{"as_of":"2026-08-15T06:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bf6d40fd67b3b277998b09c8065faec129ff9b7f056f2e502a59922aa7b3e8e9","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-08-01T16:07:59.784850Z","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":"2510.01857","last_updated":"2026-05-17T10:57:36Z","snapshot_observed_at":"2026-08-12T17:54:37.690998Z","submitted_at":"2025-10-02T09:55:26Z","title":"Learning Reasoning Rewards from Expert Demonstrations with Inverse Reinforcement Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.01857","snapshot_observed_at":"2026-08-01T16:07:59.784850Z","title":"arXiv preprint arXiv:2510.01857 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18110","last_updated":"2026-07-20T16:08:49Z","snapshot_observed_at":"2026-08-13T22:38:23.734771Z","submitted_at":"2026-07-20T16:08:49Z","title":"LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-01T16:07:59.784850Z"},"links":{"cited_paper":"/paper/2510.01857","citing_paper":"/paper/2607.18110"},"observation_digest":"sha256:92c73b54e355e827e45ff8859512b2801b80a0da63bab0d66ca86c69d168c4d8","observation_id":"0d48c75f-1715-4ede-8dde-c8ec85a6198a","resolution":{"observed_at":"2026-08-01T16:07:59.784850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2510.01857/citation-record","integrity":"/paper/2510.01857/integrity","json":"/paper/2510.01857/citation-record.json","paper":"/paper/2510.01857"},"outbound":[],"paper":{"arxiv_id":"2510.01857","last_updated":"2026-05-17T10:57:36Z","latest_version":5,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-12T17:54:37.690998Z","submitted_at":"2025-10-02T09:55:26Z","title":"Learning Reasoning Rewards from Expert Demonstrations with 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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2510.01857."}