{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:A27HEKNCA7ONJGATTWKCXF4WKL","short_pith_number":"pith:A27HEKNC","canonical_record":{"source":{"id":"2212.09478","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T14:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"e4d193ce584d6cdcaaf9fc93f5ed97b14c18f403f6f7a8aa11e8f08d9ead6e70","abstract_canon_sha256":"e30a2c88a865aaef4d9a0e4517cc95d5891ce32d95e3398b53b4172fb33640c3"},"schema_version":"1.0"},"canonical_sha256":"06be7229a207dcd498139d942b979652f822ee7ae298713e55835bf8d5b539e3","source":{"kind":"arxiv","id":"2212.09478","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09478","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09478v2","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09478","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"pith_short_12","alias_value":"A27HEKNCA7ON","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"pith_short_16","alias_value":"A27HEKNCA7ONJGAT","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"pith_short_8","alias_value":"A27HEKNC","created_at":"2026-07-05T05:54:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:A27HEKNCA7ONJGATTWKCXF4WKL","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09478","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T14:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"e4d193ce584d6cdcaaf9fc93f5ed97b14c18f403f6f7a8aa11e8f08d9ead6e70","abstract_canon_sha256":"e30a2c88a865aaef4d9a0e4517cc95d5891ce32d95e3398b53b4172fb33640c3"},"schema_version":"1.0"},"canonical_sha256":"06be7229a207dcd498139d942b979652f822ee7ae298713e55835bf8d5b539e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:14.598993Z","signature_b64":"9SOu2sytICC2htVQYyZI0XRButnId0BZMTf0dqUbpVgf5WafwkkxZUYYhm72d9qE5pNgoZcDRU5V9f2J6BIlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06be7229a207dcd498139d942b979652f822ee7ae298713e55835bf8d5b539e3","last_reissued_at":"2026-07-05T05:54:14.598378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:14.598378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09478","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:54:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56474magWZtP1SPoPUa1ZzKj4dy38J8WnfpI7wh5FLmJ2jrIpZWN822WYKv+UgEwzEUn8469YBitX4aU/vUiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T07:21:51.225583Z"},"content_sha256":"f4092b0e4fdabf311727d7babc7d019d50ad3ce7db6fff1b7f58f31bcc50fff5","schema_version":"1.0","event_id":"sha256:f4092b0e4fdabf311727d7babc7d019d50ad3ce7db6fff1b7f58f31bcc50fff5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:A27HEKNCA7ONJGATTWKCXF4WKL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Bei Liu, Huan Yang, Huiguo He, Jianlong Fu, Ludan Ruan, Nicholas Jing Yuan, Qin Jin, Yiyang Ma","submitted_at":"2022-12-19T14:11:52Z","abstract_excerpt":"We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos. To generate joint audio-video pairs, we propose a novel Multi-Modal Diffusion model (i.e., MM-Diffusion), with two-coupled denoising autoencoders. In contrast to existing single-modal diffusion models, MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Two subnets for audio and video learn to gradually generate aligned audio-video pairs from Gaussian noises. To ensure semantic con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09478","kind":"arxiv","version":2},"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/2212.09478/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":"2026-07-05T05:54:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+EUh90hL9NsKiCLSKMgphITgDOsOlYsUoLiS4XwZ7jpwcgaI0jXOxkrS/cRRy0jOv7yPEivX6kpZTB/EajROBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T07:21:51.226083Z"},"content_sha256":"9a9474930b9c73b30133ce11134188c0e49252041fd2a0b3685331b8b959bfb8","schema_version":"1.0","event_id":"sha256:9a9474930b9c73b30133ce11134188c0e49252041fd2a0b3685331b8b959bfb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A27HEKNCA7ONJGATTWKCXF4WKL/bundle.json","state_url":"https://pith.science/pith/A27HEKNCA7ONJGATTWKCXF4WKL