{"as_of":"2026-08-08T18:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9443f13903a71ab6c8c15d85e401d4e3f376cfbc5449d1924d43719a859a591a","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T12:12:59.815667Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T16:17:35.964523Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.12130","last_updated":"2025-05-13T14:30:16Z","snapshot_observed_at":"2026-07-06T19:04:22.495890Z","submitted_at":"2024-08-22T04:54:25Z","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12130","snapshot_observed_at":"2026-08-07T12:12:59.815667Z","title":"S-epoa: Overcoming the indistinguishability of segments with skill-driven preference-based reinforcement learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00388","last_updated":"2025-06-10T13:10:39Z","snapshot_observed_at":"2026-08-07T15:00:04.313363Z","submitted_at":"2025-05-31T04:37:07Z","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","version":3},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T12:12:59.815667Z"},"links":{"cited_paper":"/paper/2408.12130","citing_paper":"/paper/2506.00388"},"observation_digest":"sha256:6e46fba2da97cef9a34f22b3b81701af6603f796a20c623d7405b5fccde9665a","observation_id":"f89b50c1-8f96-4fc7-b1c9-87a7b865bfcf","resolution":{"observed_at":"2026-08-07T12:12:59.815667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12130","last_updated":"2025-05-13T14:30:16Z","snapshot_observed_at":"2026-07-06T19:04:22.495890Z","submitted_at":"2024-08-22T04:54:25Z","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2408.12130","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.12130","snapshot_observed_at":"2026-08-06T16:17:35.964523Z","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","venue":"cs.AI","work_id":"cc2fe6ba-1fea-46c1-bbe0-5c9e45abc4ce","year":2024},"citing_paper":{"arxiv_id":"2507.14066","last_updated":"2025-07-18T16:43:04Z","snapshot_observed_at":"2026-08-06T15:59:43.105055Z","submitted_at":"2025-07-18T16:43:04Z","title":"Preference-based Multi-Objective Reinforcement Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T16:17:35.749954Z"},"links":{"cited_paper":"/paper/2408.12130","citing_paper":"/paper/2507.14066"},"observation_digest":"sha256:4704114ee4761ac63a38ecddb45892f6d059cc33731402cb3996362c79abd985","observation_id":"86d955f6-956d-453c-b71f-bf247c652a92","resolution":{"observed_at":"2026-08-06T16:17:35.967349Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2408.12130/citation-record","integrity":"/paper/2408.12130/integrity","json":"/paper/2408.12130/citation-record.json","paper":"/paper/2408.12130"},"outbound":[],"paper":{"arxiv_id":"2408.12130","last_updated":"2025-05-13T14:30:16Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T19:04:22.495890Z","submitted_at":"2024-08-22T04:54:25Z","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based 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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2408.12130."}