{"as_of":"2026-08-19T17:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e6cb05633db741b2cc91c86ec1460d9114de9ab448d83ddfb4b016552e169296","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T14:35:57.180894Z","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":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:33:46.263379Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T12:16:57.647582Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15102","snapshot_observed_at":"2026-08-15T20:33:46.263379Z","title":"best practices","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13545","last_updated":"2025-07-21T14:09:54Z","snapshot_observed_at":"2026-08-19T10:45:44.001778Z","submitted_at":"2025-05-19T03:17:41Z","title":"Know Or Not: a library for evaluating out-of-knowledge base robustness","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T20:33:46.263379Z"},"links":{"cited_paper":"/paper/2411.15102","citing_paper":"/paper/2505.13545"},"observation_digest":"sha256:c807f1308f4ec4635ce76795b5e5b6dbe564bc30a6cf06face0a52ec5a48e5f5","observation_id":"2510c1a9-8587-4c44-8941-b59d435aa1a6","resolution":{"observed_at":"2026-08-15T20:33:46.263379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15102","snapshot_observed_at":"2026-08-02T21:53:25.433447Z","title":"Attribot: A bag of tricks for efficiently approximat- ing leave-one-out context attribution.arXiv preprint arXiv:2411.15102,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.18905","last_updated":"2026-06-05T06:00:51Z","snapshot_observed_at":"2026-08-18T00:28:02.497166Z","submitted_at":"2026-02-21T17:00:54Z","title":"TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T21:53:25.433447Z"},"links":{"cited_paper":"/paper/2411.15102","citing_paper":"/paper/2602.18905"},"observation_digest":"sha256:2b22bd9339a4f99db677e8011c31cba5640e53884dc7c36517d0a0dc3bc69190","observation_id":"b79a54e8-234a-45cf-8d40-d9ec911f0aba","resolution":{"observed_at":"2026-08-02T21:53:25.433447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"cited_work":{"arxiv_id":"2411.15102","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.15102","snapshot_observed_at":"2026-07-02T12:16:57.647582Z","title":"Attribot: A bag of tricks for efficiently approximating leave-one-out context attribution","venue":null,"work_id":"720abb0b-85c9-47b0-9ae7-bfa93c69eeff","year":2024},"citing_paper":{"arxiv_id":"2605.06920","last_updated":"2026-05-07T20:30:44Z","snapshot_observed_at":"2026-08-16T04:36:06.072972Z","submitted_at":"2026-05-07T20:30:44Z","title":"In-Context Credit Assignment via the Core","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-11T00:52:53.665983Z"},"links":{"cited_paper":"/paper/2411.15102","citing_paper":"/paper/2605.06920"},"observation_digest":"sha256:23fe699eb4d42504d15a638b5ecd197ad2b3b90789b1a86001add99aecb9da81","observation_id":"4ad9b449-2f58-416d-8e1c-8f625ad65c23","resolution":{"observed_at":"2026-05-11T05:05:56.881577Z","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":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"cited_work":{"arxiv_id":"2411.15102","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.15102","snapshot_observed_at":"2026-07-02T12:16:57.647582Z","title":"Attribot: A bag of tricks for efficiently approximating leave-one-out context attribution","venue":null,"work_id":"720abb0b-85c9-47b0-9ae7-bfa93c69eeff","year":2024},"citing_paper":{"arxiv_id":"2606.06475","last_updated":"2026-06-04T17:56:31Z","snapshot_observed_at":"2026-08-16T10:36:39.076635Z","submitted_at":"2026-06-04T17:56:31Z","title":"RREDCoT: Segment-Level Reward Redistribution for Reasoning Models","version":1},"reference_index":139,"source":"arxiv_source","source_observed_at":"2026-06-28T02:12:16.029526Z"},"links":{"cited_paper":"/paper/2411.15102","citing_paper":"/paper/2606.06475"},"observation_digest":"sha256:acede8038e14b4c9f1518d898fd9c24b742e222c6259e704050cc93a74bb3fd4","observation_id":"afa32f5e-3908-4c27-8e09-71b88d0bca83","resolution":{"observed_at":"2026-07-02T12:16:57.648842Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2411.15102/citation-record","integrity":"/paper/2411.15102/integrity","json":"/paper/2411.15102/citation-record.json","paper":"/paper/2411.15102"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:35:56.647207Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.647207Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:f6357779ce1e0eb33902e4b27dd17911c37c2df61f4e95d545710cd5d818d3a3","observation_id":"53e04610-d988-4489-b46a-594bec087bb9","resolution":{"observed_at":"2026-08-12T14:35:56.647207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16827","last_updated":"2024-08-02T17:59:31Z","snapshot_observed_at":"2026-08-16T14:15:11.706978Z","submitted_at":"2024-02-26T18:54:35Z","title":"A Survey on Data Selection for Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16827","snapshot_observed_at":"2026-08-12T14:35:56.662157Z","title":"A survey on data selection for language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.662157Z"},"links":{"cited_paper":"/paper/2402.16827","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:52527c168c4a9ee85dc58eaf7cbac812fb5681f5af5b70f41d8d361b773b5c02","observation_id":"6ba14f4a-3b78-40ad-b1d6-9f8e58db72ec","resolution":{"observed_at":"2026-08-12T14:35:56.662157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14985","last_updated":"2025-03-02T03:27:58Z","snapshot_observed_at":"2026-08-16T13:32:26.549245Z","submitted_at":"2024-07-20T21:24:40Z","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14985","snapshot_observed_at":"2026-08-12T14:35:56.673147Z","title":"Generalization