{"as_of":"2026-08-11T17:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d82e7de9df3b4927640b2465ef1bd97dab8452055f263d1f5b68138ed3e4c93","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":"2026-08-11T06:34:44.6726+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":"2026-08-07T22:44:50.676445Z","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":"2026-05-11T13:01:21.040353Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.12486","last_updated":"2025-05-28T09:03:41Z","snapshot_observed_at":"2026-08-07T18:10:23.136491Z","submitted_at":"2025-02-18T03:15:55Z","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","version":6},"cited_work":{"arxiv_id":"2502.12486","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.12486","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"dbf47ec4-ff7c-40a9-bd7d-b6db3c297430","year":null},"citing_paper":{"arxiv_id":"2604.18982","last_updated":"2026-04-21T02:08:25Z","snapshot_observed_at":"2026-07-06T23:05:44.499005Z","submitted_at":"2026-04-21T02:08:25Z","title":"SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T02:28:06.611688Z"},"links":{"cited_paper":"/paper/2502.12486","citing_paper":"/paper/2604.18982"},"observation_digest":"sha256:1521ecf53314642d67415dc2e7e41473c4b62e0be521837833525f9e17226e2f","observation_id":"72cd3638-cff6-4741-8ed9-5e56257d19ea","resolution":{"observed_at":"2026-05-11T13:01:21.086647Z","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":"2502.12486","last_updated":"2025-05-28T09:03:41Z","snapshot_observed_at":"2026-08-07T18:10:23.136491Z","submitted_at":"2025-02-18T03:15:55Z","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12486","snapshot_observed_at":"2026-08-07T22:44:50.676445Z","title":"arXiv preprint arXiv:2502.12486 , url=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.05832","last_updated":"2026-08-06T10:00:50Z","snapshot_observed_at":"2026-08-10T07:27:11.923510Z","submitted_at":"2026-08-06T10:00:50Z","title":"Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T22:44:50.676445Z"},"links":{"cited_paper":"/paper/2502.12486","citing_paper":"/paper/2608.05832"},"observation_digest":"sha256:91dd8aa042d228e285521855b1c489467ccda0d3263b231e283e9a232c841c0e","observation_id":"986a3fc7-fd5c-484f-b128-e60874405cea","resolution":{"observed_at":"2026-08-07T22:44:50.676445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.12486/citation-record","integrity":"/paper/2502.12486/integrity","json":"/paper/2502.12486/citation-record.json","paper":"/paper/2502.12486"},"outbound":[],"paper":{"arxiv_id":"2502.12486","last_updated":"2025-05-28T09:03:41Z","latest_version":6,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T18:10:23.136491Z","submitted_at":"2025-02-18T03:15:55Z","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via 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":"2026-08-11T06:34:44.6726+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 2 inbound Pith citation observations for arXiv:2502.12486."}