{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FWHBT65VJLNVXJRS3R4XWCCFRZ","short_pith_number":"pith:FWHBT65V","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"},"canonical_sha256":"2d8e19fbb54adb5ba632dc797b08458e4f373578a464fae18873722cbfbefc2f","source":{"kind":"arxiv","id":"2305.13903","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13903","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13903v3","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13903","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"pith_short_12","alias_value":"FWHBT65VJLNV","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"pith_short_16","alias_value":"FWHBT65VJLNVXJRS","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"pith_short_8","alias_value":"FWHBT65V","created_at":"2026-07-05T07:10:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FWHBT65VJLNVXJRS3R4XWCCFRZ","target":"record","payload":{"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"},"canonical_sha256":"2d8e19fbb54adb5ba632dc797b08458e4f373578a464fae18873722cbfbefc2f","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"},"source_kind":"arxiv","source_id":"2305.13903","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"27hjX3ALZemncZt8fMUbz0wgHKdkAtYnSrmxqLMMAolQmeF8IMqNXwxU/3ZmD/tDpSNAYZTwymUDNbehhUDoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:41.790689Z"},"content_sha256":"cefb1e6e594a819c4531729a8a03dbb4f0b122696fc1cf1ba15e92a271575f13","schema_version":"1.0","event_id":"sha256:cefb1e6e594a819c4531729a8a03dbb4f0b122696fc1cf1ba15e92a271575f13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FWHBT65VJLNVXJRS3R4XWCCFRZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwkfcKGPk73dpyM16gJd+hoRcOSGWAiUSt3V25DrmxPtVAztwr8d5c5NPmDdnvWYDuxSZG6Kt/7/QfYQGjuTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:05:41.791259Z"},"content_sha256":"7d02de05851934328b370d6975394721a4f06d938cc5a72e95debcd2dd344925","schema_version":"1.0","event_id":"sha256:7d02de05851934328b370d6975394721a4f06d938cc5a72e95debcd2dd344925"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/bundle.json","state_url":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T18:05:41Z","links":{"resolver":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ","bundle":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/bundle.json","state":"https://pith.science/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWHBT65VJLNVXJRS3R4XWCCFRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FWHBT65VJLNVXJRS3R4XWCCFRZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e5b73b16e33ca57d508e1f3bc01f52347caf34d22f5a152516d7ad9606de090f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T10:26:42Z","title_canon_sha256":"15b2ff0563a60905f780342f178524f4b8ea06d20fbc8a14ef4397a4172847fd"},"schema_version":"1.0","source":{"id":"2305.13903","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13903","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13903v3","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13903","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"pith_short_12","alias_value":"FWHBT65VJLNV","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"pith_short_16","alias_value":"FWHBT65VJLNVXJRS","created_at":"2026-07-05T07:10:47Z"},{"alias_kind":"pith_short_8","alias_value":"FWHBT65V","created_at":"2026-07-05T07:10:47Z"}],"graph_snapshots":[{"event_id":"sha256:7d02de05851934328b370d6975394721a4f06d938cc5a72e95debcd2dd344925","target":"graph","created_at":"2026-07-05T07:10:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.13903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alex Mei, Andy Ouyang, Chinmay Sonar, Daniel Rose, Michael Saxon, Ryan He, Vaishnavi Himakunthala, William Yang Wang, Yujie Lu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T10:26:42Z","title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13903","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cefb1e6e594a819c4531729a8a03dbb4f0b122696fc1cf1ba15e92a271575f13","target":"record","created_at":"2026-07-05T07:10:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e5b73b16e33ca57d508e1f3bc01f52347caf34d22f5a152516d7ad9606de090f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T10:26:42Z","title_canon_sha256":"15b2ff0563a60905f780342f178524f4b8ea06d20fbc8a14ef4397a4172847fd"},"schema_version":"1.0","source":{"id":"2305.13903","kind":"arxiv","version":3}},"canonical_sha256":"2d8e19fbb54adb5ba632dc797b08458e4f373578a464fae18873722cbfbefc2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d8e19fbb54adb5ba632dc797b08458e4f373578a464fae18873722cbfbefc2f","first_computed_at":"2026-07-05T07:10:47.984614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:47.984614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c6VyIIW/vFa4GRhgzLqcoDBsfpEUylaR79cmLW8K5ZwYlgtmV4Htfm64PXwoqt20BfqqE3v+EOUQyXRJ6HZlAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:47.985090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13903","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cefb1e6e594a819c4531729a8a03dbb4f0b122696fc1cf1ba15e92a271575f13","sha256:7d02de05851934328b370d6975394721a4f06d938cc5a72e95debcd2dd344925"],"state_sha256":"553461bb97864b9bf6e954e6ded1ed5e5706958964a2342a9b826b3fae84bd0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5YJkKgXffp5k6m/xfSz3a79NJCDFE8cLHpMneTRVly2qE8rewvdj9xc0pOjloOyRhrgPhWbfgCVKmiM/Q7m3Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:05:41.795491Z","bundle_sha256":"7d17ea5eb0ad144966a38ddf18f1fb0c9970d6ec51eb1ff6dc3a8f41146bc165"}}