{"as_of":"2026-08-07T14:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f1dea7c7d4d99186eb0a8033bc47acb7fd06cefb13c9483b55d94ee50a455979","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T14:31:35.087409Z","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":"2026-05-20T23:29:13.193347Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1704.07978","last_updated":"2018-05-24T14:13:20Z","snapshot_observed_at":"2026-07-06T05:39:20.517167Z","submitted_at":"2017-04-26T05:55:07Z","title":"On Improving Deep Reinforcement Learning for POMDPs","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.07978","snapshot_observed_at":"2026-08-05T14:31:35.087409Z","title":"On improving deep reinforcement learning for POMDPs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.21314","last_updated":"2025-09-02T23:21:19Z","snapshot_observed_at":"2026-08-05T14:31:33.919260Z","submitted_at":"2025-08-29T02:45:28Z","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T14:31:35.087409Z"},"links":{"cited_paper":"/paper/1704.07978","citing_paper":"/paper/2508.21314"},"observation_digest":"sha256:a23d97f6a48bf59111212ce67c81ce4787ecb81b8d95d521445e6722a896e2d6","observation_id":"df196e73-64fd-43da-aa25-4a7373d4756a","resolution":{"observed_at":"2026-08-05T14:31:35.087409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.07978","last_updated":"2018-05-24T14:13:20Z","snapshot_observed_at":"2026-07-06T05:39:20.517167Z","submitted_at":"2017-04-26T05:55:07Z","title":"On Improving Deep Reinforcement Learning for POMDPs","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.07978","snapshot_observed_at":"2026-08-04T13:43:29.684346Z","title":"On improving deep reinforcement learning for PODMPs.arXiv preprint arXiv:1704.07978, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.26000","last_updated":"2026-06-09T14:29:52Z","snapshot_observed_at":"2026-08-07T06:12:53.159640Z","submitted_at":"2025-09-30T09:32:20Z","title":"Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T13:43:29.684346Z"},"links":{"cited_paper":"/paper/1704.07978","citing_paper":"/paper/2509.26000"},"observation_digest":"sha256:2f6cefdb7d019d051ac6c3f2cc11c8d24c7e476adb4801869e901c2d21f1c0ed","observation_id":"4473a43d-2153-4e3b-acc8-4ff7754032d2","resolution":{"observed_at":"2026-08-04T13:43:29.684346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.07978","last_updated":"2018-05-24T14:13:20Z","snapshot_observed_at":"2026-07-06T05:39:20.517167Z","submitted_at":"2017-04-26T05:55:07Z","title":"On Improving Deep Reinforcement Learning for POMDPs","version":6},"cited_work":{"arxiv_id":"1704.07978","doi":null,"metadata_source":"pith","pith_arxiv_id":"1704.07978","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On Improving Deep Reinforcement Learning for POMDPs","venue":"cs.LG","work_id":"ef30aea3-63ea-4938-b0c8-72fe8945eeec","year":2017},"citing_paper":{"arxiv_id":"2605.16318","last_updated":"2026-05-04T22:18:05Z","snapshot_observed_at":"2026-07-06T23:27:29.931962Z","submitted_at":"2026-05-04T22:18:05Z","title":"Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-20T23:26:23.989545Z"},"links":{"cited_paper":"/paper/1704.07978","citing_paper":"/paper/2605.16318"},"observation_digest":"sha256:fcdeeb1363c562401fcfdaa64fb260820a6a1d52618e72ecb3f8a442ef12385b","observation_id":"20b36415-69e6-4bcf-a3b1-1be34dc60d37","resolution":{"observed_at":"2026-05-20T23:29:13.197038Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.07978","last_updated":"2018-05-24T14:13:20Z","snapshot_observed_at":"2026-07-06T05:39:20.517167Z","submitted_at":"2017-04-26T05:55:07Z","title":"On Improving Deep Reinforcement Learning for POMDPs","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.07978","snapshot_observed_at":"2026-08-01T16:57:46.204861Z","title":"On Improving Deep Reinforcement Learning for POMDPs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.17838","last_updated":"2026-07-20T11:29:26Z","snapshot_observed_at":"2026-08-02T19:25:17.976181Z","submitted_at":"2026-07-20T11:29:26Z","title":"Deep Recurrent Q-Learning Based Beam Steering Strategy for Throughput Maximization in WPCNs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T16:57:46.204861Z"},"links":{"cited_paper":"/paper/1704.07978","citing_paper":"/paper/2607.17838"},"observation_digest":"sha256:1eb0fa498237e03e03b47d7def7406954cd7e9a5f84e901f7826cf80b52253d2","observation_id":"1e5e39d1-e1e7-474e-9e3b-55eee1360ad1","resolution":{"observed_at":"2026-08-01T16:57:46.204861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1704.07978/citation-record","integrity":"/paper/1704.07978/integrity","json":"/paper/1704.07978/citation-record.json","paper":"/paper/1704.07978"},"outbound":[],"paper":{"arxiv_id":"1704.07978","last_updated":"2018-05-24T14:13:20Z","latest_version":6,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T05:39:20.517167Z","submitted_at":"2017-04-26T05:55:07Z","title":"On Improving Deep Reinforcement Learning for POMDPs"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1704.07978."}