{"as_of":"2026-08-09T13:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aeb9af942528e0f8ac21f9c5105ed079c137e9d71e18cc0ec170884b50806bf7","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T20:04:17.744876Z","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":"2026-07-02T20:57:23.060366Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.12017","last_updated":"2024-03-18T17:52:57Z","snapshot_observed_at":"2026-07-06T17:46:29.153377Z","submitted_at":"2024-03-18T17:52:57Z","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2403.12017","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.12017","snapshot_observed_at":"2026-07-02T20:57:23.060366Z","title":"arXiv preprint arXiv:2403.12017 , year=","venue":null,"work_id":"de3e9f02-ec63-49aa-8e04-0040a6ef63a2","year":2024},"citing_paper":{"arxiv_id":"2604.16995","last_updated":"2026-04-18T13:49:47Z","snapshot_observed_at":"2026-07-06T23:04:10.324443Z","submitted_at":"2026-04-18T13:49:47Z","title":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-10T06:57:03.100519Z"},"links":{"cited_paper":"/paper/2403.12017","citing_paper":"/paper/2604.16995"},"observation_digest":"sha256:fd654be26e69d371a1fc5a7bdc93ed1dc316d489972209d330864059dc699503","observation_id":"4c8f68e1-facc-4105-b947-2b61dfe24128","resolution":{"observed_at":"2026-05-10T07:01:49.443854Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12017","last_updated":"2024-03-18T17:52:57Z","snapshot_observed_at":"2026-07-06T17:46:29.153377Z","submitted_at":"2024-03-18T17:52:57Z","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2403.12017","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.12017","snapshot_observed_at":"2026-07-02T20:57:23.060366Z","title":"arXiv preprint arXiv:2403.12017 , year=","venue":null,"work_id":"de3e9f02-ec63-49aa-8e04-0040a6ef63a2","year":2024},"citing_paper":{"arxiv_id":"2606.08044","last_updated":"2026-08-04T12:50:00Z","snapshot_observed_at":"2026-08-07T23:11:38.433528Z","submitted_at":"2026-06-06T08:10:56Z","title":"When Behavioral Safety Evaluation Fails: A Representation-Level Perspective","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-06-27T20:04:17.744876Z"},"links":{"cited_paper":"/paper/2403.12017","citing_paper":"/paper/2606.08044"},"observation_digest":"sha256:b99bd6707448143fd9b84e3e136684fc15204e434889751a8b2d35c2e2cb08ac","observation_id":"739c97dd-5595-4134-ab9b-c337244e93d8","resolution":{"observed_at":"2026-07-02T20:57:23.061669Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.12017/citation-record","integrity":"/paper/2403.12017/integrity","json":"/paper/2403.12017/citation-record.json","paper":"/paper/2403.12017"},"outbound":[],"paper":{"arxiv_id":"2403.12017","last_updated":"2024-03-18T17:52:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:46:29.153377Z","submitted_at":"2024-03-18T17:52:57Z","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.12017."}