{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IQQOOLWLTL77PPUQ3T2WWC7EAO","short_pith_number":"pith:IQQOOLWL","canonical_record":{"source":{"id":"2210.07503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:09:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d2e9a5381616f9ad84c48fcb58fae93d46d532eb66d12b4a9afc9ee1733dbbb","abstract_canon_sha256":"f423325550fe1badfd4d2d9b9360afe03c08bc9e50d0bc0dd216790421fb117e"},"schema_version":"1.0"},"canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","source":{"kind":"arxiv","id":"2210.07503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07503","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07503v1","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07503","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"pith_short_12","alias_value":"IQQOOLWLTL77","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"pith_short_16","alias_value":"IQQOOLWLTL77PPUQ","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"pith_short_8","alias_value":"IQQOOLWL","created_at":"2026-07-05T05:06:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IQQOOLWLTL77PPUQ3T2WWC7EAO","target":"record","payload":{"canonical_record":{"source":{"id":"2210.07503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:09:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0d2e9a5381616f9ad84c48fcb58fae93d46d532eb66d12b4a9afc9ee1733dbbb","abstract_canon_sha256":"f423325550fe1badfd4d2d9b9360afe03c08bc9e50d0bc0dd216790421fb117e"},"schema_version":"1.0"},"canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:37.976478Z","signature_b64":"wUD3pgDJe3G0DkootLkxq0h1hOUXG/tk/wVPl8FgOP4qMLQX7mO5iS+v/vz349gpMVtDbji1A3AxmpQGKsp+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","last_reissued_at":"2026-07-05T05:06:37.976059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:37.976059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.07503","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:06:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hk1nSsYwjiplthFpuZapAdSwtOs01fmTIRfdBZEGVUCvg2NKWVKN6E8tsEtIe1bDkF6LdQj5g7hoYSiQnV6KBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:54:15.282504Z"},"content_sha256":"d28e4feae616d662eb7ec15661c6f98781ec178c0c4a158200a0998d66c3b714","schema_version":"1.0","event_id":"sha256:d28e4feae616d662eb7ec15661c6f98781ec178c0c4a158200a0998d66c3b714"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IQQOOLWLTL77PPUQ3T2WWC7EAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Byoung Chul Ko, Dasom Ahn, Hyunsu Hong, Sangwon Kim","submitted_at":"2022-10-14T04:09:44Z","abstract_excerpt":"In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these problems, we propose Spatio-TemporAl cRoss (STAR)-transformer, which can effectively represent two cross-modal features as a recognizable vector. First, from the input video and skeleton sequence, video frames are output as global grid tokens and skeletons are output as joint map tokens, respectively. These tokens are then aggregated into multi-class tokens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07503","kind":"arxiv","version":1},"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/2210.07503/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":"2026-07-05T05:06:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76oaFQsDVaHLakJy0D/cpKkRsFxdj0i5tOWtKMZBLduUd6B+1h+P+g9LTX6tei/7r/Jq77oStn28IcxGH6+OBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:54:15.283092Z"},"content_sha256":"b640a6d0beaba732eb2e78789eb1905410e3654002264d8c84c6d66501c5f3a8","schema_version":"1.0","event_id":"sha256:b640a6d0beaba732eb2e78789eb1905410e3654002264d8c84c6d66501c5f3a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/bundle.json","state_url":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/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":"2026-08-15T19:54:15Z","links":{"resolver":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO","bundle":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/bundle.json","state":"https://pith.science/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQQOOLWLTL77PPUQ3T2WWC7EAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IQQOOLWLTL77PPUQ3T2WWC7EAO","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":"f423325550fe1badfd4d2d9b9360afe03c08bc9e50d0bc0dd216790421fb117e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:09:44Z","title_canon_sha256":"0d2e9a5381616f9ad84c48fcb58fae93d46d532eb66d12b4a9afc9ee1733dbbb"},"schema_version":"1.0","source":{"id":"2210.07503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07503","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07503v1","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07503","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"pith_short_12","alias_value":"IQQOOLWLTL77","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"pith_short_16","alias_value":"IQQOOLWLTL77PPUQ","created_at":"2026-07-05T05:06:37Z"},{"alias_kind":"pith_short_8","alias_value":"IQQOOLWL","created_at":"2026-07-05T05:06:37Z"}],"graph_snapshots":[{"event_id":"sha256:b640a6d0beaba732eb2e78789eb1905410e3654002264d8c84c6d66501c5f3a8","target":"graph","created_at":"2026-07-05T05:06:37Z","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/2210.07503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In action recognition, although the combination of spatio-temporal videos and skeleton features can improve the recognition performance, a separate model and balancing feature representation for cross-modal data are required. To solve these problems, we propose Spatio-TemporAl cRoss (STAR)-transformer, which can effectively represent two cross-modal features as a recognizable vector. First, from the input video and skeleton sequence, video frames are output as global grid tokens and skeletons are output as joint map tokens, respectively. These tokens are then aggregated into multi-class tokens","authors_text":"Byoung Chul Ko, Dasom Ahn, Hyunsu Hong, Sangwon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:09:44Z","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07503","kind":"arxiv","version":1},"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:d28e4feae616d662eb7ec15661c6f98781ec178c0c4a158200a0998d66c3b714","target":"record","created_at":"2026-07-05T05:06:37Z","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":"f423325550fe1badfd4d2d9b9360afe03c08bc9e50d0bc0dd216790421fb117e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T04:09:44Z","title_canon_sha256":"0d2e9a5381616f9ad84c48fcb58fae93d46d532eb66d12b4a9afc9ee1733dbbb"},"schema_version":"1.0","source":{"id":"2210.07503","kind":"arxiv","version":1}},"canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4420e72ecb9afff7be90dcf56b0be403bb348ac6468f1359b285defe0844e843","first_computed_at":"2026-07-05T05:06:37.976059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:37.976059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUD3pgDJe3G0DkootLkxq0h1hOUXG/tk/wVPl8FgOP4qMLQX7mO5iS+v/vz349gpMVtDbji1A3AxmpQGKsp+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:37.976478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28e4feae616d662eb7ec15661c6f98781ec178c0c4a158200a0998d66c3b714","sha256:b640a6d0beaba732eb2e78789eb1905410e3654002264d8c84c6d66501c5f3a8"],"state_sha256":"bbc468a899ebc472175324f02f581598e00bb6ccc539c563eb639982777e6842"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxePxXMkxq95ot9HcA34KBtuGQvX9n71tCgARNGxGXV64zx2+6jvBoE9C0Hb7zR3Y5WSAdo3u2SfrSvbALafAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:54:15.289286Z","bundle_sha256":"94ffe3af7536afd54220e48c28a51115ce72337f41a4af92ecd2564bda14cad2"}}