{"as_of":"2026-08-15T05:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ab08a3130d18ea60d81bb8e94c873220466beef764df83f37db25c226ef8538b","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T19:03:03.653292Z","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":"2026-05-10T11:05:09.089717Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.04858","last_updated":"2024-07-01T10:03:33Z","snapshot_observed_at":"2026-08-15T01:32:29.918153Z","submitted_at":"2024-02-07T13:55:27Z","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04858","snapshot_observed_at":"2026-08-11T19:03:03.653292Z","title":"arXiv:2402.04858","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07322","last_updated":"2024-12-11T06:33:55Z","snapshot_observed_at":"2026-08-15T04:20:47.605648Z","submitted_at":"2024-12-10T09:10:11Z","title":"ConceptSearch: Towards Efficient Program Search Using LLMs for Abstraction and Reasoning Corpus (ARC)","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T19:03:03.653292Z"},"links":{"cited_paper":"/paper/2402.04858","citing_paper":"/paper/2412.07322"},"observation_digest":"sha256:115778cf414350d4ef663d4e64b2bdaeeb4a99175f0b333e63f8f5fb2fdca0ae","observation_id":"454b67b2-4b1c-46f8-a7d2-5071f10b59cc","resolution":{"observed_at":"2026-08-11T19:03:03.653292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04858","last_updated":"2024-07-01T10:03:33Z","snapshot_observed_at":"2026-08-15T01:32:29.918153Z","submitted_at":"2024-02-07T13:55:27Z","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","version":2},"cited_work":{"arxiv_id":"2402.04858","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04858","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint , author=","venue":null,"work_id":"56ce34a6-bb14-4c1e-b3c6-197770203df9","year":null},"citing_paper":{"arxiv_id":"2604.18839","last_updated":"2026-04-20T21:06:12Z","snapshot_observed_at":"2026-08-12T01:18:54.060014Z","submitted_at":"2026-04-20T21:06:12Z","title":"One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models","version":1},"reference_index":160,"source":"arxiv_source","source_observed_at":"2026-05-10T04:56:35.796962Z"},"links":{"cited_paper":"/paper/2402.04858","citing_paper":"/paper/2604.18839"},"observation_digest":"sha256:12326454eafc0aa2bcf8c598c114b23558e136aac885fd3f1f111e6148c0fac8","observation_id":"59a04b48-ddbb-41e2-85b1-f678b815050a","resolution":{"observed_at":"2026-05-10T11:05:09.091301Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04858","last_updated":"2024-07-01T10:03:33Z","snapshot_observed_at":"2026-08-15T01:32:29.918153Z","submitted_at":"2024-02-07T13:55:27Z","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04858","snapshot_observed_at":"2026-08-07T00:13:52.062994Z","title":"Zhang, Michaël Defferrard, and Taco Cohen","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.02713","last_updated":"2026-08-03T17:59:58Z","snapshot_observed_at":"2026-08-12T12:39:41.730067Z","submitted_at":"2026-08-03T17:59:58Z","title":"Quo Vadis, World Modeling?","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:13:52.062994Z"},"links":{"cited_paper":"/paper/2402.04858","citing_paper":"/paper/2608.02713"},"observation_digest":"sha256:5844eb2b5719b918978d14f178f520cdbcb24090440338c3cd2d060eb7cdb6c8","observation_id":"6b461ce1-74bb-4e67-8a35-bee68b317370","resolution":{"observed_at":"2026-08-07T00:13:52.062994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.04858/citation-record","integrity":"/paper/2402.04858/integrity","json":"/paper/2402.04858/citation-record.json","paper":"/paper/2402.04858"},"outbound":[],"paper":{"arxiv_id":"2402.04858","last_updated":"2024-07-01T10:03:33Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-15T01:32:29.918153Z","submitted_at":"2024-02-07T13:55:27Z","title":"CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.04858."}