{"as_of":"2026-08-05T21:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c8a1ed3509bcd98c30f1093faf7e09d55794ee9e1bd2e34f283d7f1ee2eaea38","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T02:28:23.754561Z","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":"2026-05-22T02:30:56.326201Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1702.08892","last_updated":"2017-11-22T23:11:20Z","snapshot_observed_at":"2026-07-06T05:31:46.512758Z","submitted_at":"2017-02-28T18:06:15Z","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1702.08892","doi":null,"metadata_source":"pith","pith_arxiv_id":"1702.08892","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","venue":"cs.AI","work_id":"08cd1a1b-71d7-4c9e-b600-b5671241efcb","year":2017},"citing_paper":{"arxiv_id":"2505.17352","last_updated":"2026-05-15T19:17:17Z","snapshot_observed_at":"2026-07-06T21:28:57.440918Z","submitted_at":"2025-05-23T00:08:49Z","title":"Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-22T02:28:23.754561Z"},"links":{"cited_paper":"/paper/1702.08892","citing_paper":"/paper/2505.17352"},"observation_digest":"sha256:bbd9a48c4fa78748155eb9e47cf567bda61dbd857a1da813787cd46837c76064","observation_id":"d5db5781-1027-45b3-899a-f9d3c574c32a","resolution":{"observed_at":"2026-05-22T02:30:56.329274Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08892","last_updated":"2017-11-22T23:11:20Z","snapshot_observed_at":"2026-07-06T05:31:46.512758Z","submitted_at":"2017-02-28T18:06:15Z","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1702.08892","doi":null,"metadata_source":"pith","pith_arxiv_id":"1702.08892","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","venue":"cs.AI","work_id":"08cd1a1b-71d7-4c9e-b600-b5671241efcb","year":2017},"citing_paper":{"arxiv_id":"2604.08944","last_updated":"2026-05-12T19:48:32Z","snapshot_observed_at":"2026-07-06T22:57:55.179136Z","submitted_at":"2026-04-10T04:23:29Z","title":"Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T16:38:20.312171Z"},"links":{"cited_paper":"/paper/1702.08892","citing_paper":"/paper/2604.08944"},"observation_digest":"sha256:aa4e929c1849b84538f8c01942721f0907b37aac5607ab85000c488dcc708fa4","observation_id":"f43b9f72-9e91-411e-8b84-31696cbabb5b","resolution":{"observed_at":"2026-05-11T08:26:01.242370Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08892","last_updated":"2017-11-22T23:11:20Z","snapshot_observed_at":"2026-07-06T05:31:46.512758Z","submitted_at":"2017-02-28T18:06:15Z","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"1702.08892","doi":null,"metadata_source":"pith","pith_arxiv_id":"1702.08892","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","venue":"cs.AI","work_id":"08cd1a1b-71d7-4c9e-b600-b5671241efcb","year":2017},"citing_paper":{"arxiv_id":"2604.08944","last_updated":"2026-05-12T19:48:32Z","snapshot_observed_at":"2026-07-06T22:57:55.179136Z","submitted_at":"2026-04-10T04:23:29Z","title":"Multi-Agent Decision-Focused Learning via Value-Aware Sequential Communication","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-14T22:07:23.115435Z"},"links":{"cited_paper":"/paper/1702.08892","citing_paper":"/paper/2604.08944"},"observation_digest":"sha256:03689b4e5500a172e65e15ea061a48872aa6f36ed2f696660ee315fb3f5e0f89","observation_id":"4b2ded50-9b5b-4866-b743-7bc3be887470","resolution":{"observed_at":"2026-05-14T22:08:04.152244Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1702.08892/citation-record","integrity":"/paper/1702.08892/integrity","json":"/paper/1702.08892/citation-record.json","paper":"/paper/1702.08892"},"outbound":[],"paper":{"arxiv_id":"1702.08892","last_updated":"2017-11-22T23:11:20Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-07-06T05:31:46.512758Z","submitted_at":"2017-02-28T18:06:15Z","title":"Bridging the Gap Between Value and Policy 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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1702.08892."}