{"as_of":"2026-08-22T22:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e3a38e0a03da4190680fff167abada68df3b9bca953f50ba0a4972324c2b9112","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":"2026-08-10T20:27:33.325150Z","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":"2026-08-06T14:51:50.838500Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.04231","last_updated":"2023-03-29T08:48:35Z","snapshot_observed_at":"2026-08-16T16:10:04.669482Z","submitted_at":"2022-12-08T12:28:23Z","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04231","snapshot_observed_at":"2026-08-10T20:27:33.325150Z","title":"arXiv preprint arXiv:2212.04231 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.09041","last_updated":"2025-01-15T04:00:36Z","snapshot_observed_at":"2026-08-17T20:34:32.528893Z","submitted_at":"2025-01-15T04:00:36Z","title":"Generative Visual Commonsense Answering and Explaining with Generative Scene Graph Constructing","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T20:27:33.325150Z"},"links":{"cited_paper":"/paper/2212.04231","citing_paper":"/paper/2501.09041"},"observation_digest":"sha256:ee62db82bbe4132416b6ac521473d3d176b5e8fab8b82725c0a891aa74a726ed","observation_id":"410bf8d6-05ae-4855-a71c-45e752232589","resolution":{"observed_at":"2026-08-10T20:27:33.325150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04231","last_updated":"2023-03-29T08:48:35Z","snapshot_observed_at":"2026-08-16T16:10:04.669482Z","submitted_at":"2022-12-08T12:28:23Z","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04231","snapshot_observed_at":"2026-08-09T18:03:53.338237Z","title":"Harnessing the power of multi-task pretraining for ground-truth level natural language explanations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00711","last_updated":"2025-09-02T05:28:29Z","snapshot_observed_at":"2026-08-18T12:44:50.240518Z","submitted_at":"2025-02-02T07:54:55Z","title":"VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T18:03:53.338237Z"},"links":{"cited_paper":"/paper/2212.04231","citing_paper":"/paper/2502.00711"},"observation_digest":"sha256:01178e04fb663ef01106451854b2e9cb34a496fb47ed56efbe39371a9b81ce12","observation_id":"cfe634d1-97ed-4d42-a49c-e3f291b3d187","resolution":{"observed_at":"2026-08-09T18:03:53.338237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04231","last_updated":"2023-03-29T08:48:35Z","snapshot_observed_at":"2026-08-16T16:10:04.669482Z","submitted_at":"2022-12-08T12:28:23Z","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","version":2},"cited_work":{"arxiv_id":"2212.04231","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.04231","snapshot_observed_at":"2026-08-06T14:51:50.838500Z","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","venue":"cs.CV","work_id":"1f5b9e76-5200-44f3-8052-f46ae5f96bc4","year":2022},"citing_paper":{"arxiv_id":"2507.17467","last_updated":"2025-07-23T12:46:51Z","snapshot_observed_at":"2026-08-12T03:42:52.728365Z","submitted_at":"2025-07-23T12:46:51Z","title":"Probing Vision-Language Understanding through the Visual Entailment Task: promises and pitfalls","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T14:51:50.628101Z"},"links":{"cited_paper":"/paper/2212.04231","citing_paper":"/paper/2507.17467"},"observation_digest":"sha256:79aa8c577e9558705328109751740cbd237c3ba334ef8b0da09a458f874b20e6","observation_id":"5978a572-316c-4181-9e77-edbe33f93f06","resolution":{"observed_at":"2026-08-06T14:51:50.844270Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2212.04231/citation-record","integrity":"/paper/2212.04231/integrity","json":"/paper/2212.04231/citation-record.json","paper":"/paper/2212.04231"},"outbound":[],"paper":{"arxiv_id":"2212.04231","last_updated":"2023-03-29T08:48:35Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T16:10:04.669482Z","submitted_at":"2022-12-08T12:28:23Z","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations"},"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:2212.04231."}