vs memorization: Tracing language models' capabilities back to pretraining data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.673147Z"},"links":{"cited_paper":"/paper/2407.14985","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:a138338665c2d20a3acfbc56dcec50cc5ddf470edf1ab28af8c48afbfdd45eaa","observation_id":"c4437a5f-218f-44ee-bc9f-3254a8608198","resolution":{"observed_at":"2026-08-12T14:35:56.673147Z","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":"2026-08-12T14:35:56.681377Z","title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.681377Z"},"links":{"cited_paper":"/paper/2310.11511","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:90178da08b124716a384bbd9ce7c1395781c0fbdc00d3bfba518938fe97f8ee8","observation_id":"1b44e599-efae-43a8-993c-e3b223148af2","resolution":{"observed_at":"2026-08-12T14:35:56.681377Z","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":"2026-08-12T14:35:58.963272Z","title":"If influence functions are the answer, then what is the question? Advances in Neural Information Processing Systems, 2022","venue":null,"work_id":"07997c91-25e1-4a2a-baa4-d7188f05cdc8","year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.688237Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:99d82ce82897fc034ef6eb94c49b8d0f844e9a585a5648f96afc301b14b363c8","observation_id":"9b4d7b84-71fe-4439-b2d8-19b5d380eb67","resolution":{"observed_at":"2026-08-12T14:35:58.973082Z","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":"2026-08-12T14:35:58.930910Z","title":"Influence functions in deep learning are fragile","venue":null,"work_id":"776b8e63-d141-4c3e-b0ce-06667faaa1b2","year":2021},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.696024Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:0e5593d27efe407ca711e80c6583de29b944d7074f42e20f22a422005712c44e","observation_id":"621496e3-05eb-4688-acf2-84aeb28f1b5b","resolution":{"observed_at":"2026-08-12T14:35:58.939057Z","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":"2026-08-12T14:35:58.881034Z","title":"Thread: Circuits","venue":null,"work_id":"65dc0d4a-5412-4bf4-9e67-bf018a4ffd68","year":2020},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.702113Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:5d3aa35133d2ad0de022a2cd351343eaca2f41fc19dac7dffbac5c360af026ca","observation_id":"ce91db4c-a732-4eac-b2ff-4f4ceb8ee141","resolution":{"observed_at":"2026-08-12T14:35:58.895322Z","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":"2406.11813","last_updated":"2024-11-12T16:38:37Z","snapshot_observed_at":"2026-08-18T05:44:08.166378Z","submitted_at":"2024-06-17T17:54:40Z","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11813","snapshot_observed_at":"2026-08-12T14:35:56.709822Z","title":"How do large language models acquire factual knowledge during pretraining? arXiv preprint arXiv:2406.11813, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.709822Z"},"links":{"cited_paper":"/paper/2406.11813","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:56c4d30769bd757f574cc502f71ea593a1de8b77a1c45fbe6efe005fb60a2791","observation_id":"a97ef5ff-8ad5-4b5b-ac33-9ca856e05aa6","resolution":{"observed_at":"2026-08-12T14:35:56.709822Z","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":"2026-08-12T14:35:58.853185Z","title":"Complex claim verification with evidence retrieved in the wild","venue":null,"work_id":"bdd1bf2b-5b6d-41be-aa49-6d9c31b42320","year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.717700Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:1e1fd2bdcf54a9c5d31b6ac19d1221b712dc045139a364042a768287e1ec1033","observation_id":"e2fcadd2-d15f-4de8-ad84-1c786583c60b","resolution":{"observed_at":"2026-08-12T14:35:58.861265Z","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":"2405.13954","last_updated":"2024-05-22T19:39:05Z","snapshot_observed_at":"2026-08-16T13:50:29.559994Z","submitted_at":"2024-05-22T19:39:05Z","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13954","snapshot_observed_at":"2026-08-12T14:35:56.730681Z","title":"What is your data worth to gpt? llm-scale data valuation with influence functions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.730681Z"},"links":{"cited_paper":"/paper/2405.13954","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:fca745b72f52ee0a824d0e8c7058b5d259b5c17ad30bcd2e2c80a1848e5ba5dd","observation_id":"b9165765-447f-4720-9814-63c984db6434","resolution":{"observed_at":"2026-08-12T14:35:56.730681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00729","last_updated":"2024-09-13T20:26:40Z","snapshot_observed_at":"2026-08-16T13:22:18.649123Z","submitted_at":"2024-09-01T14:36:36Z","title":"ContextCite: Attributing Model Generation to Context","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00729","snapshot_observed_at":"2026-08-12T14:35:56.740603Z","title":"Contextcite: Attributing model generation to context","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.740603Z"},"links":{"cited_paper":"/paper/2409.00729","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:dc625d06a0319847c8b39ba28dcd25cedf511232623c1390874e0b78141f5b9e","observation_id":"885ebea6-fa67-483e-a71c-60ab5588f4aa","resolution":{"observed_at":"2026-08-12T14:35:56.740603Z","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":"2026-08-12T14:35:58.831625Z","title":"Smith, and Matt