitted_at":"2022-12-16T18:23:43Z","title":"Self-Prompting Large Language Models for Zero-Shot Open-Domain QA","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.08635","snapshot_observed_at":"2026-08-07T11:17:40.447199Z","title":"Self-prompting large language models for zero-shot open-domain qa","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.447199Z"},"links":{"cited_paper":"/paper/2212.08635","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:02e8f21f33cffe5164ad71aa35d16e8fed0505379689eed9e582676796edf5eb","observation_id":"2e3e34b3-2ead-4733-95aa-1fd357d1d141","resolution":{"observed_at":"2026-08-07T11:17:40.447199Z","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":"2026-08-07T11:17:45.054051Z","title":"Mot: Pre-thinking and recalling enable chatgpt to self-improve with memory-of-thoughts","venue":null,"work_id":"051a79c9-f59a-467b-8b63-ea0e17da6152","year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.529710Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:04184c89b4c3deb1e631df2a68d0dd72335044e613319b446a455545e1ddc0f4","observation_id":"cbc3be01-c182-4957-b963-50c32cb59d89","resolution":{"observed_at":"2026-08-07T11:17:45.123763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:44.930347Z","title":"Chain-of-knowledge: Grounding large language models via dynamic knowledge adapting over heterogeneous sources","venue":null,"work_id":"94dac0cd-e38a-46fb-bb14-ac8dc25508e5","year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.611438Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:7cd216a170b693e6ef0b9dd459a66e02508cf4202caaf67882eeec8aaa88e3bd","observation_id":"872e96f7-0091-4311-8f0d-bbeb3ff991c8","resolution":{"observed_at":"2026-08-07T11:17:45.001137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06804","last_updated":"2021-01-17T23:38:40Z","snapshot_observed_at":"2026-08-16T18:51:47.106761Z","submitted_at":"2021-01-17T23:38:40Z","title":"What Makes Good In-Context Examples for GPT-$3$?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06804","snapshot_observed_at":"2026-08-07T11:17:40.688811Z","title":"What makes good in-context examples for gpt- 3 ? arXiv preprint arXiv:2101.06804, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.688811Z"},"links":{"cited_paper":"/paper/2101.06804","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:09cc205d9755f94bc85baf89f5e0cc028014924a2506cd7076bf422037788826","observation_id":"e4904414-3f30-4017-a16b-a98c5c49f3af","resolution":{"observed_at":"2026-08-07T11:17:40.688811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11624","last_updated":"2024-03-23T16:35:45Z","snapshot_observed_at":"2026-08-16T14:25:44.181612Z","submitted_at":"2024-01-21T23:34:42Z","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.11624","snapshot_observed_at":"2026-08-07T11:17:40.744158Z","title":"In-context learning with retrieved demonstrations for language models: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.744158Z"},"links":{"cited_paper":"/paper/2401.11624","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:66096e86f318f9730dd543e2bba5ce28a0787c3c10c6b6437d7ce252488c2555","observation_id":"cd067063-b0f8-4f55-a7cb-7b0b545e97d1","resolution":{"observed_at":"2026-08-07T11:17:40.744158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09865","last_updated":"2023-06-03T22:51:39Z","snapshot_observed_at":"2026-08-16T16:07:30.517195Z","submitted_at":"2022-12-19T21:34:26Z","title":"Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09865","snapshot_observed_at":"2026-08-07T11:17:40.862413Z","title":"Z-icl: Zero-shot in-context learning with pseudo-demonstrations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.862413Z"},"links":{"cited_paper":"/paper/2212.09865","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:2c2eb92bd768a610b6339fdc50533d1fbefed3b87bdbcb53408601ef1b2b8f7e","observation_id":"aa0e8bb2-d755-4654-8a0c-9d1ac34f48e3","resolution":{"observed_at":"2026-08-07T11:17:40.862413Z","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":"2026-08-07T11:17:44.748426Z","title":"Sfr-embedding-mistral:enhance text retrieval with transfer