{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:H3YFV675ODGUIWBXOAL77CMCBF","short_pith_number":"pith:H3YFV675","canonical_record":{"source":{"id":"2203.05156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T05:03:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"747a74a17251fca2fd057903ea56ea291dee4da7fa1247789acab494158fb32c","abstract_canon_sha256":"d832b2b77cb210787630375f0435b8671e274e98b0eb5930f603561ceb412973"},"schema_version":"1.0"},"canonical_sha256":"3ef05afbfd70cd4458377017ff898209417319a9293c525a8d2c4257998fe4dc","source":{"kind":"arxiv","id":"2203.05156","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.05156","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.05156v2","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05156","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"H3YFV675ODGU","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"H3YFV675ODGUIWBX","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"H3YFV675","created_at":"2026-07-05T05:21:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:H3YFV675ODGUIWBXOAL77CMCBF","target":"record","payload":{"canonical_record":{"source":{"id":"2203.05156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T05:03:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"747a74a17251fca2fd057903ea56ea291dee4da7fa1247789acab494158fb32c","abstract_canon_sha256":"d832b2b77cb210787630375f0435b8671e274e98b0eb5930f603561ceb412973"},"schema_version":"1.0"},"canonical_sha256":"3ef05afbfd70cd4458377017ff898209417319a9293c525a8d2c4257998fe4dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:40.946220Z","signature_b64":"P8JrUeZYbltaUB8bCOlSGJOIJL7bkRvXz+jF+SRLKfLGrwcv/63pahwRbfWFBhqlw22Oxp5lKdJ7BPVPJF76Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ef05afbfd70cd4458377017ff898209417319a9293c525a8d2c4257998fe4dc","last_reissued_at":"2026-07-05T05:21:40.945815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:40.945815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.05156","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":"2026-07-05T05:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6e02ZZdmHXvZPQBKtvyYyCu6OHQsOfJd60DtDfADPTnZTbrEb1+qiUGrmVftF+R9eXEjFQbgzwH/HPPfLblDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:02:33.514306Z"},"content_sha256":"57127a177fbc0c651e1a2901b6a0cf5e53f90c2f689c9e979b13a8b910815fd4","schema_version":"1.0","event_id":"sha256:57127a177fbc0c651e1a2901b6a0cf5e53f90c2f689c9e979b13a8b910815fd4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:H3YFV675ODGUIWBXOAL77CMCBF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Semantic Video Transformer for Zero-Shot Action Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Keval Doshi, Yasin Yilmaz","submitted_at":"2022-03-10T05:03:58Z","abstract_excerpt":"While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is capable of capturing long range spatiotemporal dependencies efficiently, contrary to existing approaches which use 3D-CNNs. Moreover, to address a common ambiguity in the existing works about classes that can be considered as previously unseen, we propose a new experimentation setup that satisfies the zero-shot learning premise for action recognition by avoidi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05156","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.05156/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":"2026-07-05T05:21:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWaqQ49Mi0qwnz+9F+2AWvYbYeSMKw0BJpgq3cmLDhKAGaahFkNfxqfaAEc0QK0nAq8KxfE6QSAu/GzOGOuvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T02:02:33.514818Z"},"content_sha256":"28b74db6ecea2e26ea0d9181977b65eaf6bdbac4d678db67315424f6360d3aea","schema_version":"1.0","event_id":"sha256:28b74db6ecea2e26ea0d9181977b65eaf6bdbac4d678db67315424f6360d3aea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H3YFV675ODGUIWBXOAL77CMCBF/bundle.json","state_url":"https://pith.science/pith/H3YFV675ODGUIWBXOAL77CMCBF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H3YFV675ODGUIWBXOAL77CMCBF/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":"2026-08-23T02:02:33Z","links":{"resolver":"https://pith.science/pith/H3YFV675ODGUIWBXOAL77CMCBF","bundle":"https://pith.science/pith/H3YFV675ODGUIWBXOAL77CMCBF/bundle.json","state":"https://pith.science/pith/H3YFV675ODGUIWBXOAL77CMCBF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H3YFV675ODGUIWBXOAL77CMCBF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:H3YFV675ODGUIWBXOAL77CMCBF","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":"d832b2b77cb210787630375f0435b8671e274e98b0eb5930f603561ceb412973","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T05:03:58Z","title_canon_sha256":"747a74a17251fca2fd057903ea56ea291dee4da7fa1247789acab494158fb32c"},"schema_version":"1.0","source":{"id":"2203.05156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.05156","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.05156v2","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05156","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"pith_short_12","alias_value":"H3YFV675ODGU","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"pith_short_16","alias_value":"H3YFV675ODGUIWBX","created_at":"2026-07-05T05:21:40Z"},{"alias_kind":"pith_short_8","alias_value":"H3YFV675","created_at":"2026-07-05T05:21:40Z"}],"graph_snapshots":[{"event_id":"sha256:28b74db6ecea2e26ea0d9181977b65eaf6bdbac4d678db67315424f6360d3aea","target":"graph","created_at":"2026-07-05T05:21:40Z","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/2203.05156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While video action recognition has been an active area of research for several years, zero-shot action recognition has only recently started gaining traction. In this work, we propose a novel end-to-end trained transformer model which is capable of capturing long range spatiotemporal dependencies efficiently, contrary to existing approaches which use 3D-CNNs. Moreover, to address a common ambiguity in the existing works about classes that can be considered as previously unseen, we propose a new experimentation setup that satisfies the zero-shot learning premise for action recognition by avoidi","authors_text":"Keval Doshi, Yasin Yilmaz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T05:03:58Z","title":"End-to-End Semantic Video Transformer for Zero-Shot Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05156","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":"sha256:57127a177fbc0c651e1a2901b6a0cf5e53f90c2f689c9e979b13a8b910815fd4","target":"record","created_at":"2026-07-05T05:21:40Z","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":"d832b2b77cb210787630375f0435b8671e274e98b0eb5930f603561ceb412973","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T05:03:58Z","title_canon_sha256":"747a74a17251fca2fd057903ea56ea291dee4da7fa1247789acab494158fb32c"},"schema_version":"1.0","source":{"id":"2203.05156","kind":"arxiv","version":2}},"canonical_sha256":"3ef05afbfd70cd4458377017ff898209417319a9293c525a8d2c4257998fe4dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ef05afbfd70cd4458377017ff898209417319a9293c525a8d2c4257998fe4dc","first_computed_at":"2026-07-05T05:21:40.945815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:40.945815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P8JrUeZYbltaUB8bCOlSGJOIJL7bkRvXz+jF+SRLKfLGrwcv/63pahwRbfWFBhqlw22Oxp5lKdJ7BPVPJF76Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:40.946220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.05156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57127a177fbc0c651e1a2901b6a0cf5e53f90c2f689c9e979b13a8b910815fd4","sha256:28b74db6ecea2e26ea0d9181977b65eaf6bdbac4d678db67315424f6360d3aea"],"state_sha256":"ad19ac319280ad6f0e57fc36ed8cd707bb1ba3dfb6dedb839853c4d52f14e4ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iJKnjFfwQMjNf4ck++wMACxANp614RB69xio4YlgcEOqzfuury/WPUCD/a8kC4G4WlYR9nV8fjNeN9JxJeu6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T02:02:33.519961Z","bundle_sha256":"a1fd5a188a3e9af27d2a11791dd7de97c642a3804702173b548ecc6c8b6752df"}}