Gardner","venue":null,"work_id":"c0bdd643-0ba1-46e7-95c9-ca76a242285e","year":2021},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.748552Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:4d32f32e8634e377fc8bff4d55fe1c4214017ae51720cbd291d0dda33d31eca0","observation_id":"1702fd33-82f3-4800-9a7d-cfd7e5e632cc","resolution":{"observed_at":"2026-08-12T14:35:58.838203Z","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":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-12T14:35:56.756648Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.756648Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:c847775c3a98a1217c2163e57a52a468ccbd2926ad5f0d4160ebe2c225d47c5b","observation_id":"ee5e0c4b-39b7-47bc-8ca6-7f45db96445b","resolution":{"observed_at":"2026-08-12T14:35:56.756648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15853","last_updated":"2023-05-25T08:44:11Z","snapshot_observed_at":"2026-08-16T15:29:49.823058Z","submitted_at":"2023-05-25T08:44:11Z","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15853","snapshot_observed_at":"2026-08-12T14:35:56.772102Z","title":"Sequential integrated gradients: a simple but effective method for explaining language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.772102Z"},"links":{"cited_paper":"/paper/2305.15853","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:5ea92c6bbabef829c13856cc59d92e66a8ccb7ac321689ff8689d43e333b9655","observation_id":"ba70c3f0-409b-4a25-90a7-c941605337f5","resolution":{"observed_at":"2026-08-12T14:35:56.772102Z","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":"2026-08-12T14:35:58.811319Z","title":"RARR : Researching and revising what language models say, using language models","venue":null,"work_id":"30abcfb3-5e3e-4baa-bfbb-767e037fac7c","year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.779002Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:66c91f33989ea8649acfe67521fd58dc69e3e2ac7e9058ce02df15be7f32b522","observation_id":"87b46684-f85a-4a1c-b17d-19a5fde2aabd","resolution":{"observed_at":"2026-08-12T14:35:58.817532Z","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":"2305.14627","last_updated":"2023-10-31T15:04:35Z","snapshot_observed_at":"2026-08-17T02:40:50.509296Z","submitted_at":"2023-05-24T01:53:49Z","title":"Enabling Large Language Models to Generate Text with Citations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14627","snapshot_observed_at":"2026-08-12T14:35:56.785701Z","title":"Enabling large language models to generate text with citations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.785701Z"},"links":{"cited_paper":"/paper/2305.14627","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:9a54f2e889e9d46b2d27829d369a9babeb67af8771c8459c9385324627354521","observation_id":"6418f845-e94f-4158-9cff-5f5156a5786e","resolution":{"observed_at":"2026-08-12T14:35:56.785701Z","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":"10.1016/j.mcpdig.2023.05.004","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:35:57.258755Z","title":"Learning to fake it: Limited responses and fabricated references provided by chatgpt for medical questions","venue":null,"work_id":"6732799c-e3d8-4cb9-a483-f2064be3a7d3","year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.793958Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:e5a91bf2756aa70fe69e424d061d9d47d50eeb02ac9a98fc53627300161b2049","observation_id":"7162a793-9f5b-45eb-9060-69070782d5ff","resolution":{"observed_at":"2026-08-12T14:35:57.270798Z","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":"2308.03296","last_updated":"2023-08-07T04:47:42Z","snapshot_observed_at":"2026-08-18T02:00:55.415271Z","submitted_at":"2023-08-07T04:47:42Z","title":"Studying Large Language Model Generalization with Influence Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03296","snapshot_observed_at":"2026-08-12T14:35:56.799968Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.799968Z"},"links":{"cited_paper":"/paper/2308.03296","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:5e631d74838d4cc3e1ccf6bb1d40bfdbe26a5ce2c6e6f92a30aacfe54d0fccd3","observation_id":"020c4696-1f56-416f-8c7e-0674163428d2","resolution":{"observed_at":"2026-08-12T14:35:56.799968Z","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":"2026-08-12T14:35:56.808789Z","title":null,"venue":null,"work_id":null,"year":1969},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.808789Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:74c5f364d92e6c1c4449b51d700cfbe3f0c8de3ea15ce6abffd7198ea4db922f","observation_id":"17510f07-1ef2-407d-ab8c-79a6c9ea3a9a","resolution":{"observed_at":"2026-08-12T14:35:56.808789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15556","last_updated":"2022-03-29T13:38:03Z","snapshot_observed_at":"2026-08-09T19:52:33.533277Z","submitted_at":"2022-03-29T13:38:03Z","title":"Training Compute-Optimal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.15556","snapshot_observed_at":"2026-08-12T14:35:56.815101Z","title":"Rae, Oriol Vinyals, and Laurent Sifre","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.815101Z"},"links":{"cited_paper":"/paper/2203.15556","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:7c18ff3be2e7403ec896dc5dbcffda17f6b5239dad4a4a11ac3fb1b4a000e633","observation_id":"1546b918-24d8-4338-920a-934621c3a129","resolution":{"observed_at":"2026-08-12T14:35:56.815101Z","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":"2026-08-12T14:35:58.791785Z","title":"Retrieving supporting evidence for generative question