{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QY3BORBOOR4UEM5LLG2TSXEYMQ","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":"8bad424870bf9562adef298fd5f2c0ba6135fee7a3da82a5ee8949d90d3a342b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T17:57:42Z","title_canon_sha256":"55ffef893f23d217a6d7f4022c9ac53633fcda8b97daa97abdeaaee9df5be823"},"schema_version":"1.0","source":{"id":"2403.15377","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15377","created_at":"2026-07-05T08:55:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15377v4","created_at":"2026-07-05T08:55:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15377","created_at":"2026-07-05T08:55:22Z"},{"alias_kind":"pith_short_12","alias_value":"QY3BORBOOR4U","created_at":"2026-07-05T08:55:22Z"},{"alias_kind":"pith_short_16","alias_value":"QY3BORBOOR4UEM5L","created_at":"2026-07-05T08:55:22Z"},{"alias_kind":"pith_short_8","alias_value":"QY3BORBO","created_at":"2026-07-05T08:55:22Z"}],"graph_snapshots":[{"event_id":"sha256:695c2534a88bcb021bd0a4dd268053178d3dca95367465a70ca631089ddebfa3","target":"graph","created_at":"2026-07-05T08:55:22Z","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/2403.15377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that unifies the masked video modeling, crossmodal contrastive learning, and next token prediction, scaling up the video encoder size to 6B parameters. At the data level, we prioritize spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. Through extensive exper","authors_text":"Baoqi Pei, Chenting Wang, Guo Chen, Hongjie Zhang, Jiashuo Yu, Jilan Xu, Kunchang Li, Limin Wang, Rongkun Zheng, Songze Li, Tianxiang Jiang, Xinhao Li, Yali Wang, Yansong Shi, Yifei Huang, Yinan He, Yi Wang, Yu Qiao, Ziang Yan, Zun Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T17:57:42Z","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15377","kind":"arxiv","version":4},"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:eab984102703a87de90d38ede37e5a9c3a71436097bec653d1ab6d6e6340dbef","target":"record","created_at":"2026-07-05T08:55:22Z","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":"8bad424870bf9562adef298fd5f2c0ba6135fee7a3da82a5ee8949d90d3a342b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T17:57:42Z","title_canon_sha256":"55ffef893f23d217a6d7f4022c9ac53633fcda8b97daa97abdeaaee9df5be823"},"schema_version":"1.0","source":{"id":"2403.15377","kind":"arxiv","version":4}},"canonical_sha256":"863617442e74794233ab59b5395c98641e32ca8716ef7dfb0a4ba66834c2e0db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"863617442e74794233ab59b5395c98641e32ca8716ef7dfb0a4ba66834c2e0db","first_computed_at":"2026-07-05T08:55:22.451399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:22.451399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j4AoVBFri2Wq1XR/HEhU+kfqm2zv5njxp/n05F5xBWDUcrTH/Q9lfz9KIFeaVciaAKCxJiHOYjsxVh+UmbhxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:22.451860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.15377","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eab984102703a87de90d38ede37e5a9c3a71436097bec653d1ab6d6e6340dbef","sha256:695c2534a88bcb021bd0a4dd268053178d3dca95367465a70ca631089ddebfa3"],"state_sha256":"f3e68e18db999ba95d37657153fe55bd6980def40ee91daa6cfb9580cd3d0241"}