{"as_of":"2026-08-12T03:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:854650683b512aaedfba8bbac215f817f13ccc397b739a7be31f120564f0747e","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":"2026-08-11T06:34:44.6726+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":"2026-08-11T00:18:20.260798Z","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":"2026-08-07T10:36:01.256639Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.11089","last_updated":"2020-02-25T18:36:31Z","snapshot_observed_at":"2026-08-08T12:29:54.109813Z","submitted_at":"2020-02-25T18:36:31Z","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.11089","snapshot_observed_at":"2026-08-11T00:18:20.260798Z","title":", Geng, X","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.19562","last_updated":"2024-12-27T10:05:45Z","snapshot_observed_at":"2026-08-11T00:35:32.156162Z","submitted_at":"2024-12-27T10:05:45Z","title":"Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T00:18:20.260798Z"},"links":{"cited_paper":"/paper/2002.11089","citing_paper":"/paper/2412.19562"},"observation_digest":"sha256:9f1e880bec06e28c2eec28291953372fa9cc5c1b0bd554b198dcd676aa641667","observation_id":"a336cc56-5004-46b3-a6a0-0567b1267131","resolution":{"observed_at":"2026-08-11T00:18:20.260798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.11089","last_updated":"2020-02-25T18:36:31Z","snapshot_observed_at":"2026-08-08T12:29:54.109813Z","submitted_at":"2020-02-25T18:36:31Z","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","version":1},"cited_work":{"arxiv_id":"2002.11089","doi":null,"metadata_source":"pith","pith_arxiv_id":"2002.11089","snapshot_observed_at":"2026-08-07T10:36:01.256639Z","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","venue":"cs.LG","work_id":"e08817fa-7463-4791-959b-ed99a29b6256","year":2020},"citing_paper":{"arxiv_id":"2506.05445","last_updated":"2025-06-05T13:52:38Z","snapshot_observed_at":"2026-08-07T10:24:36.469912Z","submitted_at":"2025-06-05T13:52:38Z","title":"Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T10:35:57.781252Z"},"links":{"cited_paper":"/paper/2002.11089","citing_paper":"/paper/2506.05445"},"observation_digest":"sha256:a856a3b4caf1f9b8157258c8fbafe5c8b2c194c891bcec75c7ffb9f522b9c810","observation_id":"254e7504-a210-4e33-9413-903c850d747a","resolution":{"observed_at":"2026-08-07T10:36:01.307595Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2002.11089/citation-record","integrity":"/paper/2002.11089/integrity","json":"/paper/2002.11089/citation-record.json","paper":"/paper/2002.11089"},"outbound":[],"paper":{"arxiv_id":"2002.11089","last_updated":"2020-02-25T18:36:31Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T12:29:54.109813Z","submitted_at":"2020-02-25T18:36:31Z","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2002.11089."}