answering","venue":null,"work_id":"d13711bf-61b5-4cf2-bccf-2571cc163a45","year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.823978Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:9d929ae8764f39250c47f64647013509ffd2105389acbda731c756fbb4c1c6af","observation_id":"66be7902-0580-4390-8139-6ea6e138dd3e","resolution":{"observed_at":"2026-08-12T14:35:58.798561Z","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":"2026-08-12T14:35:58.750766Z","title":null,"venue":null,"work_id":"c978ad20-345d-444f-89ed-82066f7ba921","year":2019},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.831289Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:1b2170aa3b7dc21d21162fe4f17feb527a06bd62a750ec9a5b36caebd0a85642","observation_id":"7e73fbd9-8e30-4a05-b729-e28c9661f56a","resolution":{"observed_at":"2026-08-12T14:35:58.758360Z","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":"2026-08-12T14:35:56.841429Z","title":"Large language models struggle to learn long-tail knowledge","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.841429Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:cd77af988570c146ab083ce77fc5f18558125f389db76ed8af39375f7b9ea45e","observation_id":"f675a1e2-46bf-4ff5-a3db-3966a5e97731","resolution":{"observed_at":"2026-08-12T14:35:56.841429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-12T14:35:56.848417Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.848417Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:1a36ab40f874769aaee13ca751a3620d724386d17437eb908996a242a636372f","observation_id":"5f3a38af-fb4a-44d6-9964-c5a0491e2fd5","resolution":{"observed_at":"2026-08-12T14:35:56.848417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.04730","last_updated":"2020-12-29T22:40:43Z","snapshot_observed_at":"2026-08-15T02:28:36.697260Z","submitted_at":"2017-03-14T21:07:01Z","title":"Understanding Black-box Predictions via Influence Functions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.04730","snapshot_observed_at":"2026-08-12T14:35:56.859135Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.859135Z"},"links":{"cited_paper":"/paper/1703.04730","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:74d319b32f9dfd2de4def4e1070ce253ab6a4d4707e86f28d70652724e5dbb34","observation_id":"00f8e26e-d780-4634-9956-29ef216c453f","resolution":{"observed_at":"2026-08-12T14:35:56.859135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10149","last_updated":"2024-11-06T14:50:40Z","snapshot_observed_at":"2026-08-16T13:42:53.753710Z","submitted_at":"2024-06-14T16:00:29Z","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10149","snapshot_observed_at":"2026-08-12T14:35:56.867210Z","title":"Babilong: Testing the limits of llms with long context reasoning-in-a-haystack","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.867210Z"},"links":{"cited_paper":"/paper/2406.10149","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:1aa84df86be78fcd55b5c2888ed0f0fa25effe8eaecab30558d916069b7fc681","observation_id":"79968158-cc59-4002-8267-f88c366eb762","resolution":{"observed_at":"2026-08-12T14:35:56.867210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.11401","last_updated":"2021-04-12T15:42:18Z","snapshot_observed_at":"2026-08-07T05:44:30.677502Z","submitted_at":"2020-05-22T21:34:34Z","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.11401","snapshot_observed_at":"2026-08-12T14:35:56.875343Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.875343Z"},"links":{"cited_paper":"/paper/2005.11401","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:0ce0d988ebae55529d9e48cf6132779f626915cd714602f66f05eb6bf98a8f57","observation_id":"7432d9d0-9697-4dca-baa4-928d8415f0df","resolution":{"observed_at":"2026-08-12T14:35:56.875343Z","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":"2026-08-12T14:35:58.702857Z","title":"Improving attributed text generation of large language models via preference learning","venue":null,"work_id":"8fe1ff0f-9eaa-4655-932c-1210ee90ff74","year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.882537Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:cf0ef43ae2e3c27981bebd8610eae5a20fc77e120d36eb9fb3c1313d3ef35aba","observation_id":"cd4e48c9-b7e6-4fb9-b0bf-f00b91c6d16f","resolution":{"observed_at":"2026-08-12T14:35:58.708986Z","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":"1506.01066","last_updated":"2016-01-08T18:10:22Z","snapshot_observed_at":"2026-08-18T07:36:20.224145Z","submitted_at":"2015-06-02T21:17:31Z","title":"Visualizing and Understanding Neural Models in NLP","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.01066","snapshot_observed_at":"2026-08-12T14:35:56.888448Z","title":"Visualizing and understanding neural models in nlp","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.888448Z"},"links":{"cited_paper":"/paper/1506.01066","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:75dc694739f6ebda806ba9f76e7e5e732f1dd6086e233ffc4cd2760d0f20a296","observation_id":"86457418-9281-4eb1-afac-d31d13fa8029","resolution":{"observed_at":"2026-08-12T14:35:56.888448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.08220","last_updated":"2017-01-10T01:40:51Z","snapshot_observed_at":"2026-08-14T21:23:47.203647Z","submitted_at":"2016-12-24T21:36:07Z","title":"Understanding Neural Networks through Representation Erasure","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.08220","snapshot_observed_at":"2026-08-12T14:35:56.894965Z","title":"Understanding neural networks through representation