{"as_of":"2026-08-12T20:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b1983a6dd20394332c3d594e6ce4d211e2afc1eb0e3489eb39bc1bcce19c191e","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T19:04:25.923680Z","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":"2026-05-17T23:04:44.485802Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.09374","last_updated":"2022-11-17T07:04:11Z","snapshot_observed_at":"2026-08-11T11:17:17.684093Z","submitted_at":"2022-11-17T07:04:11Z","title":"Execution-based Evaluation for Data Science Code Generation Models","version":1},"cited_work":{"arxiv_id":"2211.09374","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.09374","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2211.09374 , year=","venue":null,"work_id":"5a6e36f6-134a-407b-a3bd-f9f743996249","year":2022},"citing_paper":{"arxiv_id":"2402.13228","last_updated":"2024-07-03T13:46:33Z","snapshot_observed_at":"2026-08-08T16:03:10.053914Z","submitted_at":"2024-02-20T18:42:34Z","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","version":2},"reference_index":127,"source":"arxiv_source","source_observed_at":"2026-05-17T23:04:44.287660Z"},"links":{"cited_paper":"/paper/2211.09374","citing_paper":"/paper/2402.13228"},"observation_digest":"sha256:86521d5f4e7c8bcc5f428b0448190606d59534aa31262a7e8a2fdeafae0964db","observation_id":"b9aa67de-2bc7-48ae-8c04-cbd2352be207","resolution":{"observed_at":"2026-05-17T23:04:44.487777Z","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":"2211.09374","last_updated":"2022-11-17T07:04:11Z","snapshot_observed_at":"2026-08-11T11:17:17.684093Z","submitted_at":"2022-11-17T07:04:11Z","title":"Execution-based Evaluation for Data Science Code Generation Models","version":1},"cited_work":{"arxiv_id":"2211.09374","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.09374","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2211.09374 , year=","venue":null,"work_id":"5a6e36f6-134a-407b-a3bd-f9f743996249","year":2022},"citing_paper":{"arxiv_id":"2406.00515","last_updated":"2024-11-10T22:02:27Z","snapshot_observed_at":"2026-07-29T20:40:25.374189Z","submitted_at":"2024-06-01T17:48:15Z","title":"A Survey on Large Language Models for Code Generation","version":2},"reference_index":109,"source":"pdf_text","source_observed_at":"2026-05-13T20:18:06.304134Z"},"links":{"cited_paper":"/paper/2211.09374","citing_paper":"/paper/2406.00515"},"observation_digest":"sha256:e353f5db11c604f2b192ce8230c47470f1ad044c4abcd61bd84d83b6612ce19c","observation_id":"cdd0e85e-b736-4766-9b18-2631d738f4d1","resolution":{"observed_at":"2026-05-13T20:18:06.561107Z","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":"2211.09374","last_updated":"2022-11-17T07:04:11Z","snapshot_observed_at":"2026-08-11T11:17:17.684093Z","submitted_at":"2022-11-17T07:04:11Z","title":"Execution-based Evaluation for Data Science Code Generation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09374","snapshot_observed_at":"2026-08-10T19:04:25.923680Z","title":"In Forty-first International Confer- ence on Machine Learning, ICML 2024, Vienna, Aus- tria, July 21-27, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.10711","last_updated":"2026-07-06T06:02:32Z","snapshot_observed_at":"2026-08-10T18:59:26.797441Z","submitted_at":"2025-01-18T09:51:57Z","title":"Code Benchmarks Should Prioritize Rigor, Reliability, and Reproducibility","version":5},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T19:04:25.923680Z"},"links":{"cited_paper":"/paper/2211.09374","citing_paper":"/paper/2501.10711"},"observation_digest":"sha256:104c401ee83ab8e29f2d11646cb63794b5d2e23f0c8aa1efcb642ce5c09d0f35","observation_id":"8ca4f069-33a3-4768-8b75-1b2ff9c01810","resolution":{"observed_at":"2026-08-10T19:04:25.923680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2211.09374/citation-record","integrity":"/paper/2211.09374/integrity","json":"/paper/2211.09374/citation-record.json","paper":"/paper/2211.09374"},"outbound":[],"paper":{"arxiv_id":"2211.09374","last_updated":"2022-11-17T07:04:11Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-11T11:17:17.684093Z","submitted_at":"2022-11-17T07:04:11Z","title":"Execution-based Evaluation for Data Science Code Generation Models"},"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 3 inbound Pith citation observations for arXiv:2211.09374."}