{"as_of":"2026-08-21T19:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0b9b85ec9b5d0b2c5d61b879a5eb51ba67366e773bbc7e9cd05da2956f16d7da","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":"2026-08-21T06:32:19.484+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":"2026-06-25T23:35:03.577967Z","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":"2026-07-04T17:40:00.112551Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.12904","last_updated":"2020-12-26T02:02:31Z","snapshot_observed_at":"2026-08-14T14:19:30.751926Z","submitted_at":"2020-07-25T10:37:15Z","title":"Weak Human Preference Supervision For Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2007.12904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.12904","snapshot_observed_at":"2026-07-04T17:40:00.112551Z","title":"Human preference scaling with demonstrations for deep reinforcement learning","venue":null,"work_id":"8ce436b6-8e8d-4cfe-a339-d28a9930b9c1","year":2007},"citing_paper":{"arxiv_id":"2411.00361","last_updated":"2026-04-15T18:16:21Z","snapshot_observed_at":"2026-08-14T02:13:13.429891Z","submitted_at":"2024-11-01T04:58:40Z","title":"Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-23T18:30:38.818711Z"},"links":{"cited_paper":"/paper/2007.12904","citing_paper":"/paper/2411.00361"},"observation_digest":"sha256:24db2f69fbcccf7f14a2a12e4208dcb14543bd9de0eac926873f839cf74d6fc2","observation_id":"cb4e0346-dc79-40dd-9c63-4d0d24c39a9d","resolution":{"observed_at":"2026-05-23T18:33:19.643187Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.12904","last_updated":"2020-12-26T02:02:31Z","snapshot_observed_at":"2026-08-14T14:19:30.751926Z","submitted_at":"2020-07-25T10:37:15Z","title":"Weak Human Preference Supervision For Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2007.12904","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.12904","snapshot_observed_at":"2026-07-04T17:40:00.112551Z","title":"Human preference scaling with demonstrations for deep reinforcement learning","venue":null,"work_id":"8ce436b6-8e8d-4cfe-a339-d28a9930b9c1","year":2007},"citing_paper":{"arxiv_id":"2606.24622","last_updated":"2026-06-23T14:20:42Z","snapshot_observed_at":"2026-08-15T16:24:39.357617Z","submitted_at":"2026-06-23T14:20:42Z","title":"Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-25T23:35:03.577967Z"},"links":{"cited_paper":"/paper/2007.12904","citing_paper":"/paper/2606.24622"},"observation_digest":"sha256:2e1c58713b92312e2d2fd7d32fac7b465d82b245b9c4abbdc46df8d2c79d5026","observation_id":"efd56d09-8f33-48f8-8e89-583583adf205","resolution":{"observed_at":"2026-07-04T17:40:00.113955Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2007.12904/citation-record","integrity":"/paper/2007.12904/integrity","json":"/paper/2007.12904/citation-record.json","paper":"/paper/2007.12904"},"outbound":[],"paper":{"arxiv_id":"2007.12904","last_updated":"2020-12-26T02:02:31Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-14T14:19:30.751926Z","submitted_at":"2020-07-25T10:37:15Z","title":"Weak Human Preference Supervision For Deep 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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2007.12904."}