{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FWHBT65VJLNVXJRS3R4XWCCFRZ","short_pith_number":"pith:FWHBT65V","schema_version":"1.0","canonical_sha256":"2d8e19fbb54adb5ba632dc797b08458e4f373578a464fae18873722cbfbefc2f","source":{"kind":"arxiv","id":"2305.13903","version":3},"attestation_state":"computed","paper":{"title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alex Mei, Andy Ouyang, Chinmay Sonar, Daniel Rose, Michael Saxon, Ryan He, Vaishnavi Himakunthala, William Yang Wang, Yujie Lu","submitted_at":"2023-05-23T10:26:42Z","abstract_excerpt":"Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging the power and robustness of vision-language while alleviating the computational complexities of processing videos. To evaluate this novel application, we introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. Inspired by v"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.13903","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T10:26:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"15b2ff0563a60905f780342f178524f4b8ea06d20fbc8a14ef4397a4172847fd","abstract_canon_sha256":"e5b73b16e33ca57d508e1f3bc01f52347caf34d22f5a152516d7ad9606de090f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:47.985090Z","signature_b64":"c6VyIIW/vFa4GRhgzLqcoDBsfpEUylaR79cmLW8K5ZwYlgtmV4Htfm64PXwoqt20BfqqE3v+EOUQyXRJ6HZlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8e19fbb54adb5ba632dc797b08458e4f373578a464fae18873722cbfbefc2f","last_reissued_at":"2026-07-05T07:10:47.984614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:47.984614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alex Mei, Andy Ouyang, Chinmay Sonar, Daniel Rose, Michael Saxon, Ryan He, Vaishnavi Himakunthala, William Yang Wang, Yujie Lu","submitted_at":"2023-05-23T10:26:42Z","abstract_excerpt":"Despite exciting recent results showing vision-language systems' capacity to reason about images using natural language, their capacity for video reasoning remains under-explored. We motivate framing video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging the power and robustness of vision-language while alleviating the computational complexities of processing videos. To evaluate this novel application, we introduce VIP, an inference-time challenge dataset designed to explore models' reasoning capabilities through video chain-of-thought. Inspired by v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13903","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.13903/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.13903","created_at":"2026-07-05T07:10:47.984673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13903v3","created_at":"2026-07-05T07:10:47.984673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13903","created_at":"2026-07-05T07:10:47.984673+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWHBT65VJLNV","created_at":"2026-07-05T07:10:47.984673+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWHBT65VJLNVXJRS","created_at":"2026-07-05T07:10:47.984673+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWHBT65V","created_at":"2026-07-05T07:10:47.984673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2309.05922","citing_title":"A Survey of Hallucination in Large Foundation Models","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ","json":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ.json","graph_json":"https://pith.science/api/pith-number/FWHBT65VJLNVXJRS3R4XWCCFRZ/graph.json","events_json":"https://pith.science/api/pith-number/FWHBT65VJLNVXJRS3R4XWCCFRZ/events.json","paper":"https://pith.science/paper/FWHBT65V"},"agent_actions":{"view_html":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ","download_json":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ.json","view_paper":"https://pith.science/paper/FWHBT65V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13903&json=true","fetch_graph":"https://pith.science/api/pith-number/FWHBT65VJLNVXJRS3R4XWCCFRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FWHBT65VJLNVXJRS3R4XWCCFRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/action/storage_attestation","attest_author":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/action/author_attestation","sign_citation":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/action/citation_signature","submit_replication":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/action/replication_record"}},"created_at":"2026-07-05T07:10:47.984673+00:00","updated_at":"2026-07-05T07:10:47.984673+00:00"}