erasure","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.894965Z"},"links":{"cited_paper":"/paper/1612.08220","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:394f1b2b1d3af016188270afbfddd19579c49da257351f853805798f75d05852","observation_id":"bfcba844-1f43-43b0-8cab-d553a787d6e7","resolution":{"observed_at":"2026-08-12T14:35:56.894965Z","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":"2026-08-12T14:35:58.680263Z","title":"LL atrieval: LLM -verified retrieval for verifiable generation","venue":null,"work_id":"d49e4ceb-8b62-47d9-910c-bd4ee362d875","year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.902151Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:5d0551045588fd9e4a972f0ff4ad0d7f7c7e4f6e31ad70a1e22a2f69516e3d09","observation_id":"80f8c8d4-2158-4477-8faa-5bbf6709d005","resolution":{"observed_at":"2026-08-12T14:35:58.686542Z","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":"2304.09848","last_updated":"2023-10-23T19:11:38Z","snapshot_observed_at":"2026-08-16T15:39:11.826409Z","submitted_at":"2023-04-19T17:56:12Z","title":"Evaluating Verifiability in Generative Search Engines","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.09848","snapshot_observed_at":"2026-08-12T14:35:56.912538Z","title":"Liu, Tianyi Zhang, and Percy Liang","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.912538Z"},"links":{"cited_paper":"/paper/2304.09848","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:7ddbbdcce14ee77001ef93930719c86c3d9b810f2dd26683650be0bcc361cded","observation_id":"8afa6bf8-66d8-4a00-96cc-80a67853e2f3","resolution":{"observed_at":"2026-08-12T14:35:56.912538Z","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":"2026-08-12T14:35:58.660106Z","title":"Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang","venue":null,"work_id":"8b63022b-0771-48a8-b436-b03a5fbcb487","year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.918941Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:898ea2f589fab546b02fa6edcb961d2765418053cc4be90f03f11727964009cb","observation_id":"5df15256-7e3b-41d9-9de5-3909ded6cbbe","resolution":{"observed_at":"2026-08-12T14:35:58.667487Z","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":"1705.07874","last_updated":"2017-11-25T03:53:32Z","snapshot_observed_at":"2026-08-14T20:59:00.743160Z","submitted_at":"2017-05-22T17:38:10Z","title":"A Unified Approach to Interpreting Model Predictions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07874","snapshot_observed_at":"2026-08-12T14:35:56.926438Z","title":"A unified approach to interpreting model predictions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.926438Z"},"links":{"cited_paper":"/paper/1705.07874","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:593d227f09ce10f4fb826890720748bc054654ed41c31ab582fab3a052c66b10","observation_id":"9e0a528a-ec79-418e-bc23-e4334f9f4aab","resolution":{"observed_at":"2026-08-12T14:35:56.926438Z","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":"2026-08-12T14:35:58.624572Z","title":"Manning, Prabhakar Raghavan, and Hinrich Sch\\\" u tze","venue":null,"work_id":"664a37f9-801c-4154-a6e3-fd7e348c44f9","year":2008},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.938141Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:d858a1381dcd57f6d2c6643f4bd6bff2c7fbfee97e08feb583d5d25cfb21e618","observation_id":"1c05b58b-1066-4177-a002-6295bf8f3299","resolution":{"observed_at":"2026-08-12T14:35:58.638252Z","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":"1806.08730","last_updated":"2018-06-20T16:39:26Z","snapshot_observed_at":"2026-08-17T06:16:47.122449Z","submitted_at":"2018-06-20T16:39:26Z","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08730","snapshot_observed_at":"2026-08-12T14:35:56.950025Z","title":"The natural language decathlon: Multitask learning as question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.950025Z"},"links":{"cited_paper":"/paper/1806.08730","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:68cd9b74226bffeee3ff6f0651f6102d5662ea9b3d80e0f4f3d022a4d32f7cf4","observation_id":"0850fdb7-aa72-4a1d-96bd-ce27dd428f85","resolution":{"observed_at":"2026-08-12T14:35:56.950025Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11147","last_updated":"2022-03-21T17:26:29Z","snapshot_observed_at":"2026-08-01T19:23:25.711617Z","submitted_at":"2022-03-21T17:26:29Z","title":"Teaching language models to support answers with verified quotes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11147","snapshot_observed_at":"2026-08-12T14:35:56.956238Z","title":"Teaching language models to support answers with verified quotes","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.956238Z"},"links":{"cited_paper":"/paper/2203.11147","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:1f97e78fa3ce3d3ae63fec72c6666b15fcdb7cf2364397227a7913f47bf7c74f","observation_id":"6b9da4f2-ee22-4cba-ac7b-771f0221a466","resolution":{"observed_at":"2026-08-12T14:35:56.956238Z","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":"2026-08-12T14:35:58.601947Z","title":"Exploring the role of BERT token representations to explain sentence probing results","venue":null,"work_id":"f268962c-aac0-45d3-918f-db4b0ffbf783","year":2021},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.961338Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:4a7819af7127ebd010000663ad874cace469bdb2f40991ede518eccbf20e1bc9","observation_id":"819c2131-4ff7-4230-9a30-55733f864e45","resolution":{"observed_at":"2026-08-12T14:35:58.607429Z","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":"2112.09332","last_updated":"2022-06-01T19:08:11Z","snapshot_observed_at":"2026-08-19T02:54:55.334346Z","submitted_at":"2021-12-17T05:43:43Z","title":"WebGPT: Browser-assisted question-answering with human feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09332","snapshot_observed_at":"2026-08-12T14:35:56.975038Z","title":"Webgpt: Browser-assisted question-answering with human feedback","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.975038Z"},"links":{"cited_paper":"/paper/2112.09332","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:ef45661537b0f627360231f7b95723348cbf7514484710278460068f9f36b6e3","observation_id":"e9a0b72b-b6e6-457e-8095-c47d4a1a5ecf","resolution":{"observed_at":"2026-08-12T14:35:56.975038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-12T14:35:56.981741Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.981741Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:c3e75b5a7ec5480ef160c4e9e31a13f41751a5b4747fa9008378f72dc68d499d","observation_id":"8a401436-90c5-4442-a0c7-3f02d27b39ca","resolution":{"observed_at":"2026-08-12T14:35:56.981741Z","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":"2026-08-12T14:35:58.579892Z","title":"Credible without credit: Domain experts assess generative language models","venue":null,"work_id":"450a81ac-f547-42b7-9246-a7c5e1ddc4b4","year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.988309Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:191c7be0c9383819cedf2f864c12beebe80f12a8d29fff6f23e19a1523d10c01","observation_id":"429fe5ea-db77-41f4-bcf1-fb8b97e1415a","resolution":{"observed_at":"2026-08-12T14:35:58.585249Z","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":"2211.05102","last_updated":"2022-11-09T18:50:38Z","snapshot_observed_at":"2026-08-16T16:17:24.089886Z","submitted_at":"2022-11-09T18:50:38Z","title":"Efficiently Scaling Transformer Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05102","snapshot_observed_at":"2026-08-12T14:35:56.995517Z","title":"Efficiently scaling transformer inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:56.995517Z"},"links":{"cited_paper":"/paper/2211.05102","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:aed06a0be619b5061e5966ca243bae2f1837b621f02b9554bd69cffd6f0e62f0","observation_id":"905d6d42-0609-497b-9af6-656f9025c5a6","resolution":{"observed_at":"2026-08-12T14:35:56.995517Z","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":"2026-08-12T14:35:58.554754Z","title":null,"venue":null,"work_id":"a5cf9f64-86eb-4b39-9611-7dfc94f5635f","year":2020},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.001542Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:b4d286e332c3917008011e9556a6e501e19615061a2776d199efa1523922d706","observation_id":"3676861e-733c-44f7-a7fb-3b21a6d99e1a","resolution":{"observed_at":"2026-08-12T14:35:58.560624Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:35:58.528027Z","title":"Estimating training data influence by tracing gradient descent","venue":null,"work_id":"958981bf-e019-4c8f-82e7-8996a77e7ed8","year":2020},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.008005Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:dcbee74406fabda454091a3c2bd5346503de3d5c63ace93f93eb8d87b6b15c81","observation_id":"337e3591-2620-4286-b416-8537b1e57b07","resolution":{"observed_at":"2026-08-12T14:35:58.535232Z","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":"2026-08-12T14:35:58.509993Z","title":"Know what you don ' t know: Unanswerable questions for SQ u AD","venue":null,"work_id":"de17b4ba-658c-4036-a9af-24ee06a1ed3e","year":2018},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.014504Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:ed76920e81672f5b5635b4b27ab2e2c675cca930b71c751aaa53d0c5e0596ca8","observation_id":"21b57263-992e-42e1-b2aa-87fc4f8e3fe5","resolution":{"observed_at":"2026-08-12T14:35:58.515053Z","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":"2026-08-12T14:35:58.491046Z","title":"Impact of pretraining term frequencies on few-shot numerical reasoning","venue":null,"work_id":"a2fc10b9-eff0-4842-ad28-81fe6dbf7428","year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.021187Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:cc2ec7b60780c9391d07b71a40317765520b30f832720f9946ae6dd1abd73a5e","observation_id":"85b3b081-28ba-43db-8f2e-d182c8fffa23","resolution":{"observed_at":"2026-08-12T14:35:58.498341Z","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":"2026-08-12T14:35:58.469908Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks","venue":null,"work_id":"99d48cb9-2b5c-471c-9a87-3b26fd79bcc5","year":2019},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.029916Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:842531850f17ac37332e285c2d55481d5c4d2f77788974643cf7217ba69f4274","observation_id":"e85b7631-15b5-41b6-b3f7-c649ba476fea","resolution":{"observed_at":"2026-08-12T14:35:58.476108Z","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":"1602.04938","last_updated":"2016-08-09T17:54:52Z","snapshot_observed_at":"2026-08-14T22:10:11.360520Z","submitted_at":"2016-02-16T08:20:14Z","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.04938","snapshot_observed_at":"2026-08-12T14:35:57.039395Z","title":"why should i trust you?