learning","venue":null,"work_id":"0acdb3c0-43c2-435a-8a01-54381bd8a23e","year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:40.934996Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:c89b38fa451f336159b94627c8bb51b19d2b7c16ea487742e123aaeecf0c8b40","observation_id":"1936a5bd-40ab-4c5d-afa8-34a9e09ed084","resolution":{"observed_at":"2026-08-07T11:17:44.848808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.15943","last_updated":"2022-05-03T10:36:39Z","snapshot_observed_at":"2026-08-16T17:45:21.510670Z","submitted_at":"2021-10-29T17:42:08Z","title":"MetaICL: Learning to Learn In Context","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.15943","snapshot_observed_at":"2026-08-07T11:17:41.052656Z","title":"Metaicl: Learning to learn in context","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.052656Z"},"links":{"cited_paper":"/paper/2110.15943","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:be861bdc3db9a0fc30c1eabf6923834ce3da458c86291673dc9bf97b777f69d7","observation_id":"99f9f3df-09e5-44a6-b359-82d11c0c5746","resolution":{"observed_at":"2026-08-07T11:17:41.052656Z","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":"2026-08-07T11:17:44.603047Z","title":"The matrix cookbook","venue":null,"work_id":"6b5b2e7a-6422-4a48-95bc-ffe463686982","year":2008},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.141066Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:e234547abc77f2adf98a47c22378c1d96452529e95d806f0ff863d5de17c61a5","observation_id":"935c02eb-c88c-4aef-bca1-fdf2c16cffd9","resolution":{"observed_at":"2026-08-07T11:17:44.675277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:44.406166Z","title":"In-context retrieval-augmented language models","venue":null,"work_id":"18817ebb-f312-43ed-a2f1-4f6ecfbb50f5","year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.196258Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:682a867d5533175197d0b7eecdf2501d414621cc57664fa24e3c897308860222","observation_id":"2e416a7a-4703-4175-82fd-0d1f5e49f6d8","resolution":{"observed_at":"2026-08-07T11:17:44.498703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:44.274139Z","title":"Smallcap: Lightweight image captioning prompted with retrieval augmentation","venue":null,"work_id":"3a3f0097-c7b3-43be-9aa9-80ff616c7b2f","year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.309484Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:d854cb71ae37791baf067cd7e2098c91864988f5f474b669a33198b20318e870","observation_id":"e443f08c-ab00-49fb-94a2-1ea1de7d2457","resolution":{"observed_at":"2026-08-07T11:17:44.341800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:17:44.101849Z","title":"Retrieval-augmented transformer for image captioning","venue":null,"work_id":"d991b000-43b1-47b9-8dc9-df1b00078539","year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.393451Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:f0fdad32dc972d4447013fbfe59b0f5c8185a0111890734101027a18e5894af8","observation_id":"e596ff2a-ed2a-47b4-8700-709d2c5fb36f","resolution":{"observed_at":"2026-08-07T11:17:44.186752Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.13693","last_updated":"2022-10-25T01:33:49Z","snapshot_observed_at":"2026-08-16T16:21:26.967838Z","submitted_at":"2022-10-25T01:33:49Z","title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing","version":1},"cited_work":{"arxiv_id":"2210.13693","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.13693","snapshot_observed_at":"2026-08-07T11:17:42.901386Z","title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing","venue":"cs.CL","work_id":"83ff5512-dbc2-4903-944a-8ef4246deb7b","year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.473890Z"},"links":{"cited_paper":"/paper/2210.13693","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:599b54ec2898d690279813efd10914bd3a6abd297be0dca6e9000764cf58a67f","observation_id":"342aa257-ef0e-4c8b-89dd-10ea763c529a","resolution":{"observed_at":"2026-08-07T11:17:42.982988Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.17419","last_updated":"2024-10-03T06:03:14Z","snapshot_observed_at":"2026-08-16T23:13:28.815607Z","submitted_at":"2024-06-25T09:42:56Z","title":"Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.17419","snapshot_observed_at":"2026-08-07T11:17:41.569413Z","title":"Leave