{"as_of":"2026-08-22T18:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:819e7a24925f10159f4bceafbc443b0aba4aac4c3b1e445d991675e46496dfb9","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":"2026-08-22T06:32:14.747728+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":"2026-08-15T17:37:34.388699Z","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":"2026-05-19T01:06:57.329776Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2001.09293","last_updated":"2020-01-25T10:51:42Z","snapshot_observed_at":"2026-08-22T06:29:26.755552Z","submitted_at":"2020-01-25T10:51:42Z","title":"Learning Non-Markovian Reward Models in MDPs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.09293","snapshot_observed_at":"2026-08-06T21:45:13.232447Z","title":"Learning non-markovian reward models in mdps","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.24026","last_updated":"2025-06-30T16:32:31Z","snapshot_observed_at":"2026-08-09T06:00:57.787361Z","submitted_at":"2025-06-30T16:32:31Z","title":"Constructing Non-Markovian Decision Process via History Aggregator","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T21:45:13.232447Z"},"links":{"cited_paper":"/paper/2001.09293","citing_paper":"/paper/2506.24026"},"observation_digest":"sha256:2f4f754bbf572c52162c254f3255fae05eaa9999d46507130839cc33e2ce0d04","observation_id":"93124684-39be-43f0-a505-9e378793009e","resolution":{"observed_at":"2026-08-06T21:45:13.232447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.09293","last_updated":"2020-01-25T10:51:42Z","snapshot_observed_at":"2026-08-22T06:29:26.755552Z","submitted_at":"2020-01-25T10:51:42Z","title":"Learning Non-Markovian Reward Models in MDPs","version":1},"cited_work":{"arxiv_id":"2001.09293","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2001.09293","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"InInternational Conference on Machine Learning, 5156–5165","venue":null,"work_id":"e96a3b35-36b6-4036-ab9f-ba45ef471f90","year":2020},"citing_paper":{"arxiv_id":"2508.04282","last_updated":"2026-04-14T17:18:39Z","snapshot_observed_at":"2026-07-06T22:08:40.965707Z","submitted_at":"2025-08-06T10:13:17Z","title":"Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-19T01:06:07.789346Z"},"links":{"cited_paper":"/paper/2001.09293","citing_paper":"/paper/2508.04282"},"observation_digest":"sha256:f96b4fc2b517d22f866802fa11f1777105fe08555b67a4a7c3e089ef8fef4430","observation_id":"bb400c18-1696-4b34-a215-7b75a0d2ed32","resolution":{"observed_at":"2026-05-19T01:06:57.334946Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.09293","last_updated":"2020-01-25T10:51:42Z","snapshot_observed_at":"2026-08-22T06:29:26.755552Z","submitted_at":"2020-01-25T10:51:42Z","title":"Learning Non-Markovian Reward Models in MDPs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.09293","snapshot_observed_at":"2026-08-15T17:37:34.388699Z","title":"Learning non-Markovian reward models in MDPs","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2508.14093","last_updated":"2025-08-14T18:46:54Z","snapshot_observed_at":"2026-08-21T18:59:44.752424Z","submitted_at":"2025-08-14T18:46:54Z","title":"Physics-Informed Reward Machines","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T17:37:34.388699Z"},"links":{"cited_paper":"/paper/2001.09293","citing_paper":"/paper/2508.14093"},"observation_digest":"sha256:647c4aa3cfa0b21bef9eb273cacaa8c5f99a4e63118801d0cca3543e702b9458","observation_id":"6148e142-cc46-4273-b43c-dc9cb513a1cc","resolution":{"observed_at":"2026-08-15T17:37:34.388699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2001.09293/citation-record","integrity":"/paper/2001.09293/integrity","json":"/paper/2001.09293/citation-record.json","paper":"/paper/2001.09293"},"outbound":[],"paper":{"arxiv_id":"2001.09293","last_updated":"2020-01-25T10:51:42Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-22T06:29:26.755552Z","submitted_at":"2020-01-25T10:51:42Z","title":"Learning Non-Markovian Reward Models in MDPs"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2001.09293."}