{"as_of":"2026-08-11T18:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:adb4c030ad35721568d9c43918631d2a7f2edb8d7bb0b1e69d702be9689358a9","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":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":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T12:42:58.431814Z","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":"2026-05-21T13:14:10.954861Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.13538","last_updated":"2025-03-15T20:53:46Z","snapshot_observed_at":"2026-08-07T17:01:30.481150Z","submitted_at":"2025-03-15T20:53:46Z","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13538","snapshot_observed_at":"2026-08-04T12:42:58.431814Z","title":"From demonstrations to rewards: Alignment without explicit human preferences","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.03013","last_updated":"2026-05-27T19:46:08Z","snapshot_observed_at":"2026-08-10T10:26:21.494267Z","submitted_at":"2025-10-03T13:58:09Z","title":"Distributional Inverse Reinforcement Learning","version":4},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-04T12:42:58.431814Z"},"links":{"cited_paper":"/paper/2503.13538","citing_paper":"/paper/2510.03013"},"observation_digest":"sha256:d328f879650c577773cf6eb7b689df58bca9b366aa7fc7862f39e42e7b4e5fd0","observation_id":"d71cef4b-e355-4f82-8641-1f296cff776e","resolution":{"observed_at":"2026-08-04T12:42:58.431814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13538","last_updated":"2025-03-15T20:53:46Z","snapshot_observed_at":"2026-08-07T17:01:30.481150Z","submitted_at":"2025-03-15T20:53:46Z","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","version":1},"cited_work":{"arxiv_id":"2503.13538","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.13538","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"From demonstrations to rewards: Align- ment without explicit human preferences.arXiv preprint arXiv:2503.13538","venue":null,"work_id":"367976ad-f99e-493e-9688-39d250978bf4","year":null},"citing_paper":{"arxiv_id":"2602.07832","last_updated":"2026-07-03T17:35:46Z","snapshot_observed_at":"2026-08-03T03:33:41.469348Z","submitted_at":"2026-02-08T05:47:27Z","title":"rePIRL: Learn PRM with Inverse RL for LLM Reasoning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-21T13:13:13.293921Z"},"links":{"cited_paper":"/paper/2503.13538","citing_paper":"/paper/2602.07832"},"observation_digest":"sha256:384db717f00de7f58fbb9efc0b8dd02ada3a0e125981c29ff8dcab9dcc7bf7bc","observation_id":"766506e4-2d0a-41a8-a0ad-b03b44add646","resolution":{"observed_at":"2026-05-21T13:14:10.957045Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13538","last_updated":"2025-03-15T20:53:46Z","snapshot_observed_at":"2026-08-07T17:01:30.481150Z","submitted_at":"2025-03-15T20:53:46Z","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13538","snapshot_observed_at":"2026-08-03T03:33:46.469070Z","title":"From demonstrations to rewards: Align- ment without explicit human preferences.arXiv preprint arXiv:2503.13538,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.07832","last_updated":"2026-07-03T17:35:46Z","snapshot_observed_at":"2026-08-03T03:33:41.469348Z","submitted_at":"2026-02-08T05:47:27Z","title":"rePIRL: Learn PRM with Inverse RL for LLM Reasoning","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T03:33:46.469070Z"},"links":{"cited_paper":"/paper/2503.13538","citing_paper":"/paper/2602.07832"},"observation_digest":"sha256:f04112ce942d8c2f3d76eda02c866cf37cf54cc6e1e2723b17f1b469b1e404d0","observation_id":"4d6cdcb9-dfd1-4d73-9233-aad74e13a3b9","resolution":{"observed_at":"2026-08-03T03:33:46.469070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2503.13538/citation-record","integrity":"/paper/2503.13538/integrity","json":"/paper/2503.13538/citation-record.json","paper":"/paper/2503.13538"},"outbound":[],"paper":{"arxiv_id":"2503.13538","last_updated":"2025-03-15T20:53:46Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T17:01:30.481150Z","submitted_at":"2025-03-15T20:53:46Z","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.13538."}