{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6SZV2WS74EVQ6F77UOTEEGHOGQ","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":"f6b00e73cf1c3e2c9c47bbe7f116d1c73bbb4738e776cd0e6cab3736ef1e1266","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T23:27:21Z","title_canon_sha256":"50a4d8d5d2a5e18bbd045bcaff67971d58fc8d4526064291c17933e9603d38b0"},"schema_version":"1.0","source":{"id":"2305.03204","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03204","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03204v1","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03204","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_12","alias_value":"6SZV2WS74EVQ","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_16","alias_value":"6SZV2WS74EVQ6F77","created_at":"2026-07-05T06:07:11Z"},{"alias_kind":"pith_short_8","alias_value":"6SZV2WS7","created_at":"2026-07-05T06:07:11Z"}],"graph_snapshots":[{"event_id":"sha256:5dd4afb3d6598e61ecc5e923b0953ed9a159dec48790ebb2273f2ad46a565e63","target":"graph","created_at":"2026-07-05T06:07:11Z","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/2305.03204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is first jointly pre-trained on massive image-text data to learn fundamental vision-language concepts, and then adapted to video data in an intermediate video-text pre-training stage to learn video-specific skills such as spatio-temporal reasoning. As a result, our VideoOFA model achieves new state-of-the-art performance on four Video Captioning benchmarks, beating prior art by an average of 9.7 points in CIDEr score. It ","authors_text":"Barlas O\\u{g}uz, Lili Yu, Wenhan Xiong, Wen-tau Yih, Xilun Chen, Yashar Mehdad","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T23:27:21Z","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03204","kind":"arxiv","version":1},"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:eee367ec38fcf52d453eb82ae4da68d5c39200c6194b0086496ddf2ba4059676","target":"record","created_at":"2026-07-05T06:07:11Z","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":"f6b00e73cf1c3e2c9c47bbe7f116d1c73bbb4738e776cd0e6cab3736ef1e1266","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T23:27:21Z","title_canon_sha256":"50a4d8d5d2a5e18bbd045bcaff67971d58fc8d4526064291c17933e9603d38b0"},"schema_version":"1.0","source":{"id":"2305.03204","kind":"arxiv","version":1}},"canonical_sha256":"f4b35d5a5fe12b0f17ffa3a64218ee340d00eb4bcfce765387fbc73224aae4a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4b35d5a5fe12b0f17ffa3a64218ee340d00eb4bcfce765387fbc73224aae4a4","first_computed_at":"2026-07-05T06:07:11.922669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:11.922669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"swzdSs0J/J91YCwGQX3uthCBGDiQiMjHZyahRDIWL5izTT6sKrQ/a124r1kX6I+vT0nf5NqYomFNUJKlN7edAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:11.923142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03204","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eee367ec38fcf52d453eb82ae4da68d5c39200c6194b0086496ddf2ba4059676","sha256:5dd4afb3d6598e61ecc5e923b0953ed9a159dec48790ebb2273f2ad46a565e63"],"state_sha256":"c429ffc236ca85c6eea98f68cd1355b84516bbe7f99233e3eaf9a5b8add878ad"}