{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:Q6GQ533GQLAWKKIOO73VXIAVY7","short_pith_number":"pith:Q6GQ533G","canonical_record":{"source":{"id":"1812.02707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T18:42:25Z","cross_cats_sorted":[],"title_canon_sha256":"50fecd1e4e0f41d685aa540b664171d6e4d6e86c0817cee2424b82ec19f43a31","abstract_canon_sha256":"4c6ddbbaf5ad8e9ffbfb04d7f7e3edc6401757fdd6df97430aff694db5ad1d4c"},"schema_version":"1.0"},"canonical_sha256":"878d0eef6682c165290e77f75ba015c7ccf8c76cd3c6083b5b2645f4d2922bbb","source":{"kind":"arxiv","id":"1812.02707","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02707","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02707v2","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02707","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"Q6GQ533GQLAW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6GQ533GQLAWKKIO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6GQ533G","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:Q6GQ533GQLAWKKIOO73VXIAVY7","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T18:42:25Z","cross_cats_sorted":[],"title_canon_sha256":"50fecd1e4e0f41d685aa540b664171d6e4d6e86c0817cee2424b82ec19f43a31","abstract_canon_sha256":"4c6ddbbaf5ad8e9ffbfb04d7f7e3edc6401757fdd6df97430aff694db5ad1d4c"},"schema_version":"1.0"},"canonical_sha256":"878d0eef6682c165290e77f75ba015c7ccf8c76cd3c6083b5b2645f4d2922bbb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:56.593128Z","signature_b64":"W10QT5pr3Sg/d6zVrITu2prK2qScOalknHBo4+hMP91xzrYMlyueCkfsfo1P5Fa/7f/lHu9Tz6uEU6J2AVh3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"878d0eef6682c165290e77f75ba015c7ccf8c76cd3c6083b5b2645f4d2922bbb","last_reissued_at":"2026-05-17T23:45:56.592663Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:56.592663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02707","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcjsClHirdYraqQwWULjfzalHbb+w2t04PPsp3pc0AzC+nKjp44X2avBpnCg8By5igUN8tvX05fw5uqCxO7MCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:19:19.286402Z"},"content_sha256":"3ba7d8928026115955d8b8d091f72798095aa55889a565b0f31e7973e16c4e5c","schema_version":"1.0","event_id":"sha256:3ba7d8928026115955d8b8d091f72798095aa55889a565b0f31e7973e16c4e5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:Q6GQ533GQLAWKKIOO73VXIAVY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Action Transformer Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Carl Doersch, Jo\\~ao Carreira, Rohit Girdhar","submitted_at":"2018-12-06T18:42:25Z","abstract_excerpt":"We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we are trying to classify. We show that by using high-resolution, person-specific, class-agnostic queries, the model spontaneously learns to track individual people and to pick up on semantic context from the actions of others. Additionally its attention mechanism learns to emphasize hands and faces, which are often crucial to discriminate an action - all without"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02707","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTacCm6aNGx9TaKFL43953lr/G5xN48iuQE6BQ8prbx2SKKT+Xh8pTvcRrp60l9g56IyskoCGQWrHkW2vwnYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:19:19.286759Z"},"content_sha256":"fc494784b3aaa7ad132c77aa96c831a5ccfe980050b0c11704b23aeeb9876b8a","schema_version":"1.0","event_id":"sha256:fc494784b3aaa7ad132c77aa96c831a5ccfe980050b0c11704b23aeeb9876b8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6GQ533GQLAWKKIOO73VXIAVY7/bundle.json","state_url":"https://pith.science/pith/Q6GQ533GQLAWKKIOO73VXIAVY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6GQ533GQLAWKKIOO73VXIAVY7/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":"2026-05-30T13:19:19Z","links":{"resolver":"https://pith.science/pith/Q6GQ533GQLAWKKIOO73VXIAVY7","bundle":"https://pith.science/pith/Q6GQ533GQLAWKKIOO73VXIAVY7/bundle.json","state":"https://pith.science/pith/Q6GQ533GQLAWKKIOO73VXIAVY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6GQ533GQLAWKKIOO73VXIAVY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Q6GQ533GQLAWKKIOO73VXIAVY7","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":"4c6ddbbaf5ad8e9ffbfb04d7f7e3edc6401757fdd6df97430aff694db5ad1d4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T18:42:25Z","title_canon_sha256":"50fecd1e4e0f41d685aa540b664171d6e4d6e86c0817cee2424b82ec19f43a31"},"schema_version":"1.0","source":{"id":"1812.02707","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02707","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02707v2","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02707","created_at":"2026-05-17T23:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"Q6GQ533GQLAW","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6GQ533GQLAWKKIO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6GQ533G","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:fc494784b3aaa7ad132c77aa96c831a5ccfe980050b0c11704b23aeeb9876b8a","target":"graph","created_at":"2026-05-17T23:45:56Z","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"},"paper":{"abstract_excerpt":"We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we are trying to classify. We show that by using high-resolution, person-specific, class-agnostic queries, the model spontaneously learns to track individual people and to pick up on semantic context from the actions of others. Additionally its attention mechanism learns to emphasize hands and faces, which are often crucial to discriminate an action - all without","authors_text":"Andrew Zisserman, Carl Doersch, Jo\\~ao Carreira, Rohit Girdhar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T18:42:25Z","title":"Video Action Transformer Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02707","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":"sha256:3ba7d8928026115955d8b8d091f72798095aa55889a565b0f31e7973e16c4e5c","target":"record","created_at":"2026-05-17T23:45:56Z","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":"4c6ddbbaf5ad8e9ffbfb04d7f7e3edc6401757fdd6df97430aff694db5ad1d4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-06T18:42:25Z","title_canon_sha256":"50fecd1e4e0f41d685aa540b664171d6e4d6e86c0817cee2424b82ec19f43a31"},"schema_version":"1.0","source":{"id":"1812.02707","kind":"arxiv","version":2}},"canonical_sha256":"878d0eef6682c165290e77f75ba015c7ccf8c76cd3c6083b5b2645f4d2922bbb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"878d0eef6682c165290e77f75ba015c7ccf8c76cd3c6083b5b2645f4d2922bbb","first_computed_at":"2026-05-17T23:45:56.592663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:56.592663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W10QT5pr3Sg/d6zVrITu2prK2qScOalknHBo4+hMP91xzrYMlyueCkfsfo1P5Fa/7f/lHu9Tz6uEU6J2AVh3Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:56.593128Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02707","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ba7d8928026115955d8b8d091f72798095aa55889a565b0f31e7973e16c4e5c","sha256:fc494784b3aaa7ad132c77aa96c831a5ccfe980050b0c11704b23aeeb9876b8a"],"state_sha256":"34977500e7b2f9f97996da3b0e367da09d03ed38de84f39f6de497f068cc3403"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0gMnAV3IPc7igZiofpAofjTtXfHsjd2/F25DGaiqq8Znzat1dZJsOGBe5W+nTRhqcFWDcf9JNrncwh9sW/S0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:19:19.288793Z","bundle_sha256":"638c225990d230421eafc42567c05f7fc68c604341bb8d639a7f6070c0aa488a"}}