{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TTOZQKVL7WHDN4JG5GJWHTF72P","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":"a5ca88bf05c2c62d831772f979e59566e6d014d8191466fb6106a3955fdad9db","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T17:59:46Z","title_canon_sha256":"1bc2a4bb413ef59f87703edc44c79c76db37bc5b89cc7341d5ee0e1848b01571"},"schema_version":"1.0","source":{"id":"2106.13230","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13230","created_at":"2026-07-05T02:52:10Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13230v1","created_at":"2026-07-05T02:52:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13230","created_at":"2026-07-05T02:52:10Z"},{"alias_kind":"pith_short_12","alias_value":"TTOZQKVL7WHD","created_at":"2026-07-05T02:52:10Z"},{"alias_kind":"pith_short_16","alias_value":"TTOZQKVL7WHDN4JG","created_at":"2026-07-05T02:52:10Z"},{"alias_kind":"pith_short_8","alias_value":"TTOZQKVL","created_at":"2026-07-05T02:52:10Z"}],"graph_snapshots":[{"event_id":"sha256:23aaea234ea74e52685d20aa5f7309f48446943a4a4628f93f68ad18397e7f13","target":"graph","created_at":"2026-07-05T02:52:10Z","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/2106.13230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and temporal dimensions. In this paper, we instead advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization. The locality of the proposed video a","authors_text":"Han Hu, Jia Ning, Stephen Lin, Yixuan Wei, Yue Cao, Ze Liu, Zheng Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T17:59:46Z","title":"Video Swin Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13230","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:ff70533d2f9d9d15d070a50bfbbca9e53e192a1099ffe409e81bbeb11f723b03","target":"record","created_at":"2026-07-05T02:52:10Z","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":"a5ca88bf05c2c62d831772f979e59566e6d014d8191466fb6106a3955fdad9db","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T17:59:46Z","title_canon_sha256":"1bc2a4bb413ef59f87703edc44c79c76db37bc5b89cc7341d5ee0e1848b01571"},"schema_version":"1.0","source":{"id":"2106.13230","kind":"arxiv","version":1}},"canonical_sha256":"9cdd982aabfd8e36f126e99363ccbfd3f4437494bd4ddafd9b4aca492e2b0cb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cdd982aabfd8e36f126e99363ccbfd3f4437494bd4ddafd9b4aca492e2b0cb3","first_computed_at":"2026-07-05T02:52:10.781951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:10.781951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7UnzhqatVhW6SaPy1h6+5bNFJqgTkuEfi11OlA5Syujx8ggZ/Z8itrnHWFv3sZFkl3DkxpOMulpIFw4WMIoBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:10.782429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13230","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff70533d2f9d9d15d070a50bfbbca9e53e192a1099ffe409e81bbeb11f723b03","sha256:23aaea234ea74e52685d20aa5f7309f48446943a4a4628f93f68ad18397e7f13"],"state_sha256":"8d5c60bce824f9580660be267deeb54babe5b1fb649379d1bc0d606bdb68f51e"}