{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZQ7TYUZ4G4L2T6B3QP3B5AN22C","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":"97ca59213508d26ed5e46fba96e4ec32bca3891e4296795cbf31ec3234190a2f","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T07:53:40Z","title_canon_sha256":"6382b07e92a103d10d00d352c6fb314cd4a10cfd38c8f0e2df30d1a06cd93e0b"},"schema_version":"1.0","source":{"id":"2502.20811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20811","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20811v2","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20811","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_12","alias_value":"ZQ7TYUZ4G4L2","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_16","alias_value":"ZQ7TYUZ4G4L2T6B3","created_at":"2026-07-05T11:17:42Z"},{"alias_kind":"pith_short_8","alias_value":"ZQ7TYUZ4","created_at":"2026-07-05T11:17:42Z"}],"graph_snapshots":[{"event_id":"sha256:b65ea87ad24713cae3d380908696ff3bca4f9775cd704d4b1cf5156a5ede97e4","target":"graph","created_at":"2026-07-05T11:17:42Z","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/2502.20811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Di Zhang, Fuzheng Zhang, Jianlong Wu, Jingyun Hua, Liqiang Nie, Weihong Lin, Xiao Wang, Yuanxing Zhang","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T07:53:40Z","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20811","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":"sha256:056c457ca6495a7394fd8f4fbe7294da5b617da9df2bb4971f52011158675eeb","target":"record","created_at":"2026-07-05T11:17:42Z","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":"97ca59213508d26ed5e46fba96e4ec32bca3891e4296795cbf31ec3234190a2f","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-28T07:53:40Z","title_canon_sha256":"6382b07e92a103d10d00d352c6fb314cd4a10cfd38c8f0e2df30d1a06cd93e0b"},"schema_version":"1.0","source":{"id":"2502.20811","kind":"arxiv","version":2}},"canonical_sha256":"cc3f3c533c3717a9f83b83f61e81bad0a74bf3894ddf25afd37477ae2a65820b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc3f3c533c3717a9f83b83f61e81bad0a74bf3894ddf25afd37477ae2a65820b","first_computed_at":"2026-07-05T11:17:42.267258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:42.267258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B1ZGU5JoqQGw1p6xOdDT53EhoTOBBOO3XsEM0HtOzPIOTBFrgNlRDnYNNdkMde38LoHsg102pYHJzezFVboGAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:42.267752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:056c457ca6495a7394fd8f4fbe7294da5b617da9df2bb4971f52011158675eeb","sha256:b65ea87ad24713cae3d380908696ff3bca4f9775cd704d4b1cf5156a5ede97e4"],"state_sha256":"0b5fbd5e279794badd0e944894b5ebe61322f3a9019449d62b93c3fca049af7b"}