{"as_of":"2026-08-10T13:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90d0125bbb273e9eb69335ec6025d84465a937b9f9f7470e6cd88332b522d070","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:54:43.905457Z","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":"2026-07-01T16:25:50.066636Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00794","snapshot_observed_at":"2026-08-06T21:54:43.905457Z","title":"& Shan, B","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.23182","last_updated":"2025-07-11T14:05:02Z","snapshot_observed_at":"2026-08-10T01:07:31.993061Z","submitted_at":"2025-06-29T10:50:46Z","title":"Attribution assignment for deep-generative sequence models enables interpretability analysis using positive-only data","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T21:54:43.905457Z"},"links":{"cited_paper":"/paper/2402.00794","citing_paper":"/paper/2506.23182"},"observation_digest":"sha256:81a7a974983ec761614c5027c13196cde7c086edc01822a51cffe0e83ad6136f","observation_id":"7a3846bb-28fb-4116-8a76-b2ede2c0469d","resolution":{"observed_at":"2026-08-06T21:54:43.905457Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00794","snapshot_observed_at":"2026-08-03T12:26:59.690104Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2601.03089","last_updated":"2026-05-26T16:19:50Z","snapshot_observed_at":"2026-08-09T08:13:47.154780Z","submitted_at":"2026-01-06T15:22:39Z","title":"Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Information","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-03T12:26:59.690104Z"},"links":{"cited_paper":"/paper/2402.00794","citing_paper":"/paper/2601.03089"},"observation_digest":"sha256:6e03f80b1a83c3e1c5a738f2a88c82c8264919f1ba8b484d100534cc6d2ea229","observation_id":"45867db1-62d7-4a11-a338-940656b3b9cb","resolution":{"observed_at":"2026-08-03T12:26:59.690104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","version":2},"cited_work":{"arxiv_id":"2402.00794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.00794","snapshot_observed_at":"2026-07-01T16:25:50.066636Z","title":"ReAGent: A Model-Agnostic Feature Attribution Method for Generative Language Models","venue":null,"work_id":"7ce8c9e9-a2f4-4459-ba1c-cb4c944bb0a7","year":2024},"citing_paper":{"arxiv_id":"2604.13258","last_updated":"2026-04-14T19:43:43Z","snapshot_observed_at":"2026-07-06T23:01:19.191464Z","submitted_at":"2026-04-14T19:43:43Z","title":"Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-05-10T15:23:53.906870Z"},"links":{"cited_paper":"/paper/2402.00794","citing_paper":"/paper/2604.13258"},"observation_digest":"sha256:52a6b5cc3e6a3f04bdcb79c3ae63be460e1d629483baaa648c96b3178fbfc936","observation_id":"affa6095-360b-406a-94af-1c11ea39cfa2","resolution":{"observed_at":"2026-05-11T10:41:02.203269Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","version":2},"cited_work":{"arxiv_id":"2402.00794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.00794","snapshot_observed_at":"2026-07-01T16:25:50.066636Z","title":"ReAGent: A Model-Agnostic Feature Attribution Method for Generative Language Models","venue":null,"work_id":"7ce8c9e9-a2f4-4459-ba1c-cb4c944bb0a7","year":2024},"citing_paper":{"arxiv_id":"2605.23080","last_updated":"2026-06-01T07:17:20Z","snapshot_observed_at":"2026-08-06T20:39:36.338304Z","submitted_at":"2026-05-21T22:27:04Z","title":"The Attribution Contract: Feature Attribution for Generative Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-25T05:31:09.737172Z"},"links":{"cited_paper":"/paper/2402.00794","citing_paper":"/paper/2605.23080"},"observation_digest":"sha256:8fd8a8ee4fc042a414a42320996473e1223854f25fc9b6d9f03288f364a8f53d","observation_id":"1c549040-4912-41ca-b7c8-6bb166e8e0d4","resolution":{"observed_at":"2026-05-25T05:36:40.485068Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","version":2},"cited_work":{"arxiv_id":"2402.00794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.00794","snapshot_observed_at":"2026-07-01T16:25:50.066636Z","title":"ReAGent: A Model-Agnostic Feature Attribution Method for Generative Language Models","venue":null,"work_id":"7ce8c9e9-a2f4-4459-ba1c-cb4c944bb0a7","year":2024},"citing_paper":{"arxiv_id":"2605.23080","last_updated":"2026-06-01T07:17:20Z","snapshot_observed_at":"2026-08-06T20:39:36.338304Z","submitted_at":"2026-05-21T22:27:04Z","title":"The Attribution Contract: Feature Attribution for Generative Language Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-30T16:38:10.113987Z"},"links":{"cited_paper":"/paper/2402.00794","citing_paper":"/paper/2605.23080"},"observation_digest":"sha256:56ddee5b0a41c678dcaa16be511a81af78709e8f626fe6c10655d6deadd5121e","observation_id":"8d94ccad-82ae-4ecb-bab7-295ff4b78c42","resolution":{"observed_at":"2026-06-30T16:44:56.181431Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","version":2},"cited_work":{"arxiv_id":"2402.00794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.00794","snapshot_observed_at":"2026-07-01T16:25:50.066636Z","title":"ReAGent: A Model-Agnostic Feature Attribution Method for Generative Language Models","venue":null,"work_id":"7ce8c9e9-a2f4-4459-ba1c-cb4c944bb0a7","year":2024},"citing_paper":{"arxiv_id":"2606.28615","last_updated":"2026-06-26T21:14:56Z","snapshot_observed_at":"2026-08-04T19:40:32.344244Z","submitted_at":"2026-06-26T21:14:56Z","title":"What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-06-30T00:38:21.949283Z"},"links":{"cited_paper":"/paper/2402.00794","citing_paper":"/paper/2606.28615"},"observation_digest":"sha256:dd1fb5fdf23e31d242920046df6858258003bccc2468dc0a4634679a009a4906","observation_id":"67a01bb0-d32d-40da-b9c9-6b3ee538ee6c","resolution":{"observed_at":"2026-07-01T16:25:50.068166Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.00794/citation-record","integrity":"/paper/2402.00794/integrity","json":"/paper/2402.00794/citation-record.json","paper":"/paper/2402.00794"},"outbound":[],"paper":{"arxiv_id":"2402.00794","last_updated":"2024-02-07T21:01:16Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:23:51.547578Z","submitted_at":"2024-02-01T17:25:51Z","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2402.00794."}