{"as_of":"2026-08-22T02:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:29715a64e1539d8739561bf7683cdc75f63b825a2b2621b05a299c494d89f44e","coverage":[{"denominator":2,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T21:17:53.242182Z","state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T00:53:26.206601Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.25850","last_updated":"2026-05-25T13:42:37Z","snapshot_observed_at":"2026-08-17T03:53:46.092851Z","submitted_at":"2026-05-25T13:42:37Z","title":"TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.25850","snapshot_observed_at":"2026-08-04T00:53:26.206601Z","title":"2605.25850 , archivePrefix =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00301","last_updated":"2026-07-31T21:31:07Z","snapshot_observed_at":"2026-08-14T19:42:48.000510Z","submitted_at":"2026-07-31T21:31:07Z","title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T00:53:26.206601Z"},"links":{"cited_paper":"/paper/2605.25850","citing_paper":"/paper/2608.00301"},"observation_digest":"sha256:ab59f4e6b0765ed70002bef202849a84e6209bee47e87285c61cd6cca56f9d8c","observation_id":"1d0ec2be-5923-4e84-8d32-c4160d977077","resolution":{"observed_at":"2026-08-04T00:53:26.206601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.25850/citation-record","integrity":"/paper/2605.25850/integrity","json":"/paper/2605.25850/citation-record.json","paper":"/paper/2605.25850"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2510.01152","last_updated":"2026-04-13T17:08:57Z","snapshot_observed_at":"2026-08-17T03:52:53.258214Z","submitted_at":"2025-10-01T17:41:54Z","title":"MASH: Modeling Abstention via Selective Help-Seeking","version":2},"cited_work":{"arxiv_id":"2510.01152","doi":null,"metadata_source":"pith","pith_arxiv_id":"2510.01152","snapshot_observed_at":"2026-06-29T21:23:59.201517Z","title":"MASH: Modeling Abstention via Selective Help-Seeking","venue":"cs.CL","work_id":"a951971c-a838-46ec-a500-dbfa5cbda8d2","year":2025},"citing_paper":{"arxiv_id":"2605.25850","last_updated":"2026-05-25T13:42:37Z","snapshot_observed_at":"2026-08-17T03:53:46.092851Z","submitted_at":"2026-05-25T13:42:37Z","title":"TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T21:17:53.242182Z"},"links":{"cited_paper":"/paper/2510.01152","citing_paper":"/paper/2605.25850"},"observation_digest":"sha256:381fed5ac23ffbad9be9be8446a012da58aa0c83ff7a08499ff58ab97a14a81c","observation_id":"5edcd46b-0dd3-4228-b3f0-3868542a2c12","resolution":{"observed_at":"2026-06-29T21:23:59.202807Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18290","last_updated":"2024-07-29T22:26:36Z","snapshot_observed_at":"2026-08-01T16:34:38.795326Z","submitted_at":"2023-05-29T17:57:46Z","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","version":3},"cited_work":{"arxiv_id":"2305.18290","doi":"10.48550/arxiv.2305.18290","metadata_source":"pith","pith_arxiv_id":"2305.18290","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","venue":"cs.LG","work_id":"62105b61-411f-46e5-970a-bd322c6adbbc","year":2023},"citing_paper":{"arxiv_id":"2605.25850","last_updated":"2026-05-25T13:42:37Z","snapshot_observed_at":"2026-08-17T03:53:46.092851Z","submitted_at":"2026-05-25T13:42:37Z","title":"TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T21:17:53.242182Z"},"links":{"cited_paper":"/paper/2305.18290","citing_paper":"/paper/2605.25850"},"observation_digest":"sha256:6d8a34b2f58b4a47d96cd5292548212da67a6082acec87c8e3eea37b84dcd97f","observation_id":"12066919-c45a-4d6f-bd89-9ae10a0009c6","resolution":{"observed_at":"2026-06-29T21:23:59.199943Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-07T21:08:26.462363+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-07T21:08:26.462363+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.25850","last_updated":"2026-05-25T13:42:37Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-17T03:53:46.092851Z","submitted_at":"2026-05-25T13:42:37Z","title":"TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning"},"reference_resolution":{"displayed":2,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":2},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 2 of 2 outbound references and 1 inbound Pith citation observation for arXiv:2605.25850."}