no document behind: Benchmarking long-context llms with extended multi-doc qa","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.569413Z"},"links":{"cited_paper":"/paper/2406.17419","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:ae78c87646390c6d3fc76660f1e283295d87c2e58ef8dfcd3221d5d1ec6079ce","observation_id":"e661e810-7120-410f-a6a3-d2e4e31443dd","resolution":{"observed_at":"2026-08-07T11:17:41.569413Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09695","last_updated":"2024-12-04T15:35:48Z","snapshot_observed_at":"2026-08-16T13:09:58.672761Z","submitted_at":"2024-10-13T02:10:26Z","title":"Can In-context Learning Really Generalize to Out-of-distribution Tasks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09695","snapshot_observed_at":"2026-08-07T11:17:41.632679Z","title":"Can in-context learning really generalize to out-of-distribution tasks? arXiv preprint arXiv:2410.09695, 2024 b","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.632679Z"},"links":{"cited_paper":"/paper/2410.09695","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:85bf64ef35dfa923701980aae52c9d8795315be93f56d31ee376a11325270275","observation_id":"f5346b35-224c-428d-bca0-fbc0dd17e265","resolution":{"observed_at":"2026-08-07T11:17:41.632679Z","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":"2026-08-07T11:17:41.716891Z","title":"Certifiably robust rag against retrieval corruption","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.716891Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:0a6fc6f2c1de3577d003ae478b3d33ac23ce920a908b91665c6e1ab61c986fbc","observation_id":"7862e33e-dc62-43bd-9192-131a0aa39c32","resolution":{"observed_at":"2026-08-07T11:17:41.716891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.02080","last_updated":"2022-07-21T07:44:13Z","snapshot_observed_at":"2026-08-10T22:45:29.185791Z","submitted_at":"2021-11-03T09:12:33Z","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02080","snapshot_observed_at":"2026-08-07T11:17:41.814337Z","title":"An explanation of in-context learning as implicit bayesian inference","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.814337Z"},"links":{"cited_paper":"/paper/2111.02080","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:ffa549f73d65cbd6ef11d76892f999b4bd471fb7b897d6087bca0f85d7301aa0","observation_id":"dac30df0-a7e3-4574-8529-13ad7a03afcc","resolution":{"observed_at":"2026-08-07T11:17:41.814337Z","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":"2026-08-07T11:17:43.937904Z","title":"RECOMP : Improving retrieval-augmented LM s with context compression and selective augmentation","venue":null,"work_id":"2f62079b-46a8-43ed-8562-c3d63dd16d64","year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:41.923286Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:185533b0ca2e7df1d66bff203f872353fab2dff75f3f95a9a550a5a7c160fb49","observation_id":"5a408d94-4550-4828-b903-615f277a3121","resolution":{"observed_at":"2026-08-07T11:17:44.006795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.10999","last_updated":"2020-10-21T13:40:15Z","snapshot_observed_at":"2026-08-16T19:11:47.661410Z","submitted_at":"2020-10-21T13:40:15Z","title":"Is Retriever Merely an Approximator of Reader?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.10999","snapshot_observed_at":"2026-08-07T11:17:42.003536Z","title":"Is retriever merely an approximator of reader? arXiv preprint arXiv:2010.10999, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.003536Z"},"links":{"cited_paper":"/paper/2010.10999","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:ec19c45c14be3502952e2ab0d2db6e2f47f51b15b21c107903d916611088ca7d","observation_id":"c2ed5542-c425-40bb-902f-434ced401127","resolution":{"observed_at":"2026-08-07T11:17:42.003536Z","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":"2026-08-07T11:17:43.781356Z","title":"Compositional exemplars for in-context