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.039395Z"},"links":{"cited_paper":"/paper/1602.04938","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:2d3cba93729e64c5b8be76d15c113b6948bb7b7fa2ce6d7bddd145c3ab8bf6f6","observation_id":"66104c41-9473-4eeb-b75a-4af82136899e","resolution":{"observed_at":"2026-08-12T14:35:57.039395Z","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":"1706.1983","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:35:57.666690Z","title":"Percentage points for a generalized esd many-outlier procedure","venue":null,"work_id":"adf9fb81-48fc-467f-b14a-2cad79f87af7","year":1983},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.049352Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:3e5c85e474d663d069f167de06314371034ecbb1016e5cdd747170c302a9e626","observation_id":"b90edd80-704e-4350-8cd9-93f9b7a0ec00","resolution":{"observed_at":"2026-08-12T14:35:57.679509Z","resolver_source":"raw_fallback","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":"2026-08-12T14:35:58.448481Z","title":"Discretized integrated gradients for explaining language models","venue":null,"work_id":"2f277f33-ac2c-4365-8cfa-bae42a9ef29a","year":2021},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.057201Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:6cdc364a78abdd19026f1abb9a1aa93e7fd60663d718317ca614d0b2aaa57c8d","observation_id":"fe4aeb78-cd3e-4246-818a-38b6e5e38703","resolution":{"observed_at":"2026-08-12T14:35:58.455344Z","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":"1906.03731","last_updated":"2019-06-09T22:46:12Z","snapshot_observed_at":"2026-08-14T16:18:26.568951Z","submitted_at":"2019-06-09T22:46:12Z","title":"Is Attention Interpretable?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.03731","snapshot_observed_at":"2026-08-12T14:35:57.062338Z","title":null,"venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.062338Z"},"links":{"cited_paper":"/paper/1906.03731","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:e61700d4eb96e8f056942709e6cf54f0cfab358a49e0384d298c9df5d1dd27de","observation_id":"514e84e7-ff44-4e59-89d5-f16645fa73ce","resolution":{"observed_at":"2026-08-12T14:35:57.062338Z","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":"2026-08-12T14:35:58.426659Z","title":"Integrated directional gradients: Feature interaction attribution for neural NLP models","venue":null,"work_id":"ffe36b17-9922-4673-ac27-5acd6f900bc2","year":2021},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.070011Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:2cb5b12cfa163d80289cc2a308b489ad3611ea89818e82b64d1d21e707f26af1","observation_id":"2dccc37f-082b-436c-91fc-936d43a7d499","resolution":{"observed_at":"2026-08-12T14:35:58.434834Z","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":"2312.09075","last_updated":"2024-10-18T09:02:46Z","snapshot_observed_at":"2026-08-16T14:34:42.764822Z","submitted_at":"2023-12-14T16:10:56Z","title":"Towards Verifiable Text Generation with Evolving Memory and Self-Reflection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09075","snapshot_observed_at":"2026-08-12T14:35:57.077237Z","title":"Towards verifiable text generation with evolving memory and self-reflection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.077237Z"},"links":{"cited_paper":"/paper/2312.09075","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:d819846ca908fa7193c41461eff74603b7049b56fe9c7de96a062e1e18885094","observation_id":"037978e8-d9a4-4de2-a24e-b507ac452071","resolution":{"observed_at":"2026-08-12T14:35:57.077237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-12T14:35:57.082725Z","title":"Gemini: A family of highly capable multimodal models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.082725Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:22cf1500a0434acb8c2d89fccc5b826169b7e55aa04b83cb3a4c83a191529a25","observation_id":"a8c07973-1e5c-4370-8d8b-6a52d7dd7ce5","resolution":{"observed_at":"2026-08-12T14:35:57.082725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.08239","last_updated":"2022-02-10T16:30:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-20T15:44:37Z","title":"LaMDA: Language Models for Dialog Applications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.08239","snapshot_observed_at":"2026-08-12T14:35:57.088116Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.088116Z"},"links":{"cited_paper":"/paper/2201.08239","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:e32c2cf671559e5776cbea555bef394dcf60b2b390f918f8f0b89ab8a4405659","observation_id":"c039265b-4e73-424d-bc6f-572e3c0b60b7","resolution":{"observed_at":"2026-08-12T14:35:57.088116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03762","last_updated":"2023-08-02T00:41:18Z","snapshot_observed_at":"2026-08-19T04:42:40.974785Z","submitted_at":"2017-06-12T17:57:34Z","title":"Attention Is All You Need","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03762","snapshot_observed_at":"2026-08-12T14:35:57.094872Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.094872Z"},"links":{"cited_paper":"/paper/1706.03762","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:42853a3f89dd9c7f79a874ef17eb9fa9b8649e2945ebeca7017abded2b2179f4","observation_id":"f1a14885-24b5-457e-80cd-54c6abce34b2","resolution":{"observed_at":"2026-08-12T14:35:57.094872Z","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":"2026-08-12T14:35:58.404319Z","title":"`` according to","venue":null,"work_id":"187a977b-d401-4542-8ba2-f39f52db2add","year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.102163Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:a90cec8a6141e4d0bc7c522eb8efb3fa9d0e4d5fb1eafc687ead77198530c3c2","observation_id":"91cd2c7f-1315-4013-942d-914cdc5b1282","resolution":{"observed_at":"2026-08-12T14:35:58.411479Z","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":"2026-08-12T14:35:58.382846Z","title":"Attention