{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X46YQUWI2TDNAR23DMFQI6QYUB","short_pith_number":"pith:X46YQUWI","canonical_record":{"source":{"id":"2405.17842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T05:43:03Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"f50f4745ca92c6ffecc014196af9d4f9422639bb441b63310a51de155dd01f49","abstract_canon_sha256":"50c32560310762df127eed95f4d3eab8a0a4d45e47d417edf0e9909d61ac5bad"},"schema_version":"1.0"},"canonical_sha256":"bf3d8852c8d4c6d0475b1b0b047a18a05db304aa0b0ace359ea520f571c0aa2d","source":{"kind":"arxiv","id":"2405.17842","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17842","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17842v2","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17842","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"X46YQUWI2TDN","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"X46YQUWI2TDNAR23","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"X46YQUWI","created_at":"2026-07-05T10:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X46YQUWI2TDNAR23DMFQI6QYUB","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17842","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T05:43:03Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"f50f4745ca92c6ffecc014196af9d4f9422639bb441b63310a51de155dd01f49","abstract_canon_sha256":"50c32560310762df127eed95f4d3eab8a0a4d45e47d417edf0e9909d61ac5bad"},"schema_version":"1.0"},"canonical_sha256":"bf3d8852c8d4c6d0475b1b0b047a18a05db304aa0b0ace359ea520f571c0aa2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:24.452945Z","signature_b64":"q9+h36ZVzYjfKuKIjbZvw6wmU0yYbuT8B+oEIl3YWr6zIeFLnwn/1f3K9bFtRsRFrmb1oi5UynHz2cS9F/TIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3d8852c8d4c6d0475b1b0b047a18a05db304aa0b0ace359ea520f571c0aa2d","last_reissued_at":"2026-07-05T10:19:24.452397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:24.452397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17842","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":"2026-07-05T10:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OrZ2pIxxKHFZOSSj3Ra4mOcbycpH0j3wp9wQl6LYikxrts3Qs5VrtIXeYReDCBJh2bboa18Ouq/3g7YaTR2VAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:45:30.160885Z"},"content_sha256":"26af0be84f06d46f5684cc19080a90307045634ef01893b86f6094a4590cd389","schema_version":"1.0","event_id":"sha256:26af0be84f06d46f5684cc19080a90307045634ef01893b86f6094a4590cd389"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X46YQUWI2TDNAR23DMFQI6QYUB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji","submitted_at":"2024-05-28T05:43:03Z","abstract_excerpt":"This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17842","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/2405.17842/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":"2026-07-05T10:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72u6fEul1MUmYQOgBQ+/UokUkiBR8n2X13jKWmNrl8R8VjiOQMz0MomMDS7Bw/u81aZ9DGMHwDx3IFK3XBICCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:45:30.161613Z"},"content_sha256":"7ed3d819114c0e751b5f26e4fb37953860c6f18f647f1aa1b28f062bb6442d92","schema_version":"1.0","event_id":"sha256:7ed3d819114c0e751b5f26e4fb37953860c6f18f647f1aa1b28f062bb6442d92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X46YQUWI2TDNAR23DMFQI6QYUB/bundle.json","state_url":"https://pith.science/pith/X46YQUWI2TDNAR23DMFQI6QYUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X46YQUWI2TDNAR23DMFQI6QYUB/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":"2026-08-12T15:45:30Z","links":{"resolver":"https://pith.science/pith/X46YQUWI2TDNAR23DMFQI6QYUB","bundle":"https://pith.science/pith/X46YQUWI2TDNAR23DMFQI6QYUB/bundle.json","state":"https://pith.science/pith/X46YQUWI2TDNAR23DMFQI6QYUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X46YQUWI2TDNAR23DMFQI6QYUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X46YQUWI2TDNAR23DMFQI6QYUB","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":"50c32560310762df127eed95f4d3eab8a0a4d45e47d417edf0e9909d61ac5bad","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T05:43:03Z","title_canon_sha256":"f50f4745ca92c6ffecc014196af9d4f9422639bb441b63310a51de155dd01f49"},"schema_version":"1.0","source":{"id":"2405.17842","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17842","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17842v2","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17842","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"X46YQUWI2TDN","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"X46YQUWI2TDNAR23","created_at":"2026-07-05T10:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"X46YQUWI","created_at":"2026-07-05T10:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:7ed3d819114c0e751b5f26e4fb37953860c6f18f647f1aa1b28f062bb6442d92","target":"graph","created_at":"2026-07-05T10:19:24Z","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/2405.17842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of","authors_text":"Akio Hayakawa, Masato Ishii, Takashi Shibuya, Yuki Mitsufuji","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T05:43:03Z","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17842","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":"sha256:26af0be84f06d46f5684cc19080a90307045634ef01893b86f6094a4590cd389","target":"record","created_at":"2026-07-05T10:19:24Z","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":"50c32560310762df127eed95f4d3eab8a0a4d45e47d417edf0e9909d61ac5bad","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-28T05:43:03Z","title_canon_sha256":"f50f4745ca92c6ffecc014196af9d4f9422639bb441b63310a51de155dd01f49"},"schema_version":"1.0","source":{"id":"2405.17842","kind":"arxiv","version":2}},"canonical_sha256":"bf3d8852c8d4c6d0475b1b0b047a18a05db304aa0b0ace359ea520f571c0aa2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf3d8852c8d4c6d0475b1b0b047a18a05db304aa0b0ace359ea520f571c0aa2d","first_computed_at":"2026-07-05T10:19:24.452397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:24.452397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q9+h36ZVzYjfKuKIjbZvw6wmU0yYbuT8B+oEIl3YWr6zIeFLnwn/1f3K9bFtRsRFrmb1oi5UynHz2cS9F/TIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:24.452945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17842","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26af0be84f06d46f5684cc19080a90307045634ef01893b86f6094a4590cd389","sha256:7ed3d819114c0e751b5f26e4fb37953860c6f18f647f1aa1b28f062bb6442d92"],"state_sha256":"148bee975bf3cf817ed91fcdd7a88a4099e90f30e11fa01b1a2561f9fb345dcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHZtbu7lqwmKgh7U8fMPZIwvKAruVrcT9c71MKXnQeSkpp46J4p2+X1LqPcJ7S42S4UudvMP0MLWNP3PQDMtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:45:30.168410Z","bundle_sha256":"703db29ea3e6da046ab46bada584994adeb5edd15dd55108d68d1d0f90cfc081"}}