{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3XJBEESSWTKPH6NUYFJLQWDNCD","short_pith_number":"pith:3XJBEESS","canonical_record":{"source":{"id":"2504.18152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T08:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"155b70e552149a47e3c60786f9d30dd76f3df8b86400b1dc2e6c8abf73a9c679","abstract_canon_sha256":"1b913c97280235fcf7bd3a21acad7fd5c8c8aff1cac8164e3944cda47f00ef12"},"schema_version":"1.0"},"canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","source":{"kind":"arxiv","id":"2504.18152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18152","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18152v1","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18152","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"3XJBEESSWTKP","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"3XJBEESSWTKPH6NU","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"3XJBEESS","created_at":"2026-07-05T10:54:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3XJBEESSWTKPH6NUYFJLQWDNCD","target":"record","payload":{"canonical_record":{"source":{"id":"2504.18152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T08:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"155b70e552149a47e3c60786f9d30dd76f3df8b86400b1dc2e6c8abf73a9c679","abstract_canon_sha256":"1b913c97280235fcf7bd3a21acad7fd5c8c8aff1cac8164e3944cda47f00ef12"},"schema_version":"1.0"},"canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:02.806284Z","signature_b64":"8/Y6coE4NYM51fjVQmXDipWhnwNB8qij/WKszIrA2t06mVG6Z4DRHfmMYzUenrWimgPlAlPdLtJRIC0w4z+fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","last_reissued_at":"2026-07-05T10:54:02.805840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:02.805840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.18152","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":"2026-07-05T10:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6wqTWTqVSmmdLfGh8aDxnzAKOSIZBGvdK4XDVvIRWJ3mvKxB2/kZL6Wz8Ypn0S+BCg2todzeNjwQ8b/pCB5qBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:07:23.353559Z"},"content_sha256":"754f99352ba592693f60862c8d32475675cc06725315d6d8d2705c5dd281375d","schema_version":"1.0","event_id":"sha256:754f99352ba592693f60862c8d32475675cc06725315d6d8d2705c5dd281375d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3XJBEESSWTKPH6NUYFJLQWDNCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kun-Yu Lin, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xihan Wei, Yi-Xing Peng, Yu-Ming Tang","submitted_at":"2025-04-25T08:05:32Z","abstract_excerpt":"Fine-grained understanding of human actions and poses in videos is essential for human-centric AI applications. In this work, we introduce ActionArt, a fine-grained video-caption dataset designed to advance research in human-centric multimodal understanding. Our dataset comprises thousands of videos capturing a broad spectrum of human actions, human-object interactions, and diverse scenarios, each accompanied by detailed annotations that meticulously label every limb movement. We develop eight sub-tasks to evaluate the fine-grained understanding capabilities of existing large multimodal models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18152","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/2504.18152/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":"2026-07-05T10:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C88eURz5d4Xu8K8k3pbNS/QnrMSDCTXoY/zjBuTrI9TdPU61kqydgc9WWyCvs+HRNRwP12vqCVAlVGPKLVQgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:07:23.354048Z"},"content_sha256":"c54609bf41c5dc3498f027367421d9a6a6f8ff1842c8dabbf015cd102bbfe489","schema_version":"1.0","event_id":"sha256:c54609bf41c5dc3498f027367421d9a6a6f8ff1842c8dabbf015cd102bbfe489"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/bundle.json","state_url":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/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":"2026-08-05T07:07:23Z","links":{"resolver":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD","bundle":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/bundle.json","state":"https://pith.science/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XJBEESSWTKPH6NUYFJLQWDNCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3XJBEESSWTKPH6NUYFJLQWDNCD","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":"1b913c97280235fcf7bd3a21acad7fd5c8c8aff1cac8164e3944cda47f00ef12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T08:05:32Z","title_canon_sha256":"155b70e552149a47e3c60786f9d30dd76f3df8b86400b1dc2e6c8abf73a9c679"},"schema_version":"1.0","source":{"id":"2504.18152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18152","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18152v1","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18152","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"3XJBEESSWTKP","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"3XJBEESSWTKPH6NU","created_at":"2026-07-05T10:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"3XJBEESS","created_at":"2026-07-05T10:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:c54609bf41c5dc3498f027367421d9a6a6f8ff1842c8dabbf015cd102bbfe489","target":"graph","created_at":"2026-07-05T10:54:02Z","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/2504.18152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained understanding of human actions and poses in videos is essential for human-centric AI applications. In this work, we introduce ActionArt, a fine-grained video-caption dataset designed to advance research in human-centric multimodal understanding. Our dataset comprises thousands of videos capturing a broad spectrum of human actions, human-object interactions, and diverse scenarios, each accompanied by detailed annotations that meticulously label every limb movement. We develop eight sub-tasks to evaluate the fine-grained understanding capabilities of existing large multimodal models","authors_text":"Kun-Yu Lin, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xihan Wei, Yi-Xing Peng, Yu-Ming Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T08:05:32Z","title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18152","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":"sha256:754f99352ba592693f60862c8d32475675cc06725315d6d8d2705c5dd281375d","target":"record","created_at":"2026-07-05T10:54:02Z","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":"1b913c97280235fcf7bd3a21acad7fd5c8c8aff1cac8164e3944cda47f00ef12","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T08:05:32Z","title_canon_sha256":"155b70e552149a47e3c60786f9d30dd76f3df8b86400b1dc2e6c8abf73a9c679"},"schema_version":"1.0","source":{"id":"2504.18152","kind":"arxiv","version":1}},"canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddd2121252b4d4f3f9b4c152b8586d10de6863eb93a27eb9bc1150aac7a202d2","first_computed_at":"2026-07-05T10:54:02.805840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:02.805840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/Y6coE4NYM51fjVQmXDipWhnwNB8qij/WKszIrA2t06mVG6Z4DRHfmMYzUenrWimgPlAlPdLtJRIC0w4z+fDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:02.806284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:754f99352ba592693f60862c8d32475675cc06725315d6d8d2705c5dd281375d","sha256:c54609bf41c5dc3498f027367421d9a6a6f8ff1842c8dabbf015cd102bbfe489"],"state_sha256":"1e9b263c2194879d9a729af761ecb16bc1ddc156bf6ac8f3a3831d94f2c8791a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZWCqB9auyVer7QgIp4NGh8QVFlGFSyQ4VWo9VZ8I9pAThOXF4tVaJmGi2SAK+7k4QlL/rr2UnIYuk1ODr41Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:07:23.357567Z","bundle_sha256":"48daf945c34c2598f1897b1839b8eee9711dcbee791d5582c2ca68287c22e59f"}}