is not not explanation","venue":null,"work_id":"eadf10d8-3f8d-43ad-8432-3c7c2f1a37bd","year":2019},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.111145Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:eff9f9955e3aa6b3642fc5d7d919487db0bbe56c3f40175fce67774f93325e07","observation_id":"27294988-9b35-447a-b291-b03d55e3fe43","resolution":{"observed_at":"2026-08-12T14:35:58.389329Z","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":"2004.14786","last_updated":"2021-05-28T04:17:32Z","snapshot_observed_at":"2026-08-12T20:20:45.728285Z","submitted_at":"2020-04-30T14:02:29Z","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","version":3},"cited_work":{"arxiv_id":"2004.14786","doi":null,"metadata_source":"pith","pith_arxiv_id":"2004.14786","snapshot_observed_at":"2026-08-12T14:35:57.420952Z","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","venue":"cs.CL","work_id":"ed56184e-b6d6-482c-b3dc-2d9411d16f00","year":2020},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.119880Z"},"links":{"cited_paper":"/paper/2004.14786","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:b1073155c00ea96d58c661a1e0f129821616f0e189e48913e9a1e08823d8d651","observation_id":"b891457e-ec68-4df3-a50b-ecd23b942b88","resolution":{"observed_at":"2026-08-12T14:35:57.427815Z","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":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-08-17T11:08:48.802438Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-08-12T14:35:57.128678Z","title":"Qwen2 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.128678Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:02aedd5f52719297259f71f7b5244ebfb0649fdcd99c8cd8e1b4daf797e6c698","observation_id":"5a8bb4a0-d0c4-4af4-a368-05c1cbb6d183","resolution":{"observed_at":"2026-08-12T14:35:57.128678Z","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":"2026-08-12T14:35:57.138158Z","title":"Cohen, Ruslan Salakhutdinov, and Christopher D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.138158Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:808f37685b7e7a6fbab8a8e57d7b54ce668239ce330da86aeafb7d02755582f0","observation_id":"625f225c-12ba-4f53-8f96-71903331d408","resolution":{"observed_at":"2026-08-12T14:35:57.138158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.10419","last_updated":"2022-05-23T17:40:55Z","snapshot_observed_at":"2026-08-16T17:19:44.147547Z","submitted_at":"2022-02-21T18:32:24Z","title":"Interpreting Language Models with Contrastive Explanations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.10419","snapshot_observed_at":"2026-08-12T14:35:57.144257Z","title":"Interpreting language models with contrastive explanations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.144257Z"},"links":{"cited_paper":"/paper/2202.10419","citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:9a6e11a49a792dccb692cf1442c8723a6d88dee6df3fca99701a8b0a7fa04083","observation_id":"08be7fc1-c499-47f8-9b67-ad625d496438","resolution":{"observed_at":"2026-08-12T14:35:57.144257Z","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":"2026-08-12T14:35:58.334699Z","title":"Chatgpt hallucinates when attributing answers","venue":null,"work_id":"b89241f2-4c00-4d5f-aded-607337a10c76","year":2023},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.152820Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:7fe1b269f7f8f53882514ba775f53e4bd3a5460a67032e56cbe6f1b80dc304a0","observation_id":"d1ee1281-8713-420b-a23f-085ed1736d0e","resolution":{"observed_at":"2026-08-12T14:35:58.340626Z","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":"2026-08-12T14:35:57.163335Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.163335Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:5686abb270b4752ddbc9c32c34f4206512488b28e720ba08f126004fb69005a1","observation_id":"35fba0f7-d3cc-4cf4-a4d2-24ceb33819df","resolution":{"observed_at":"2026-08-12T14:35:57.163335Z","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":"2026-08-12T14:35:57.171316Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.171316Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:eda741ec1da775fa73a3afac4e54b470991930de4786fb8ba1ab5dd3715a9588","observation_id":"c88faba7-656e-4a99-8dc7-1ce9675d72af","resolution":{"observed_at":"2026-08-12T14:35:57.171316Z","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":"2026-08-12T14:35:57.180894Z","title":"tab:theoretical_flops table","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution","version":3},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-12T14:35:57.180894Z"},"links":{"citing_paper":"/paper/2411.15102"},"observation_digest":"sha256:5539d7118b0d77893161112eff032b216ef53869535bbfafdb27117205c9af5a","observation_id":"cff3876c-63ed-462b-88d5-3e1a6014a0fd","resolution":{"observed_at":"2026-08-12T14:35:57.180894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.15102","last_updated":"2025-03-21T15:47:53Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T23:47:27.200157Z","submitted_at":"2024-11-22T18:06:14Z","title":"AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":41,"verified_exact":3,"verified_fuzzy":22},"total_outbound_references":66},"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 19 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 4 inbound Pith citation observations for arXiv:2411.15102."}