{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQ7TYUZ4G4L2T6B3QP3B5AN22C","short_pith_number":"pith:ZQ7TYUZ4","schema_version":"1.0","canonical_sha256":"cc3f3c533c3717a9f83b83f61e81bad0a74bf3894ddf25afd37477ae2a65820b","source":{"kind":"arxiv","id":"2502.20811","version":2},"attestation_state":"computed","paper":{"title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Fuzheng Zhang, Jianlong Wu, Jingyun Hua, Liqiang Nie, Weihong Lin, Xiao Wang, Yuanxing Zhang","submitted_at":"2025-02-28T07:53:40Z","abstract_excerpt":"Recent Multi-modal Large Language Models (MLLMs) have made great progress in video understanding. However, their performance on videos involving human actions is still limited by the lack of high-quality data. To address this, we introduce a two-stage data annotation pipeline. First, we design strategies to accumulate videos featuring clear human actions from the Internet. Second, videos are annotated in a standardized caption format that uses human attributes to distinguish individuals and chronologically details their actions and interactions. Through this pipeline, we curate two datasets, n"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.20811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T07:53:40Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"6382b07e92a103d10d00d352c6fb314cd4a10cfd38c8f0e2df30d1a06cd93e0b","abstract_canon_sha256":"97ca59213508d26ed5e46fba96e4ec32bca3891e4296795cbf31ec3234190a2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:42.267752Z","signature_b64":"B1ZGU5JoqQGw1p6xOdDT53EhoTOBBOO3XsEM0HtOzPIOTBFrgNlRDnYNNdkMde38LoHsg102pYHJzezFVboGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3f3c533c3717a9f83b83f61e81bad0a74bf3894ddf25afd37477ae2a65820b","last_reissued_at":"2026-07-05T11:17:42.267258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:42.267258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Di Zhang, Fuzheng Zhang, Jianlong Wu, Jingyun Hua, Liqiang Nie, Weihong Lin, Xiao Wang, Yuanxing Zhang","submitted_at":"2025-02-28T07:53:40Z","abstract_excerpt":"Recent Multi-modal Large Language Models (MLLMs) have made great progress in video understanding. However, their performance on videos involving human actions is still limited by the lack of high-quality data. To address this, we introduce a two-stage data annotation pipeline. First, we design strategies to accumulate videos featuring clear human actions from the Internet. Second, videos are annotated in a standardized caption format that uses human attributes to distinguish individuals and chronologically details their actions and interactions. Through this pipeline, we curate two datasets, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20811","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/2502.20811/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.20811","created_at":"2026-07-05T11:17:42.267323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20811v2","created_at":"2026-07-05T11:17:42.267323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20811","created_at":"2026-07-05T11:17:42.267323+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ7TYUZ4G4L2","created_at":"2026-07-05T11:17:42.267323+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ7TYUZ4G4L2T6B3","created_at":"2026-07-05T11:17:42.267323+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ7TYUZ4","created_at":"2026-07-05T11:17:42.267323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C","json":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C.json","graph_json":"https://pith.science/api/pith-number/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/graph.json","events_json":"https://pith.science/api/pith-number/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/events.json","paper":"https://pith.science/paper/ZQ7TYUZ4"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C","download_json":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C.json","view_paper":"https://pith.science/paper/ZQ7TYUZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20811&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ7TYUZ4G4L2T6B3QP3B5AN22C/action/replication_record"}},"created_at":"2026-07-05T11:17:42.267323+00:00","updated_at":"2026-07-05T11:17:42.267323+00:00"}