{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ECXIKAU3MPTKEPGB5ETCOCDAFL","short_pith_number":"pith:ECXIKAU3","canonical_record":{"source":{"id":"2202.07925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T08:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"f1a8747fe02ee69df49154a279539e5d1330c7a17729ebd638d2d2ec2d42eabb","abstract_canon_sha256":"de1c514bfd145152af84feef2a9dc0012857e0f0f958671dcbff01c282aba818"},"schema_version":"1.0"},"canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","source":{"kind":"arxiv","id":"2202.07925","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07925","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07925v2","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07925","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"pith_short_12","alias_value":"ECXIKAU3MPTK","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"pith_short_16","alias_value":"ECXIKAU3MPTKEPGB","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"pith_short_8","alias_value":"ECXIKAU3","created_at":"2026-07-05T04:51:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ECXIKAU3MPTKEPGB5ETCOCDAFL","target":"record","payload":{"canonical_record":{"source":{"id":"2202.07925","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T08:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"f1a8747fe02ee69df49154a279539e5d1330c7a17729ebd638d2d2ec2d42eabb","abstract_canon_sha256":"de1c514bfd145152af84feef2a9dc0012857e0f0f958671dcbff01c282aba818"},"schema_version":"1.0"},"canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:55.135608Z","signature_b64":"hcM/odsx8X/gZ1V2HbYrD5SF9+Zblz3VtosiM+0dLPtRn1F076pWTq/QZEkhe+4TMN3a7US1s4IvVls90BeiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","last_reissued_at":"2026-07-05T04:51:55.135163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:55.135163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.07925","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":"2026-07-05T04:51:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o6tQkIWLZACVJjSfE43m//9coDWAIYSj3eHF+RwtR3+Y+/NOs3nDNJHMqZCMGjQzeOCDizUXtGMEJ4zHLR+JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:59:36.591246Z"},"content_sha256":"4b93b9dfc72481f37f229d8c11e8d82b01be6eb1dfc15ef2592d6278691a66cc","schema_version":"1.0","event_id":"sha256:4b93b9dfc72481f37f229d8c11e8d82b01be6eb1dfc15ef2592d6278691a66cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ECXIKAU3MPTKEPGB5ETCOCDAFL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ActionFormer: Localizing Moments of Actions with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlin Zhang, Jianxin Wu, Yin Li","submitted_at":"2022-02-16T08:34:11Z","abstract_excerpt":"Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer -- a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07925","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/2202.07925/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":"2026-07-05T04:51:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FdLPqXeqALThfdNGF+BkJp3UZG607r3TfoYb0O5TeDpW7m2eMrg4QecJJGi/78AZIr1a4r2uVoQfsVZCtW6XDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:59:36.591732Z"},"content_sha256":"b56aaf78b6df948a2ae0b872532821efb76798ddfdce0aa7e1ae20cdfb20091b","schema_version":"1.0","event_id":"sha256:b56aaf78b6df948a2ae0b872532821efb76798ddfdce0aa7e1ae20cdfb20091b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/bundle.json","state_url":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/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":"2026-08-09T13:59:36Z","links":{"resolver":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL","bundle":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/bundle.json","state":"https://pith.science/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECXIKAU3MPTKEPGB5ETCOCDAFL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ECXIKAU3MPTKEPGB5ETCOCDAFL","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":"de1c514bfd145152af84feef2a9dc0012857e0f0f958671dcbff01c282aba818","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T08:34:11Z","title_canon_sha256":"f1a8747fe02ee69df49154a279539e5d1330c7a17729ebd638d2d2ec2d42eabb"},"schema_version":"1.0","source":{"id":"2202.07925","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07925","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07925v2","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07925","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"pith_short_12","alias_value":"ECXIKAU3MPTK","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"pith_short_16","alias_value":"ECXIKAU3MPTKEPGB","created_at":"2026-07-05T04:51:55Z"},{"alias_kind":"pith_short_8","alias_value":"ECXIKAU3","created_at":"2026-07-05T04:51:55Z"}],"graph_snapshots":[{"event_id":"sha256:b56aaf78b6df948a2ae0b872532821efb76798ddfdce0aa7e1ae20cdfb20091b","target":"graph","created_at":"2026-07-05T04:51:55Z","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/2202.07925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer -- a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and u","authors_text":"Chenlin Zhang, Jianxin Wu, Yin Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T08:34:11Z","title":"ActionFormer: Localizing Moments of Actions with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07925","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":"sha256:4b93b9dfc72481f37f229d8c11e8d82b01be6eb1dfc15ef2592d6278691a66cc","target":"record","created_at":"2026-07-05T04:51:55Z","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":"de1c514bfd145152af84feef2a9dc0012857e0f0f958671dcbff01c282aba818","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-16T08:34:11Z","title_canon_sha256":"f1a8747fe02ee69df49154a279539e5d1330c7a17729ebd638d2d2ec2d42eabb"},"schema_version":"1.0","source":{"id":"2202.07925","kind":"arxiv","version":2}},"canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20ae85029b63e6a23cc1e9262708602aeef585966fa7019f55acc84713864016","first_computed_at":"2026-07-05T04:51:55.135163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:55.135163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hcM/odsx8X/gZ1V2HbYrD5SF9+Zblz3VtosiM+0dLPtRn1F076pWTq/QZEkhe+4TMN3a7US1s4IvVls90BeiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:55.135608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.07925","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b93b9dfc72481f37f229d8c11e8d82b01be6eb1dfc15ef2592d6278691a66cc","sha256:b56aaf78b6df948a2ae0b872532821efb76798ddfdce0aa7e1ae20cdfb20091b"],"state_sha256":"609fc19d7277eb66b1e9df224012e2f90285d6c3a696121ce87edc2cd884dd87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCQ0Oa8A2dmN1x2aNUZiD1BvXmYF8rnR5BO2PUs2xcDY+kRlFGM66ZyPRRc5VTP1vnYSdvYLOtnpX1IVe1iJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:59:36.595366Z","bundle_sha256":"bfb523d3ea0701207412590d22ab880772a00f7e61eeb310cdb05f24cb1acd7c"}}