{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ASTFCPBVL33NZFUPL2KGGI3GFD","short_pith_number":"pith:ASTFCPBV","canonical_record":{"source":{"id":"2102.00719","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-01T09:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"84ee0ffd54546a57f981b657dde03071702f121498187f25c6073d91c34cb84e","abstract_canon_sha256":"1a8cd0ad432fcca52add3b72c3861fd7d7f7d5f35c48e2eaea486541af256dd0"},"schema_version":"1.0"},"canonical_sha256":"04a6513c355ef6dc968f5e9463236628f34b096fb6330507738ac191899e639d","source":{"kind":"arxiv","id":"2102.00719","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.00719","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2102.00719v3","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00719","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"ASTFCPBVL33N","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"ASTFCPBVL33NZFUP","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"ASTFCPBV","created_at":"2026-07-05T03:06:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ASTFCPBVL33NZFUPL2KGGI3GFD","target":"record","payload":{"canonical_record":{"source":{"id":"2102.00719","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-01T09:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"84ee0ffd54546a57f981b657dde03071702f121498187f25c6073d91c34cb84e","abstract_canon_sha256":"1a8cd0ad432fcca52add3b72c3861fd7d7f7d5f35c48e2eaea486541af256dd0"},"schema_version":"1.0"},"canonical_sha256":"04a6513c355ef6dc968f5e9463236628f34b096fb6330507738ac191899e639d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:18.351004Z","signature_b64":"Y+um1F4LyD0/3/NARlOMoYVIybGylT8lUv4tMFA1asr6eic6eL8ig6DCt0T32hRDMGAXrrPniEj4CkEw8jp+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04a6513c355ef6dc968f5e9463236628f34b096fb6330507738ac191899e639d","last_reissued_at":"2026-07-05T03:06:18.350525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:18.350525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.00719","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":"2026-07-05T03:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbTbnHhgg/Wt0cWOCF+X9fhaoDtiHf47vWWoXHtAIXk5vLFvZ8D42y/WuT+MG+dcMhZpeUxHAiRsR1MaKkkABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:51:21.944023Z"},"content_sha256":"b6433e45a5f36357e4eb1d5fda41e63f31f4505dbc946c1e045b3d27957c3514","schema_version":"1.0","event_id":"sha256:b6433e45a5f36357e4eb1d5fda41e63f31f4505dbc946c1e045b3d27957c3514"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ASTFCPBVL33NZFUPL2KGGI3GFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Transformer Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Neimark, Dotan Asselmann, Maya Zohar, Omri Bar","submitted_at":"2021-02-01T09:29:10Z","abstract_excerpt":"This paper presents VTN, a transformer-based framework for video recognition. Inspired by recent developments in vision transformers, we ditch the standard approach in video action recognition that relies on 3D ConvNets and introduce a method that classifies actions by attending to the entire video sequence information. Our approach is generic and builds on top of any given 2D spatial network. In terms of wall runtime, it trains $16.1\\times$ faster and runs $5.1\\times$ faster during inference while maintaining competitive accuracy compared to other state-of-the-art methods. It enables whole vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00719","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/2102.00719/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":"2026-07-05T03:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2cK6Vux627bTizulXUlXfaLE2h/83oOcHI5srI8hazr2KoqhRJBbHGChRR6rp2ia13Ty1suNVeqkHcKSMEuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:51:21.944522Z"},"content_sha256":"4be9e9a1b3892b7b46aa798d45daeeda255539de90780128476a8e954b17f3cf","schema_version":"1.0","event_id":"sha256:4be9e9a1b3892b7b46aa798d45daeeda255539de90780128476a8e954b17f3cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASTFCPBVL33NZFUPL2KGGI3GFD/bundle.json","state_url":"https://pith.science/pith/ASTFCPBVL33NZFUPL2KGGI3GFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASTFCPBVL33NZFUPL2KGGI3GFD/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":"2026-08-12T07:51:21Z","links":{"resolver":"https://pith.science/pith/ASTFCPBVL33NZFUPL2KGGI3GFD","bundle":"https://pith.science/pith/ASTFCPBVL33NZFUPL2KGGI3GFD/bundle.json","state":"https://pith.science/pith/ASTFCPBVL33NZFUPL2KGGI3GFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASTFCPBVL33NZFUPL2KGGI3GFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ASTFCPBVL33NZFUPL2KGGI3GFD","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":"1a8cd0ad432fcca52add3b72c3861fd7d7f7d5f35c48e2eaea486541af256dd0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-01T09:29:10Z","title_canon_sha256":"84ee0ffd54546a57f981b657dde03071702f121498187f25c6073d91c34cb84e"},"schema_version":"1.0","source":{"id":"2102.00719","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.00719","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2102.00719v3","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00719","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"ASTFCPBVL33N","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"ASTFCPBVL33NZFUP","created_at":"2026-07-05T03:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"ASTFCPBV","created_at":"2026-07-05T03:06:18Z"}],"graph_snapshots":[{"event_id":"sha256:4be9e9a1b3892b7b46aa798d45daeeda255539de90780128476a8e954b17f3cf","target":"graph","created_at":"2026-07-05T03:06:18Z","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/2102.00719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents VTN, a transformer-based framework for video recognition. Inspired by recent developments in vision transformers, we ditch the standard approach in video action recognition that relies on 3D ConvNets and introduce a method that classifies actions by attending to the entire video sequence information. Our approach is generic and builds on top of any given 2D spatial network. In terms of wall runtime, it trains $16.1\\times$ faster and runs $5.1\\times$ faster during inference while maintaining competitive accuracy compared to other state-of-the-art methods. It enables whole vi","authors_text":"Daniel Neimark, Dotan Asselmann, Maya Zohar, Omri Bar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-01T09:29:10Z","title":"Video Transformer Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00719","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:b6433e45a5f36357e4eb1d5fda41e63f31f4505dbc946c1e045b3d27957c3514","target":"record","created_at":"2026-07-05T03:06:18Z","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":"1a8cd0ad432fcca52add3b72c3861fd7d7f7d5f35c48e2eaea486541af256dd0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-01T09:29:10Z","title_canon_sha256":"84ee0ffd54546a57f981b657dde03071702f121498187f25c6073d91c34cb84e"},"schema_version":"1.0","source":{"id":"2102.00719","kind":"arxiv","version":3}},"canonical_sha256":"04a6513c355ef6dc968f5e9463236628f34b096fb6330507738ac191899e639d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04a6513c355ef6dc968f5e9463236628f34b096fb6330507738ac191899e639d","first_computed_at":"2026-07-05T03:06:18.350525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:18.350525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y+um1F4LyD0/3/NARlOMoYVIybGylT8lUv4tMFA1asr6eic6eL8ig6DCt0T32hRDMGAXrrPniEj4CkEw8jp+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:18.351004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.00719","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6433e45a5f36357e4eb1d5fda41e63f31f4505dbc946c1e045b3d27957c3514","sha256:4be9e9a1b3892b7b46aa798d45daeeda255539de90780128476a8e954b17f3cf"],"state_sha256":"e8ed86914cf7a22c8ecdb118565e4f080a051d283cc47ba29d932eb9f4ded35f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jYnlD2UJGwteORqa9ANgw0bijdjj18Yle20lJcCmoGMU8QbNT2j2ujhG3wECgmieQk34NbnYwU6YZxTfm10BAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:51:21.948556Z","bundle_sha256":"d59b4ae8a3f33ae72b92f4a7c7a989b98e9b652530b77864b8dd745c4a2e1608"}}