{"as_of":"2026-08-08T05:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:06702183a7e59f9c3249c1f0bb63a71c05413751b9b1e9886c4c2300436fed5f","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T11:05:22.329232Z","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":"2026-08-07T11:05:22.533168Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1801.06176","last_updated":"2018-05-23T17:52:27Z","snapshot_observed_at":"2026-07-06T06:19:16.799773Z","submitted_at":"2018-01-18T18:57:33Z","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","version":3},"cited_work":{"arxiv_id":"1801.06176","doi":null,"metadata_source":"pith","pith_arxiv_id":"1801.06176","snapshot_observed_at":"2026-08-07T11:05:22.533168Z","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","venue":"cs.CL","work_id":"7cc685d1-890e-49ae-b72a-ba73a0d2d300","year":2018},"citing_paper":{"arxiv_id":"2506.03519","last_updated":"2025-06-05T06:09:38Z","snapshot_observed_at":"2026-08-07T10:58:43.727280Z","submitted_at":"2025-06-04T03:07:55Z","title":"An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T11:05:22.329232Z"},"links":{"cited_paper":"/paper/1801.06176","citing_paper":"/paper/2506.03519"},"observation_digest":"sha256:ab6c9ac92a557f766a68e92ff05c102f12f731838ee0676b489fdd445897f38a","observation_id":"ba326a11-4c43-4765-8043-fe43be17f6ea","resolution":{"observed_at":"2026-08-07T11:05:22.540401Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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":"1801.06176","last_updated":"2018-05-23T17:52:27Z","snapshot_observed_at":"2026-07-06T06:19:16.799773Z","submitted_at":"2018-01-18T18:57:33Z","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06176","snapshot_observed_at":"2026-08-05T15:38:49.949007Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2508.19689","last_updated":"2025-08-27T08:52:47Z","snapshot_observed_at":"2026-08-07T07:48:25.655053Z","submitted_at":"2025-08-27T08:52:47Z","title":"Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality","version":1},"reference_index":124,"source":"arxiv_source","source_observed_at":"2026-08-05T15:38:49.949007Z"},"links":{"cited_paper":"/paper/1801.06176","citing_paper":"/paper/2508.19689"},"observation_digest":"sha256:2884d7c1b741e7d421ab02e267d20f8621fcdfd654108da4c367b285a0c97268","observation_id":"9b747b86-1930-4f19-b8b1-4c49bb3fb30c","resolution":{"observed_at":"2026-08-05T15:38:49.949007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1801.06176/citation-record","integrity":"/paper/1801.06176/integrity","json":"/paper/1801.06176/citation-record.json","paper":"/paper/1801.06176"},"outbound":[],"paper":{"arxiv_id":"1801.06176","last_updated":"2018-05-23T17:52:27Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T06:19:16.799773Z","submitted_at":"2018-01-18T18:57:33Z","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:1801.06176."}