{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PNTJRUHLUB346MOLZ6UOOCMANA","short_pith_number":"pith:PNTJRUHL","canonical_record":{"source":{"id":"2508.00733","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-01T16:03:57Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"77bdfb1ece849d55ea090597688274474dcc02dabbcee9b6f57135c90682eaea","abstract_canon_sha256":"397edfa632cf18268c208e2f30af9da85562b20e7cb63ba1a843a93826819083"},"schema_version":"1.0"},"canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","source":{"kind":"arxiv","id":"2508.00733","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00733","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00733v4","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00733","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"PNTJRUHLUB34","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"PNTJRUHLUB346MOL","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"PNTJRUHL","created_at":"2026-07-05T11:49:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PNTJRUHLUB346MOLZ6UOOCMANA","target":"record","payload":{"canonical_record":{"source":{"id":"2508.00733","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-01T16:03:57Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"77bdfb1ece849d55ea090597688274474dcc02dabbcee9b6f57135c90682eaea","abstract_canon_sha256":"397edfa632cf18268c208e2f30af9da85562b20e7cb63ba1a843a93826819083"},"schema_version":"1.0"},"canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:58.835275Z","signature_b64":"xAAsHhrQ/SN3CSlHGsi6BE8JN2QMzIGi+ibMgDSJXmubZFK5/C2Xmxj7u4/bTGHm6zQMVnosQxcwiJYf2luIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","last_reissued_at":"2026-07-05T11:49:58.834833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:58.834833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.00733","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fbOh3HGzZ77F2Ua94gRgRgdzumxETaeXXvtc2dv5Ui8Mg+cufLBtUW6I2BMlwrYhbo0AjcnXSwXVJ5S4mDBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:07:07.377851Z"},"content_sha256":"75de60f903581ae28d9c6c7eddd9b0441b0251d39e7c9d9ecf084a5c8a9e6285","schema_version":"1.0","event_id":"sha256:75de60f903581ae28d9c6c7eddd9b0441b0251d39e7c9d9ecf084a5c8a9e6285"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PNTJRUHLUB346MOLZ6UOOCMANA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Chunyu Qiang, Di Zhang, Feng Deng, Jun Wang, Kun Gai, Le Wang","submitted_at":"2025-08-01T16:03:57Z","abstract_excerpt":"We present AudioGen-Omni - a unified approach based on multimodal diffusion transformers (MMDit), capable of generating high-fidelity audio, speech, and song coherently synchronized with the input video. AudioGen-Omni introduces a novel joint training paradigm that seamlessly integrates large-scale video-text-audio corpora, enabling a model capable of generating semantically rich, acoustically diverse audio conditioned on multimodal inputs and adaptable to a wide range of audio generation tasks. AudioGen-Omni employs a unified lyrics-transcription encoder that encodes graphemes and phonemes fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00733","kind":"arxiv","version":4},"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/2508.00733/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":"2026-07-05T11:49:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bLg8m5Cm9A7XOs12GHtqHE20L0Fq/CYcDyNRpzzvckYyUguscbLCztR3Ydpur61v56EYeaEIGyTz4QBK7bEPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:07:07.378231Z"},"content_sha256":"c3fe49c21fa2b9785aa80258dd703b0b919af850a1d2c5634ede8461d8d96edc","schema_version":"1.0","event_id":"sha256:c3fe49c21fa2b9785aa80258dd703b0b919af850a1d2c5634ede8461d8d96edc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/bundle.json","state_url":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNTJRUHLUB346MOLZ6UOOCMANA/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":"2026-08-05T01:07:07Z","links":{"resolver":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA","bundle":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/bundle.json","state":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNTJRUHLUB346MOLZ6UOOCMANA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PNTJRUHLUB346MOLZ6UOOCMANA","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":"397edfa632cf18268c208e2f30af9da85562b20e7cb63ba1a843a93826819083","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-01T16:03:57Z","title_canon_sha256":"77bdfb1ece849d55ea090597688274474dcc02dabbcee9b6f57135c90682eaea"},"schema_version":"1.0","source":{"id":"2508.00733","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00733","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00733v4","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00733","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_12","alias_value":"PNTJRUHLUB34","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_16","alias_value":"PNTJRUHLUB346MOL","created_at":"2026-07-05T11:49:58Z"},{"alias_kind":"pith_short_8","alias_value":"PNTJRUHL","created_at":"2026-07-05T11:49:58Z"}],"graph_snapshots":[{"event_id":"sha256:c3fe49c21fa2b9785aa80258dd703b0b919af850a1d2c5634ede8461d8d96edc","target":"graph","created_at":"2026-07-05T11:49:58Z","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/2508.00733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present AudioGen-Omni - a unified approach based on multimodal diffusion transformers (MMDit), capable of generating high-fidelity audio, speech, and song coherently synchronized with the input video. AudioGen-Omni introduces a novel joint training paradigm that seamlessly integrates large-scale video-text-audio corpora, enabling a model capable of generating semantically rich, acoustically diverse audio conditioned on multimodal inputs and adaptable to a wide range of audio generation tasks. AudioGen-Omni employs a unified lyrics-transcription encoder that encodes graphemes and phonemes fr","authors_text":"Chen Zhang, Chunyu Qiang, Di Zhang, Feng Deng, Jun Wang, Kun Gai, Le Wang","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-01T16:03:57Z","title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00733","kind":"arxiv","version":4},"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":"sha256:75de60f903581ae28d9c6c7eddd9b0441b0251d39e7c9d9ecf084a5c8a9e6285","target":"record","created_at":"2026-07-05T11:49:58Z","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":"397edfa632cf18268c208e2f30af9da85562b20e7cb63ba1a843a93826819083","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-01T16:03:57Z","title_canon_sha256":"77bdfb1ece849d55ea090597688274474dcc02dabbcee9b6f57135c90682eaea"},"schema_version":"1.0","source":{"id":"2508.00733","kind":"arxiv","version":4}},"canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","first_computed_at":"2026-07-05T11:49:58.834833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:58.834833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xAAsHhrQ/SN3CSlHGsi6BE8JN2QMzIGi+ibMgDSJXmubZFK5/C2Xmxj7u4/bTGHm6zQMVnosQxcwiJYf2luIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:58.835275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00733","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75de60f903581ae28d9c6c7eddd9b0441b0251d39e7c9d9ecf084a5c8a9e6285","sha256:c3fe49c21fa2b9785aa80258dd703b0b919af850a1d2c5634ede8461d8d96edc"],"state_sha256":"4da86fd51d09a5fc7bcecdac1dbf5266010c0f48469a98d1c63d24d05b152bcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+o6gU8XaMj2mpMHfKdJyHjE4DVif8iANe1A2aaw2EDx1dgE1lZpDhCUGiyWeKTiTWovUovzf36xvLy4gmFqGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:07:07.380462Z","bundle_sha256":"dba6125665f269e485ace5285503f4ae42af438b6f43c361056857f50d081b74"}}