{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MO4C4JLBU7IP4KANAUTPYMRQSO","short_pith_number":"pith:MO4C4JLB","canonical_record":{"source":{"id":"2509.08519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T11:54:29Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"22d0f863f2160abcb9ba4068ad65b51bd652f6b0acf282b70a8696b26984f2d7","abstract_canon_sha256":"be72d0828be92037c1fb1d108c9dee8cfc3f619d210b54a44de8e00db1da5751"},"schema_version":"1.0"},"canonical_sha256":"63b82e2561a7d0fe280d0526fc323093ba119593431e1dee3e298955c86dccf9","source":{"kind":"arxiv","id":"2509.08519","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08519","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08519v1","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08519","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"MO4C4JLBU7IP","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"MO4C4JLBU7IP4KAN","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"MO4C4JLB","created_at":"2026-07-05T12:08:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MO4C4JLBU7IP4KANAUTPYMRQSO","target":"record","payload":{"canonical_record":{"source":{"id":"2509.08519","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T11:54:29Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"22d0f863f2160abcb9ba4068ad65b51bd652f6b0acf282b70a8696b26984f2d7","abstract_canon_sha256":"be72d0828be92037c1fb1d108c9dee8cfc3f619d210b54a44de8e00db1da5751"},"schema_version":"1.0"},"canonical_sha256":"63b82e2561a7d0fe280d0526fc323093ba119593431e1dee3e298955c86dccf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:31.625922Z","signature_b64":"goaRbj8j/+HVrCp/HVNWjiIZg6YegV273PboyMINNN017WWnmp9C2oCGPIHpIrz8Dqt875VB/VNiJOUCBpNYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b82e2561a7d0fe280d0526fc323093ba119593431e1dee3e298955c86dccf9","last_reissued_at":"2026-07-05T12:08:31.625452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:31.625452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.08519","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":"2026-07-05T12:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fk8VdSf2o6ZFnLbWJaKkdS1m0i1LvvLB0a1j6ubMFzePPGR+MkR6joMsDws3DfpHOAIz5YDLRKaozK5y5zTfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:14:41.901930Z"},"content_sha256":"43417a7342910323cf8419efc94fc5b15ade504d89bce0481ea2cbf052811fe1","schema_version":"1.0","event_id":"sha256:43417a7342910323cf8419efc94fc5b15ade504d89bce0481ea2cbf052811fe1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MO4C4JLBU7IP4KANAUTPYMRQSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bingchuan Li, Gen Li, Jiawei Liu, Lijie Liu, Liyang Chen, Qian He, Tianxiang Ma, Xu He, Zhiyong Wu, Zhuowei Chen","submitted_at":"2025-09-10T11:54:29Z","abstract_excerpt":"Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two challenges: the scarcity of training data with paired triplet conditions and the difficulty of collaborating the sub-tasks of subject preservation and audio-visual sync with multimodal inputs. In this work, we present HuMo, a unified HCVG framework for collaborative multimodal control. For the first challenge, we construct a high-quality dataset with diverse and paire"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08519","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/2509.08519/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":"2026-07-05T12:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGzVfuqMiqk4a8dSjN1nmPT5Al0PU0ZvJ20RMYMl/p/IltugBXepnLZ0WpeQ6i2S/bxnwN4XyRzpcAT0YiApAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T06:14:41.902310Z"},"content_sha256":"4b5075f3789e41987df624403faf32547a1e76f08e4d8ad2c0ffd0c214703cce","schema_version":"1.0","event_id":"sha256:4b5075f3789e41987df624403faf32547a1e76f08e4d8ad2c0ffd0c214703cce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MO4C4JLBU7IP4KANAUTPYMRQSO/bundle.json","state_url":"https://pith.science/pith/MO4C4JLBU7IP4KANAUTPYMRQSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MO4C4JLBU7IP4KANAUTPYMRQSO/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":"2026-07-25T06:14:41Z","links":{"resolver":"https://pith.science/pith/MO4C4JLBU7IP4KANAUTPYMRQSO","bundle":"https://pith.science/pith/MO4C4JLBU7IP4KANAUTPYMRQSO/bundle.json","state":"https://pith.science/pith/MO4C4JLBU7IP4KANAUTPYMRQSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MO4C4JLBU7IP4KANAUTPYMRQSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MO4C4JLBU7IP4KANAUTPYMRQSO","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":"be72d0828be92037c1fb1d108c9dee8cfc3f619d210b54a44de8e00db1da5751","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T11:54:29Z","title_canon_sha256":"22d0f863f2160abcb9ba4068ad65b51bd652f6b0acf282b70a8696b26984f2d7"},"schema_version":"1.0","source":{"id":"2509.08519","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08519","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08519v1","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08519","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"MO4C4JLBU7IP","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"MO4C4JLBU7IP4KAN","created_at":"2026-07-05T12:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"MO4C4JLB","created_at":"2026-07-05T12:08:31Z"}],"graph_snapshots":[{"event_id":"sha256:4b5075f3789e41987df624403faf32547a1e76f08e4d8ad2c0ffd0c214703cce","target":"graph","created_at":"2026-07-05T12:08:31Z","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/2509.08519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human-Centric Video Generation (HCVG) methods seek to synthesize human videos from multimodal inputs, including text, image, and audio. Existing methods struggle to effectively coordinate these heterogeneous modalities due to two challenges: the scarcity of training data with paired triplet conditions and the difficulty of collaborating the sub-tasks of subject preservation and audio-visual sync with multimodal inputs. In this work, we present HuMo, a unified HCVG framework for collaborative multimodal control. For the first challenge, we construct a high-quality dataset with diverse and paire","authors_text":"Bingchuan Li, Gen Li, Jiawei Liu, Lijie Liu, Liyang Chen, Qian He, Tianxiang Ma, Xu He, Zhiyong Wu, Zhuowei Chen","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T11:54:29Z","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08519","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":"sha256:43417a7342910323cf8419efc94fc5b15ade504d89bce0481ea2cbf052811fe1","target":"record","created_at":"2026-07-05T12:08:31Z","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":"be72d0828be92037c1fb1d108c9dee8cfc3f619d210b54a44de8e00db1da5751","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T11:54:29Z","title_canon_sha256":"22d0f863f2160abcb9ba4068ad65b51bd652f6b0acf282b70a8696b26984f2d7"},"schema_version":"1.0","source":{"id":"2509.08519","kind":"arxiv","version":1}},"canonical_sha256":"63b82e2561a7d0fe280d0526fc323093ba119593431e1dee3e298955c86dccf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b82e2561a7d0fe280d0526fc323093ba119593431e1dee3e298955c86dccf9","first_computed_at":"2026-07-05T12:08:31.625452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:31.625452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"goaRbj8j/+HVrCp/HVNWjiIZg6YegV273PboyMINNN017WWnmp9C2oCGPIHpIrz8Dqt875VB/VNiJOUCBpNYCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:31.625922Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08519","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43417a7342910323cf8419efc94fc5b15ade504d89bce0481ea2cbf052811fe1","sha256:4b5075f3789e41987df624403faf32547a1e76f08e4d8ad2c0ffd0c214703cce"],"state_sha256":"2d1143952b5fae36a00e03de85d7c3eed0e6c45baaee4f74d12a52eff22b9597"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VjudYV5hMuyO46D4oPnFtgMnDiSIVz+NfGZNuPQvivMDdI5pTWlEu9DeArZ7eiq4WNqjPSM3PH4NKxJCNRcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T06:14:41.904486Z","bundle_sha256":"3412992c1ca1ada924094777980b8fecdf1dd155772ce03fe49e73b585a2d52a"}}