{"as_of":"2026-08-16T14:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f76a33d057697bfdc94bf254f0e3261d6daa466b7ab55e7011fe55365672ad4","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":"2026-08-16T06:30:59.297886+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":"2026-08-14T15:30:29.318381Z","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":"2026-05-24T18:24:48.386780Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1709.03969","last_updated":"2021-06-22T20:27:31Z","snapshot_observed_at":"2026-08-16T13:54:53.618678Z","submitted_at":"2017-09-12T17:42:21Z","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds","version":2},"cited_work":{"arxiv_id":"1709.03969","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1709.03969","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Explore, exploit or listen: Combining human feed- back and policy model to speed up deep reinforcement learning in 3d worlds","venue":null,"work_id":"8ee58dab-756d-4b0b-9d52-02ba02f4c4ae","year":2017},"citing_paper":{"arxiv_id":"1907.09273","last_updated":"2019-07-25T21:52:08Z","snapshot_observed_at":"2026-08-15T14:09:06.662435Z","submitted_at":"2019-07-22T12:32:15Z","title":"Why Build an Assistant in Minecraft?","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-24T18:20:58.081505Z"},"links":{"cited_paper":"/paper/1709.03969","citing_paper":"/paper/1907.09273"},"observation_digest":"sha256:eb1cbc7b26fb419ff7fa36c1e384b1300e933332cbba53f9c272fbda9f4b30ba","observation_id":"37df2c17-0522-46f2-a4d4-3cbf9e01fe6c","resolution":{"observed_at":"2026-05-24T18:24:48.389793Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03969","last_updated":"2021-06-22T20:27:31Z","snapshot_observed_at":"2026-08-16T13:54:53.618678Z","submitted_at":"2017-09-12T17:42:21Z","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.03969","snapshot_observed_at":"2026-08-14T15:30:29.318381Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.01007","last_updated":"2019-08-02T18:36:44Z","snapshot_observed_at":"2026-08-15T09:52:28.849599Z","submitted_at":"2019-08-02T18:36:44Z","title":"Improving Deep Reinforcement Learning in Minecraft with Action Advice","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-14T15:30:29.318381Z"},"links":{"cited_paper":"/paper/1709.03969","citing_paper":"/paper/1908.01007"},"observation_digest":"sha256:af1acb2adf4590a3d4eeeb1ed3ad13109bffd1f1e55611fea9dd57408ed634f3","observation_id":"489a2b68-8b34-4570-98b6-7dcc973c62d5","resolution":{"observed_at":"2026-08-14T15:30:29.318381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03969","last_updated":"2021-06-22T20:27:31Z","snapshot_observed_at":"2026-08-16T13:54:53.618678Z","submitted_at":"2017-09-12T17:42:21Z","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.03969","snapshot_observed_at":"2026-08-12T18:15:15.720677Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.11761","last_updated":"2025-02-20T16:22:19Z","snapshot_observed_at":"2026-08-15T08:34:22.985905Z","submitted_at":"2024-11-18T17:40:42Z","title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","version":2},"reference_index":112,"source":"pdf_text","source_observed_at":"2026-08-12T18:15:15.720677Z"},"links":{"cited_paper":"/paper/1709.03969","citing_paper":"/paper/2411.11761"},"observation_digest":"sha256:9f781f8926503ad19ebedd858a82e56450493f8114da90f7c665e5dd674f4c6b","observation_id":"cf7e173d-bc97-4ad6-ba4b-caeb82844158","resolution":{"observed_at":"2026-08-12T18:15:15.720677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1709.03969/citation-record","integrity":"/paper/1709.03969/integrity","json":"/paper/1709.03969/citation-record.json","paper":"/paper/1709.03969"},"outbound":[],"paper":{"arxiv_id":"1709.03969","last_updated":"2021-06-22T20:27:31Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T13:54:53.618678Z","submitted_at":"2017-09-12T17:42:21Z","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:1709.03969."}