{"as_of":"2026-08-12T21:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a1494da8ea55ded9931652415446054adbf913d564dd73d641d19b553e492838","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:28:44.869965Z","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":"2026-06-30T10:34:36.468758Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2002.04523","last_updated":"2021-04-19T03:02:59Z","snapshot_observed_at":"2026-07-06T08:56:30.534634Z","submitted_at":"2020-02-11T16:26:07Z","title":"Objective Mismatch in Model-based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.04523","snapshot_observed_at":"2026-08-11T20:28:44.869965Z","title":"Lambert, B","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.05766","last_updated":"2024-12-08T00:21:37Z","snapshot_observed_at":"2026-08-12T20:35:45.805046Z","submitted_at":"2024-12-08T00:21:37Z","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:44.869965Z"},"links":{"cited_paper":"/paper/2002.04523","citing_paper":"/paper/2412.05766"},"observation_digest":"sha256:c14ea8d0024c1e56189305d9104fcedb21ca5733d958671a8639a86282a198d8","observation_id":"e832b5b3-2826-4730-99f8-90621918d39e","resolution":{"observed_at":"2026-08-11T20:28:44.869965Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.04523","last_updated":"2021-04-19T03:02:59Z","snapshot_observed_at":"2026-07-06T08:56:30.534634Z","submitted_at":"2020-02-11T16:26:07Z","title":"Objective Mismatch in Model-based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.04523","snapshot_observed_at":"2026-08-11T19:42:10.295272Z","title":"arXiv preprint arXiv:2002.04523 (2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.06486","last_updated":"2024-12-09T13:35:46Z","snapshot_observed_at":"2026-08-12T01:44:20.130077Z","submitted_at":"2024-12-09T13:35:46Z","title":"SimuDICE: Offline Policy Optimization Through World Model Updates and DICE Estimation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T19:42:10.295272Z"},"links":{"cited_paper":"/paper/2002.04523","citing_paper":"/paper/2412.06486"},"observation_digest":"sha256:b37f71c862e4cc276330beb3d2e1ebe237707580f19c5f5134229969d75475c3","observation_id":"ca2da1fb-b1eb-40b7-8637-eaca30cb2d68","resolution":{"observed_at":"2026-08-11T19:42:10.295272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.04523","last_updated":"2021-04-19T03:02:59Z","snapshot_observed_at":"2026-07-06T08:56:30.534634Z","submitted_at":"2020-02-11T16:26:07Z","title":"Objective Mismatch in Model-based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":"2002.04523","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2002.04523","snapshot_observed_at":"2026-06-30T10:34:36.468758Z","title":"Objective mismatch in model-based rein- forcement learning","venue":null,"work_id":"6acc30af-beaa-4afd-a040-d16965f89c57","year":2020},"citing_paper":{"arxiv_id":"2606.15032","last_updated":"2026-06-28T03:48:42Z","snapshot_observed_at":"2026-07-06T23:52:28.557859Z","submitted_at":"2026-06-13T00:21:21Z","title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-30T10:31:37.108792Z"},"links":{"cited_paper":"/paper/2002.04523","citing_paper":"/paper/2606.15032"},"observation_digest":"sha256:9bdd55837d02ee3d30c279a957e06f0ee09dfff9ec2314e529c9deb224400f41","observation_id":"06fb74af-b16b-4b69-bd5e-da71dc261ac6","resolution":{"observed_at":"2026-06-30T10:34:36.470152Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.04523","last_updated":"2021-04-19T03:02:59Z","snapshot_observed_at":"2026-07-06T08:56:30.534634Z","submitted_at":"2020-02-11T16:26:07Z","title":"Objective Mismatch in Model-based Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.04523","snapshot_observed_at":"2026-08-02T04:49:51.783589Z","title":"Lambert, Brandon Amos, Omry Yadan, and Roberto Calandra","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14169","last_updated":"2026-07-19T13:17:14Z","snapshot_observed_at":"2026-08-07T18:39:18.327535Z","submitted_at":"2026-07-15T08:54:59Z","title":"When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-02T04:49:51.783589Z"},"links":{"cited_paper":"/paper/2002.04523","citing_paper":"/paper/2607.14169"},"observation_digest":"sha256:3862bc1b5da5b7f759da2dbb31be43d558de5bbf6ebac5037f1c8069445d0205","observation_id":"8dfa4569-5f99-4803-818f-ae431aab7089","resolution":{"observed_at":"2026-08-02T04:49:51.783589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2002.04523/citation-record","integrity":"/paper/2002.04523/integrity","json":"/paper/2002.04523/citation-record.json","paper":"/paper/2002.04523"},"outbound":[],"paper":{"arxiv_id":"2002.04523","last_updated":"2021-04-19T03:02:59Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T08:56:30.534634Z","submitted_at":"2020-02-11T16:26:07Z","title":"Objective Mismatch in Model-based Reinforcement 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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2002.04523."}