{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M362KP5LHBM65DAHDDVX7ZCV46","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":"8c1e739e6cf77b7687c121441484abab7b9516ef4add91df0e4c1951995e19a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T07:26:37Z","title_canon_sha256":"3ea99b694cae0e6d4885a13829950295c6f08ef6ff43b6316e28247dc1d5184a"},"schema_version":"1.0","source":{"id":"2501.15111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15111","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15111v1","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15111","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"M362KP5LHBM6","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"M362KP5LHBM65DAH","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"M362KP5L","created_at":"2026-07-05T10:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:586b831353ebff8af4c701c8afab090899678bd7066904f18de3020862201ef6","target":"graph","created_at":"2026-07-05T10:05:24Z","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/2501.15111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In human-centric scenes, the ability to simultaneously understand visual and auditory information is crucial. While recent omni models can process multiple modalities, they generally lack effectiveness in human-centric scenes due to the absence of large-scale, specialized datasets and non-targeted architectures. In this work, we developed HumanOmni, the industry's first human-centric Omni-multimodal large language model. We constructed a dataset containing over 2.4 million human-centric video clips with detailed captions and more than 14 million instructions, facilitating the understanding of ","authors_text":"Boyuan Sun, Detao Bai, Jiaxing Zhao, Liefeng Bo, Qize Yang, Shenghao Fu, Shimin Yao, Weixuan Chen, Xiang Chen, Xihan Wei, Yixing Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T07:26:37Z","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15111","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":"sha256:054b8c12326180dfc91f716324ac1fb75d8948e1c9ed6615c786a1c7d9714e98","target":"record","created_at":"2026-07-05T10:05:24Z","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":"8c1e739e6cf77b7687c121441484abab7b9516ef4add91df0e4c1951995e19a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T07:26:37Z","title_canon_sha256":"3ea99b694cae0e6d4885a13829950295c6f08ef6ff43b6316e28247dc1d5184a"},"schema_version":"1.0","source":{"id":"2501.15111","kind":"arxiv","version":1}},"canonical_sha256":"66fda53fab3859ee8c0718eb7fe455e790f45d67c9e5d612955d014694808561","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66fda53fab3859ee8c0718eb7fe455e790f45d67c9e5d612955d014694808561","first_computed_at":"2026-07-05T10:05:24.595994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:24.595994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qrflf0u/CqEX/9mYsh7c23LiMfAQEIttQzrQ0jIEX7PEcVEdgl2fA508N3Gu9/Zx/6g604+oEFMoNBl9/QUvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:24.596562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:054b8c12326180dfc91f716324ac1fb75d8948e1c9ed6615c786a1c7d9714e98","sha256:586b831353ebff8af4c701c8afab090899678bd7066904f18de3020862201ef6"],"state_sha256":"77b6f65c11a9ec2eb86d8efcdba48008a00cd34fad8bc845108d99ecf3e7a99e"}