{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V7Y5M63PL56L7YQKEG2A3C5IRG","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":"8ab15401a322d223dc430f138d94eb5d5997662d7b78fa84927b630bb424ff5f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:29:49Z","title_canon_sha256":"e6fcce104cf0356c1142381557e04c61ced1013dcf286c86cf0869fc754ee185"},"schema_version":"1.0","source":{"id":"2402.13217","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13217","created_at":"2026-07-05T11:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13217v3","created_at":"2026-07-05T11:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13217","created_at":"2026-07-05T11:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"V7Y5M63PL56L","created_at":"2026-07-05T11:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"V7Y5M63PL56L7YQK","created_at":"2026-07-05T11:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"V7Y5M63P","created_at":"2026-07-05T11:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:9808a457f3f8b07564a0b2c187c15d616b99966ef195f3f6a60adfd211a6a3f5","target":"graph","created_at":"2026-07-05T11:17:32Z","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/2402.13217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model. We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text (e.g., ASR transcripts). The pretraining approach improves upon masked autoencoding by global-local distillation of semantic video embeddings and a token shuffling scheme, enabling VideoPrism to focus primarily on the video modality while leveraging the invaluable text associated with videos. We extensively test VideoPrism ","authors_text":"Boqing Gong, David A. Ross, Florian Schroff, Hao Zhou, Hartwig Adam, Huisheng Wang, Jennifer J. Sun, Liangzhe Yuan, Long Zhao, Luke Friedman, Mikhail Sirotenko, Ming-Hsuan Yang, Nitesh B. Gundavarapu, Rachel Hornung, Rui Qian, Shen Yan, Ting Liu, Tobias Weyand, Yue Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:29:49Z","title":"VideoPrism: A Foundational Visual Encoder for Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13217","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":"sha256:57c721842681414cf5028838557bd59425fd41bfd962433c249b31c70d7f9d5d","target":"record","created_at":"2026-07-05T11:17:32Z","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":"8ab15401a322d223dc430f138d94eb5d5997662d7b78fa84927b630bb424ff5f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T18:29:49Z","title_canon_sha256":"e6fcce104cf0356c1142381557e04c61ced1013dcf286c86cf0869fc754ee185"},"schema_version":"1.0","source":{"id":"2402.13217","kind":"arxiv","version":3}},"canonical_sha256":"aff1d67b6f5f7cbfe20a21b40d8ba889b25d261c8f378470675d279d4ea6c8d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aff1d67b6f5f7cbfe20a21b40d8ba889b25d261c8f378470675d279d4ea6c8d1","first_computed_at":"2026-07-05T11:17:32.089260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:32.089260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHkhY5AnRqwp0qa6W2fK2Jw3ufWKrQ4mLkXy/oB9MwvvHWKC3Gd/rdDolkZwsJ4xvo3BEFlR6rhk9Tvtn0OaBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:32.089739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13217","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57c721842681414cf5028838557bd59425fd41bfd962433c249b31c70d7f9d5d","sha256:9808a457f3f8b07564a0b2c187c15d616b99966ef195f3f6a60adfd211a6a3f5"],"state_sha256":"6b69cb9087e19f06d91ccd218276d40668ff2da352f428f628d09d0c70c09351"}