{"as_of":"2026-08-15T18:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f52086c482368faaa207c59ab6d94e083ea21c735376f173ce3776d0b1f93f10","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":"2026-08-15T06:32:42.880941+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":"2026-08-07T11:20:13.676261Z","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":"2026-06-30T14:44:45.880321Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.03282","last_updated":"2024-11-09T07:09:00Z","snapshot_observed_at":"2026-08-13T04:25:49.973792Z","submitted_at":"2024-02-05T18:38:55Z","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03282","snapshot_observed_at":"2026-08-07T11:20:13.676261Z","title":"A framework for partially observed reward-states in rlhf","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03066","last_updated":"2026-07-17T19:03:49Z","snapshot_observed_at":"2026-08-12T23:06:28.677740Z","submitted_at":"2025-06-03T16:42:39Z","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T11:20:13.676261Z"},"links":{"cited_paper":"/paper/2402.03282","citing_paper":"/paper/2506.03066"},"observation_digest":"sha256:4363fbb8708795da9d3b72997216277ac1d7909f2b284b9ccc3a73fb3c53887e","observation_id":"5e79b9c9-f0f6-461b-8c8b-9946d45997bc","resolution":{"observed_at":"2026-08-07T11:20:13.676261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03282","last_updated":"2024-11-09T07:09:00Z","snapshot_observed_at":"2026-08-13T04:25:49.973792Z","submitted_at":"2024-02-05T18:38:55Z","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF","version":3},"cited_work":{"arxiv_id":"2402.03282","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.03282","snapshot_observed_at":"2026-06-30T14:44:45.880321Z","title":"URLhttps: //openreview.net/forum?id=f7OkIurx4b","venue":null,"work_id":"1e346ba9-e6e6-4d1f-a252-187458cd91dc","year":null},"citing_paper":{"arxiv_id":"2606.30271","last_updated":"2026-06-29T13:18:42Z","snapshot_observed_at":"2026-08-15T13:43:59.904517Z","submitted_at":"2026-06-29T13:18:42Z","title":"Preference-Based Reward Learning under Partial Observability with Inexact Dynamics","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-30T05:19:16.647402Z"},"links":{"cited_paper":"/paper/2402.03282","citing_paper":"/paper/2606.30271"},"observation_digest":"sha256:eaf509c5318714b639ae2fa4c70fced2e4743f8f7e71d9d5e1e0af50dbbd6dcc","observation_id":"7841ec4e-05ba-4aa7-8039-5e7d7216917c","resolution":{"observed_at":"2026-06-30T14:44:45.882140Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.03282/citation-record","integrity":"/paper/2402.03282/integrity","json":"/paper/2402.03282/citation-record.json","paper":"/paper/2402.03282"},"outbound":[],"paper":{"arxiv_id":"2402.03282","last_updated":"2024-11-09T07:09:00Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T04:25:49.973792Z","submitted_at":"2024-02-05T18:38:55Z","title":"A Theoretical Framework for Partially Observed Reward-States in RLHF"},"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 2 inbound Pith citation observations for arXiv:2402.03282."}