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A27HEKNCA7ONJGATTWKCXF4WKL/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":"2026-08-23T07:21:51Z","links":{"resolver":"https://pith.science/pith/A27HEKNCA7ONJGATTWKCXF4WKL","bundle":"https://pith.science/pith/A27HEKNCA7ONJGATTWKCXF4WKL/bundle.json","state":"https://pith.science/pith/A27HEKNCA7ONJGATTWKCXF4WKL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A27HEKNCA7ONJGATTWKCXF4WKL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:A27HEKNCA7ONJGATTWKCXF4WKL","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":"e30a2c88a865aaef4d9a0e4517cc95d5891ce32d95e3398b53b4172fb33640c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T14:11:52Z","title_canon_sha256":"e4d193ce584d6cdcaaf9fc93f5ed97b14c18f403f6f7a8aa11e8f08d9ead6e70"},"schema_version":"1.0","source":{"id":"2212.09478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09478","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09478v2","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09478","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"pith_short_12","alias_value":"A27HEKNCA7ON","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"pith_short_16","alias_value":"A27HEKNCA7ONJGAT","created_at":"2026-07-05T05:54:14Z"},{"alias_kind":"pith_short_8","alias_value":"A27HEKNC","created_at":"2026-07-05T05:54:14Z"}],"graph_snapshots":[{"event_id":"sha256:9a9474930b9c73b30133ce11134188c0e49252041fd2a0b3685331b8b959bfb8","target":"graph","created_at":"2026-07-05T05:54:14Z","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/2212.09478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the first joint audio-video generation framework that brings engaging watching and listening experiences simultaneously, towards high-quality realistic videos. To generate joint audio-video pairs, we propose a novel Multi-Modal Diffusion model (i.e., MM-Diffusion), with two-coupled denoising autoencoders. In contrast to existing single-modal diffusion models, MM-Diffusion consists of a sequential multi-modal U-Net for a joint denoising process by design. Two subnets for audio and video learn to gradually generate aligned audio-video pairs from Gaussian noises. To ensure semantic con","authors_text":"Baining Guo, Bei Liu, Huan Yang, Huiguo He, Jianlong Fu, Ludan Ruan, Nicholas Jing Yuan, Qin Jin, Yiyang Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T14:11:52Z","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09478","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:f4092b0e4fdabf311727d7babc7d019d50ad3ce7db6fff1b7f58f31bcc50fff5","target":"record","created_at":"2026-07-05T05:54:14Z","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":"e30a2c88a865aaef4d9a0e4517cc95d5891ce32d95e3398b53b4172fb33640c3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-19T14:11:52Z","title_canon_sha256":"e4d193ce584d6cdcaaf9fc93f5ed97b14c18f403f6f7a8aa11e8f08d9ead6e70"},"schema_version":"1.0","source":{"id":"2212.09478","kind":"arxiv","version":2}},"canonical_sha256":"06be7229a207dcd498139d942b979652f822ee7ae298713e55835bf8d5b539e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06be7229a207dcd498139d942b979652f822ee7ae298713e55835bf8d5b539e3","first_computed_at":"2026-07-05T05:54:14.598378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:14.598378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9SOu2sytICC2htVQYyZI0XRButnId0BZMTf0dqUbpVgf5WafwkkxZUYYhm72d9qE5pNgoZcDRU5V9f2J6BIlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:14.598993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4092b0e4fdabf311727d7babc7d019d50ad3ce7db6fff1b7f58f31bcc50fff5","sha256:9a9474930b9c73b30133ce11134188c0e49252041fd2a0b3685331b8b959bfb8"],"state_sha256":"4dee644aee173c0576d5987b9af3e13d8c985cd15347ffc2e0c7cf3a3d2a6e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDTnhypW7tK530hXVaVg/R+3cESJGublcmaVVcs6q4H1tyeOz1H2q/zVkafmDg7zVafaxvg3EwEWpyqOfVNIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T07:21:51.230764Z","bundle_sha256":"81c364345923efaaf14a5cbbc4926abc930b78ba263fd3fb4e7252ca57330c0d"}}