learning","venue":null,"work_id":"b1b1d628-ed98-4056-8d62-b5ac729d5980","year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.053260Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:6559159c1be5208e2263baf2e284ece7148fde907c260e11bdd7cf6ae0bd88ab","observation_id":"504bdad9-5f44-4d46-942b-8ff747489115","resolution":{"observed_at":"2026-08-07T11:17:43.846537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01558","last_updated":"2024-05-05T15:58:24Z","snapshot_observed_at":"2026-08-16T14:55:43.156858Z","submitted_at":"2023-10-02T18:52:35Z","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01558","snapshot_observed_at":"2026-08-07T11:17:42.164458Z","title":"Making retrieval-augmented language models robust to irrelevant context","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.164458Z"},"links":{"cited_paper":"/paper/2310.01558","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:ba75805ef8f96348b98966ca377b48bde4e0b84472b0ef0d6f543393e2eeb59e","observation_id":"d54ed430-e86f-4d44-9091-ceea372959c4","resolution":{"observed_at":"2026-08-07T11:17:42.164458Z","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":"2026-08-07T11:17:42.238089Z","title":"Trained transformers learn linear models in-context","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.238089Z"},"links":{"citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:5aeeebc9734c1c5ec4632a9e3699e91dd8cb8b3059bb76574b6f588d8c6ea46e","observation_id":"3845079c-5d56-4fcf-a55a-40e2d4d1e956","resolution":{"observed_at":"2026-08-07T11:17:42.238089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03493","last_updated":"2022-10-07T12:28:21Z","snapshot_observed_at":"2026-07-06T14:01:50.333970Z","submitted_at":"2022-10-07T12:28:21Z","title":"Automatic Chain of Thought Prompting in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03493","snapshot_observed_at":"2026-08-07T11:17:42.323534Z","title":"Automatic chain of thought prompting in large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.323534Z"},"links":{"cited_paper":"/paper/2210.03493","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:4753a658b32ef50382829681ea63e9a3f2ab97d4b097f2c20c42bd623808bdf3","observation_id":"fd2d55af-4d18-4142-b4f0-cb2d681259d0","resolution":{"observed_at":"2026-08-07T11:17:42.323534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19473","last_updated":"2024-06-21T08:26:36Z","snapshot_observed_at":"2026-08-13T05:27:55.126585Z","submitted_at":"2024-02-29T18:59:01Z","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19473","snapshot_observed_at":"2026-08-07T11:17:42.362748Z","title":"Retrieval-augmented generation for ai-generated content: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.362748Z"},"links":{"cited_paper":"/paper/2402.19473","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:f7d2ad9c8ca5ae6c519425bf6ac0140f3ed067b5dc51181874a054eda5d6ff05","observation_id":"bb610021-4f19-4822-8653-f6736cefce14","resolution":{"observed_at":"2026-08-07T11:17:42.362748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05515","last_updated":"2024-02-15T15:25:47Z","snapshot_observed_at":"2026-08-16T14:20:18.365045Z","submitted_at":"2024-02-08T09:48:02Z","title":"NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning","version":2},"cited_work":{"arxiv_id":"2402.05515","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.05515","snapshot_observed_at":"2026-08-07T11:17:42.561236Z","title":"NoisyICL: A Little Noise in Model Parameters Calibrates In-context Learning","venue":"cs.CL","work_id":"8f371bd6-3c71-4cb2-83de-32aea97d2666","year":2024},"citing_paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T11:17:42.424277Z"},"links":{"cited_paper":"/paper/2402.05515","citing_paper":"/paper/2506.03100"},"observation_digest":"sha256:db315e47e27a98f7dfc197147eb09f101e29e3e557b101fac46702e70220c5f6","observation_id":"5980e085-0b6c-4107-a5e2-98834121e438","resolution":{"observed_at":"2026-08-07T11:17:42.636941Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.03100","last_updated":"2025-06-09T10:35:22Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T22:05:53.415139Z","submitted_at":"2025-06-03T17:31:53Z","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":3,"verified_fuzzy":15},"total_outbound_references":50},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2506.03100."}