{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HKAVV3A45HPE2MXZS3GYBMNRD6","short_pith_number":"pith:HKAVV3A4","canonical_record":{"source":{"id":"2304.08451","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T17:21:21Z","cross_cats_sorted":[],"title_canon_sha256":"09239f0028055c64a3326e6dd0adaca97d7badfc57feb52c8105d3c79feb3294","abstract_canon_sha256":"ffe7aff1c499345a4e5b510d15671f5217ab2e7dc41b37366d576bc9ed02af90"},"schema_version":"1.0"},"canonical_sha256":"3a815aec1ce9de4d32f996cd80b1b11fa6a74fe9497d94c6cb91efae9249e2ba","source":{"kind":"arxiv","id":"2304.08451","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08451","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08451v3","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08451","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"HKAVV3A45HPE","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"pith_short_16","alias_value":"HKAVV3A45HPE2MXZ","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"pith_short_8","alias_value":"HKAVV3A4","created_at":"2026-07-05T06:45:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HKAVV3A45HPE2MXZS3GYBMNRD6","target":"record","payload":{"canonical_record":{"source":{"id":"2304.08451","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T17:21:21Z","cross_cats_sorted":[],"title_canon_sha256":"09239f0028055c64a3326e6dd0adaca97d7badfc57feb52c8105d3c79feb3294","abstract_canon_sha256":"ffe7aff1c499345a4e5b510d15671f5217ab2e7dc41b37366d576bc9ed02af90"},"schema_version":"1.0"},"canonical_sha256":"3a815aec1ce9de4d32f996cd80b1b11fa6a74fe9497d94c6cb91efae9249e2ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:16.308063Z","signature_b64":"z82wxbdXQa43aJAKcGvEU4W43JvsuSj/9JFTS7u0HpthliSEW2jJJooUMyfTmQMTKWFXo4V6BUa78962hLd7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a815aec1ce9de4d32f996cd80b1b11fa6a74fe9497d94c6cb91efae9249e2ba","last_reissued_at":"2026-07-05T06:45:16.307683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:16.307683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.08451","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yK/TpZj/o7oY2ZOUVs7qjnktVhSvOtdlExGr7DryIzGpxrf5PJXXA1DFrXSO1CGrXvALD4I9alTcFZ5zgTw4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:11:39.497767Z"},"content_sha256":"d588bf50643a323073885716ba44c926031ccb9bbd108cdd0e9e81fec03fb3c9","schema_version":"1.0","event_id":"sha256:d588bf50643a323073885716ba44c926031ccb9bbd108cdd0e9e81fec03fb3c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HKAVV3A45HPE2MXZS3GYBMNRD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Video Action Detection with Token Dropout and Context Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gangshan Wu, Lei Chen, Limin Wang, Yibing Song, Zhan Tong","submitted_at":"2023-04-17T17:21:21Z","abstract_excerpt":"Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08451","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.08451/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDfDn3xRhhQLTcmvUqFmfbS4S2gfkL1pIbkoWgJn/joZbDEo5oXPYEZve39ge65U2/9Re2vJc3ReKVmNCAooDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:11:39.498164Z"},"content_sha256":"79d59349735baa3c577f036522c79e2ee6353d582989d48bee39a626fb0f7d54","schema_version":"1.0","event_id":"sha256:79d59349735baa3c577f036522c79e2ee6353d582989d48bee39a626fb0f7d54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKAVV3A45HPE2MXZS3GYBMNRD6/bundle.json","state_url":"https://pith.science/pith/HKAVV3A45HPE2MXZS3GYBMNRD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKAVV3A45HPE2MXZS3GYBMNRD6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T18:11:39Z","links":{"resolver":"https://pith.science/pith/HKAVV3A45HPE2MXZS3GYBMNRD6","bundle":"https://pith.science/pith/HKAVV3A45HPE2MXZS3GYBMNRD6/bundle.json","state":"https://pith.science/pith/HKAVV3A45HPE2MXZS3GYBMNRD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKAVV3A45HPE2MXZS3GYBMNRD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HKAVV3A45HPE2MXZS3GYBMNRD6","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":"ffe7aff1c499345a4e5b510d15671f5217ab2e7dc41b37366d576bc9ed02af90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T17:21:21Z","title_canon_sha256":"09239f0028055c64a3326e6dd0adaca97d7badfc57feb52c8105d3c79feb3294"},"schema_version":"1.0","source":{"id":"2304.08451","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08451","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08451v3","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08451","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"HKAVV3A45HPE","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"pith_short_16","alias_value":"HKAVV3A45HPE2MXZ","created_at":"2026-07-05T06:45:16Z"},{"alias_kind":"pith_short_8","alias_value":"HKAVV3A4","created_at":"2026-07-05T06:45:16Z"}],"graph_snapshots":[{"event_id":"sha256:79d59349735baa3c577f036522c79e2ee6353d582989d48bee39a626fb0f7d54","target":"graph","created_at":"2026-07-05T06:45:16Z","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/2304.08451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relev","authors_text":"Gangshan Wu, Lei Chen, Limin Wang, Yibing Song, Zhan Tong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T17:21:21Z","title":"Efficient Video Action Detection with Token Dropout and Context Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08451","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:d588bf50643a323073885716ba44c926031ccb9bbd108cdd0e9e81fec03fb3c9","target":"record","created_at":"2026-07-05T06:45:16Z","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":"ffe7aff1c499345a4e5b510d15671f5217ab2e7dc41b37366d576bc9ed02af90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T17:21:21Z","title_canon_sha256":"09239f0028055c64a3326e6dd0adaca97d7badfc57feb52c8105d3c79feb3294"},"schema_version":"1.0","source":{"id":"2304.08451","kind":"arxiv","version":3}},"canonical_sha256":"3a815aec1ce9de4d32f996cd80b1b11fa6a74fe9497d94c6cb91efae9249e2ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a815aec1ce9de4d32f996cd80b1b11fa6a74fe9497d94c6cb91efae9249e2ba","first_computed_at":"2026-07-05T06:45:16.307683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:16.307683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z82wxbdXQa43aJAKcGvEU4W43JvsuSj/9JFTS7u0HpthliSEW2jJJooUMyfTmQMTKWFXo4V6BUa78962hLd7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:16.308063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08451","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d588bf50643a323073885716ba44c926031ccb9bbd108cdd0e9e81fec03fb3c9","sha256:79d59349735baa3c577f036522c79e2ee6353d582989d48bee39a626fb0f7d54"],"state_sha256":"2b90b96ff88ad359c413472e9e1225da4c74f24d636ecfb6a9bd1ae25f721569"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpYbO+TWO2Yy4sOHmvsvjlD1s6uTEXaC+ccyW/rZ2uBJXCC0WYz2ET8orgVIPLaNCOSmW8oG0bYa31FTUsOZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:11:39.500827Z","bundle_sha256":"49e731ea4ef3a5dff6ea29c19451ff232c6814baf8fea5e812643f6ceea39b06"}}