{"as_of":"2026-08-09T09:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ef6335317543d0e5ddadfe1cf7b9091076274ddc22bba92cdcc69e5a1dce02f","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":"2026-08-09T06:31:02.800959+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":"2026-08-05T15:38:53.313821Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1605.07669","last_updated":"2016-06-02T14:01:07Z","snapshot_observed_at":"2026-07-06T04:57:29.584519Z","submitted_at":"2016-05-24T21:56:08Z","title":"On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07669","snapshot_observed_at":"2026-08-05T15:38:53.313821Z","title":null,"venue":null,"work_id":null,"year":2016},"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":158,"source":"arxiv_source","source_observed_at":"2026-08-05T15:38:53.313821Z"},"links":{"cited_paper":"/paper/1605.07669","citing_paper":"/paper/2508.19689"},"observation_digest":"sha256:d178f1e8d80e0456e924a158da4445fa03b95efeb927775c026bccf264d4bf4c","observation_id":"23f438e9-0c0c-45e8-8279-62ea4aab80f1","resolution":{"observed_at":"2026-08-05T15:38:53.313821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07669","last_updated":"2016-06-02T14:01:07Z","snapshot_observed_at":"2026-07-06T04:57:29.584519Z","submitted_at":"2016-05-24T21:56:08Z","title":"On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07669","snapshot_observed_at":"2026-07-13T03:47:31.338781Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.09338","last_updated":"2026-07-10T12:19:59Z","snapshot_observed_at":"2026-08-08T01:50:21.350924Z","submitted_at":"2026-07-10T12:19:59Z","title":"Towards Detecting Inconsistencies in End-to-end Generated TODs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-13T03:47:31.338781Z"},"links":{"cited_paper":"/paper/1605.07669","citing_paper":"/paper/2607.09338"},"observation_digest":"sha256:181e53ee4fa5ec4044bd8fb6dd2fe7b1126b95291ee8591fd80bbc034704318b","observation_id":"bec58ce9-5ef7-4de3-bdc3-989e46a9b7e5","resolution":{"observed_at":"2026-07-13T03:47:31.338781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1605.07669/citation-record","integrity":"/paper/1605.07669/integrity","json":"/paper/1605.07669/citation-record.json","paper":"/paper/1605.07669"},"outbound":[],"paper":{"arxiv_id":"1605.07669","last_updated":"2016-06-02T14:01:07Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T04:57:29.584519Z","submitted_at":"2016-05-24T21:56:08Z","title":"On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1605.07669."}