{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FKHDMYK35TG7OYETQJ7TFSDLA7","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":"51f1d05e9e012961743f6b79331a423e2173a750a803c9faa6cce766e0143224","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T15:39:28Z","title_canon_sha256":"4bd278d6444e528b0aaedadf23353f45f7dbfd461166349f2eb5fa23514d54af"},"schema_version":"1.0","source":{"id":"2303.16058","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.16058","created_at":"2026-07-05T07:54:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.16058v2","created_at":"2026-07-05T07:54:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16058","created_at":"2026-07-05T07:54:30Z"},{"alias_kind":"pith_short_12","alias_value":"FKHDMYK35TG7","created_at":"2026-07-05T07:54:30Z"},{"alias_kind":"pith_short_16","alias_value":"FKHDMYK35TG7OYET","created_at":"2026-07-05T07:54:30Z"},{"alias_kind":"pith_short_8","alias_value":"FKHDMYK3","created_at":"2026-07-05T07:54:30Z"}],"graph_snapshots":[{"event_id":"sha256:080fef657fd918dca11add7d9547a4768250a6ed2ae517f570eddbdb6ac9e7ef","target":"graph","created_at":"2026-07-05T07:54:30Z","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/2303.16058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-level reconstruction poses convergence difficulties and conflicts with high-level cross-modal alignment. This paper proposes a training-efficient method for temporal-sensitive VFMs that integrates the benefits of existing methods. To increase data efficiency, we mask out most of the low-semantics vid","authors_text":"Kunchang Li, Limin Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T15:39:28Z","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16058","kind":"arxiv","version":2},"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:e2bcd443d9e1cc29e5bc7dbaba13d2486cf6956b761af73f3741c7333e0862aa","target":"record","created_at":"2026-07-05T07:54:30Z","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":"51f1d05e9e012961743f6b79331a423e2173a750a803c9faa6cce766e0143224","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-28T15:39:28Z","title_canon_sha256":"4bd278d6444e528b0aaedadf23353f45f7dbfd461166349f2eb5fa23514d54af"},"schema_version":"1.0","source":{"id":"2303.16058","kind":"arxiv","version":2}},"canonical_sha256":"2a8e36615beccdf76093827f32c86b07e5ba159c78ef4cae67f5e2933c86e26f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a8e36615beccdf76093827f32c86b07e5ba159c78ef4cae67f5e2933c86e26f","first_computed_at":"2026-07-05T07:54:30.015779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:30.015779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LHddYEj8PN6kVrdDGFg+vRsj7vuehmS8vK2FOicbDCW8ok65n90b5R+0gIp9PwnXZ6RMGZG3WsLHVgsveAODCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:30.016253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.16058","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2bcd443d9e1cc29e5bc7dbaba13d2486cf6956b761af73f3741c7333e0862aa","sha256:080fef657fd918dca11add7d9547a4768250a6ed2ae517f570eddbdb6ac9e7ef"],"state_sha256":"e6a35a61810f92064307839c229415dd88f5bfeca528b232dc7ebb546eab2944"}