{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LFBL7LP6PZXNDQT3VS75XECXOX","short_pith_number":"pith:LFBL7LP6","canonical_record":{"source":{"id":"2503.19824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:38:23Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"a2235bfd78ac8966ca0366923635b5a9c1e0c3ff70b11207520b9738451da9cc","abstract_canon_sha256":"8ac7676c32cb3ed6a8f8d864b867bf9056d4b9209899b7810b89f51db2690020"},"schema_version":"1.0"},"canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","source":{"kind":"arxiv","id":"2503.19824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19824","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19824v1","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19824","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"LFBL7LP6PZXN","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"LFBL7LP6PZXNDQT3","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"LFBL7LP6","created_at":"2026-07-05T11:18:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LFBL7LP6PZXNDQT3VS75XECXOX","target":"record","payload":{"canonical_record":{"source":{"id":"2503.19824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:38:23Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"a2235bfd78ac8966ca0366923635b5a9c1e0c3ff70b11207520b9738451da9cc","abstract_canon_sha256":"8ac7676c32cb3ed6a8f8d864b867bf9056d4b9209899b7810b89f51db2690020"},"schema_version":"1.0"},"canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:19.730255Z","signature_b64":"sOBrx+bPusi0ZNKAK1jGLq/6CYXoIWQcmNGJoaFHzl3aA32RK8f21MPldZ1cKYrKgeCAZ0KNfyFoxfHmozK2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","last_reissued_at":"2026-07-05T11:18:19.729691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:19.729691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.19824","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":"2026-07-05T11:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOjxVn+6vilTlvyp7cGxY3x5QHLVJFSHt5gyRyAAIqhFHFyPE/L2WBgwSHI/GgVV5N7nYotbDl5I9x5UVka5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:16.847939Z"},"content_sha256":"61b0bd26ede762a1ba1530081fe4a5e2240b19e13fc917c870312722261a883c","schema_version":"1.0","event_id":"sha256:61b0bd26ede762a1ba1530081fe4a5e2240b19e13fc917c870312722261a883c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LFBL7LP6PZXNDQT3VS75XECXOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Borong Liang, Errui Ding, Hang Zhou, Haocheng Feng, Jiazhi Guan, Jingdong Wang, Kaisiyuan Wang, Quanwei Yang, Shengyi He, Yasheng Sun, Yingying Li, Youjian Zhao, Yukang Cao, Zhiliang Xu, Ziwei Liu","submitted_at":"2025-03-25T16:38:23Z","abstract_excerpt":"Despite the recent progress of audio-driven video generation, existing methods mostly focus on driving facial movements, leading to non-coherent head and body dynamics. Moving forward, it is desirable yet challenging to generate holistic human videos with both accurate lip-sync and delicate co-speech gestures w.r.t. given audio. In this work, we propose AudCast, a generalized audio-driven human video generation framework adopting a cascade Diffusion-Transformers (DiTs) paradigm, which synthesizes holistic human videos based on a reference image and a given audio. 1) Firstly, an audio-condition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19824","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/2503.19824/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":"2026-07-05T11:18:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MisCu+kTkCMizq7r2YnTIHaf3xlxzDFbkyBkd6VoDksW6C8vHvmkt9w2J4cQUE4GvgOSMpXSkJJDBnTE0W0iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:32:16.848304Z"},"content_sha256":"d986762210c596cab94366994bb383c42505d19fb4e4fcb15b3eeaa1ae197148","schema_version":"1.0","event_id":"sha256:d986762210c596cab94366994bb383c42505d19fb4e4fcb15b3eeaa1ae197148"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/bundle.json","state_url":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFBL7LP6PZXNDQT3VS75XECXOX/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":"2026-07-09T04:32:16Z","links":{"resolver":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX","bundle":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/bundle.json","state":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFBL7LP6PZXNDQT3VS75XECXOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LFBL7LP6PZXNDQT3VS75XECXOX","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":"8ac7676c32cb3ed6a8f8d864b867bf9056d4b9209899b7810b89f51db2690020","cross_cats_sorted":["cs.GR","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:38:23Z","title_canon_sha256":"a2235bfd78ac8966ca0366923635b5a9c1e0c3ff70b11207520b9738451da9cc"},"schema_version":"1.0","source":{"id":"2503.19824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19824","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19824v1","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19824","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_12","alias_value":"LFBL7LP6PZXN","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_16","alias_value":"LFBL7LP6PZXNDQT3","created_at":"2026-07-05T11:18:19Z"},{"alias_kind":"pith_short_8","alias_value":"LFBL7LP6","created_at":"2026-07-05T11:18:19Z"}],"graph_snapshots":[{"event_id":"sha256:d986762210c596cab94366994bb383c42505d19fb4e4fcb15b3eeaa1ae197148","target":"graph","created_at":"2026-07-05T11:18:19Z","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/2503.19824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent progress of audio-driven video generation, existing methods mostly focus on driving facial movements, leading to non-coherent head and body dynamics. Moving forward, it is desirable yet challenging to generate holistic human videos with both accurate lip-sync and delicate co-speech gestures w.r.t. given audio. In this work, we propose AudCast, a generalized audio-driven human video generation framework adopting a cascade Diffusion-Transformers (DiTs) paradigm, which synthesizes holistic human videos based on a reference image and a given audio. 1) Firstly, an audio-condition","authors_text":"Borong Liang, Errui Ding, Hang Zhou, Haocheng Feng, Jiazhi Guan, Jingdong Wang, Kaisiyuan Wang, Quanwei Yang, Shengyi He, Yasheng Sun, Yingying Li, Youjian Zhao, Yukang Cao, Zhiliang Xu, Ziwei Liu","cross_cats":["cs.GR","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:38:23Z","title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19824","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":"sha256:61b0bd26ede762a1ba1530081fe4a5e2240b19e13fc917c870312722261a883c","target":"record","created_at":"2026-07-05T11:18:19Z","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":"8ac7676c32cb3ed6a8f8d864b867bf9056d4b9209899b7810b89f51db2690020","cross_cats_sorted":["cs.GR","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:38:23Z","title_canon_sha256":"a2235bfd78ac8966ca0366923635b5a9c1e0c3ff70b11207520b9738451da9cc"},"schema_version":"1.0","source":{"id":"2503.19824","kind":"arxiv","version":1}},"canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","first_computed_at":"2026-07-05T11:18:19.729691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:19.729691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sOBrx+bPusi0ZNKAK1jGLq/6CYXoIWQcmNGJoaFHzl3aA32RK8f21MPldZ1cKYrKgeCAZ0KNfyFoxfHmozK2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:19.730255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61b0bd26ede762a1ba1530081fe4a5e2240b19e13fc917c870312722261a883c","sha256:d986762210c596cab94366994bb383c42505d19fb4e4fcb15b3eeaa1ae197148"],"state_sha256":"194f511e3efe669878a7122eba843e97e0e2e507fa0dfb91caeed87fdcc9b06e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZfcfCFmFRvydBDrRGGyQS2HE2afG+nnSaFJfojM8ge2FZWf+dk4nFc0S/SKoIgpDj3JJ01qAmpo+xyYCZwwzBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:32:16.851184Z","bundle_sha256":"f03a7001991d0c4d7d0b49e55897dd81c08f6c4af782de3c4fbb8d7cf953941a"}}