{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4I6O4NPM2P6ZN2RABYFZZQZSVB","short_pith_number":"pith:4I6O4NPM","canonical_record":{"source":{"id":"2506.03364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-03T20:16:41Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"e5f0ac475af8710cca31df047d529f68cb634a138877360bf1460b64914ea6ce","abstract_canon_sha256":"0f205153e0b20cfdd11d33567be516e402e9cee0c98ce482de8165479554f7d2"},"schema_version":"1.0"},"canonical_sha256":"e23cee35ecd3fd96ea200e0b9cc332a844aea8b551e9cf010badafbe90ca995b","source":{"kind":"arxiv","id":"2506.03364","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03364","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03364v1","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03364","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"4I6O4NPM2P6Z","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"4I6O4NPM2P6ZN2RA","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"4I6O4NPM","created_at":"2026-07-05T11:15:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4I6O4NPM2P6ZN2RABYFZZQZSVB","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-03T20:16:41Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"e5f0ac475af8710cca31df047d529f68cb634a138877360bf1460b64914ea6ce","abstract_canon_sha256":"0f205153e0b20cfdd11d33567be516e402e9cee0c98ce482de8165479554f7d2"},"schema_version":"1.0"},"canonical_sha256":"e23cee35ecd3fd96ea200e0b9cc332a844aea8b551e9cf010badafbe90ca995b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:48.337273Z","signature_b64":"kwKKoWnNo1PwYADtqSVHJ1yQkbbLahM6PSJWHaNFstY72+8Fsgm2Ksl1lz/1y64qbUa2lJwl7Q7xRWCqMHjRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e23cee35ecd3fd96ea200e0b9cc332a844aea8b551e9cf010badafbe90ca995b","last_reissued_at":"2026-07-05T11:15:48.336756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:48.336756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03364","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":"2026-07-05T11:15:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qsy0lwioXH1wz0XQEI8ImKEXuk475IHhJK33YsqH/a5Z7w7BGI5MX0i+eXph3mFEDrN7O6g57UsjG+Kv0X25CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:55:44.137433Z"},"content_sha256":"c27b0c369f4ac86675b9b7098a897d324856bc479564ff4a1fea6b72421bf297","schema_version":"1.0","event_id":"sha256:c27b0c369f4ac86675b9b7098a897d324856bc479564ff4a1fea6b72421bf297"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4I6O4NPM2P6ZN2RABYFZZQZSVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Orchid Chetia Phukan, Pailla Balakrishna Reddy, Priyabrata Mallick, Rajesh Sharma, Swarup Ranjan Behera","submitted_at":"2025-06-03T20:16:41Z","abstract_excerpt":"In this work, we introduce the task of singing voice deepfake source attribution (SVDSA). We hypothesize that multimodal foundation models (MMFMs) such as ImageBind, LanguageBind will be most effective for SVDSA as they are better equipped for capturing subtle source-specific characteristics-such as unique timbre, pitch manipulation, or synthesis artifacts of each singing voice deepfake source due to their cross-modality pre-training. Our experiments with MMFMs, speech foundation models and music foundation models verify the hypothesis that MMFMs are the most effective for SVDSA. Furthermore, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03364","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/2506.03364/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":"2026-07-05T11:15:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ofzbhTuR1R0I9QLrD0cBDLuXg6cvwBtKv1iuJI0X5GyaiHOVBwNFs7VB5+rVLmSdfRnO0t8xQhaTrMT/fx7oBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:55:44.137740Z"},"content_sha256":"a7c6b3ccd21c49fcddb8ca881c5c554260b74c72ce3c1c2d528ae8160f01d4a2","schema_version":"1.0","event_id":"sha256:a7c6b3ccd21c49fcddb8ca881c5c554260b74c72ce3c1c2d528ae8160f01d4a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB/bundle.json","state_url":"https://pith.science/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB/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":"2026-08-01T06:55:44Z","links":{"resolver":"https://pith.science/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB","bundle":"https://pith.science/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB/bundle.json","state":"https://pith.science/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4I6O4NPM2P6ZN2RABYFZZQZSVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4I6O4NPM2P6ZN2RABYFZZQZSVB","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":"0f205153e0b20cfdd11d33567be516e402e9cee0c98ce482de8165479554f7d2","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-03T20:16:41Z","title_canon_sha256":"e5f0ac475af8710cca31df047d529f68cb634a138877360bf1460b64914ea6ce"},"schema_version":"1.0","source":{"id":"2506.03364","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03364","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03364v1","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03364","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"4I6O4NPM2P6Z","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"4I6O4NPM2P6ZN2RA","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"4I6O4NPM","created_at":"2026-07-05T11:15:48Z"}],"graph_snapshots":[{"event_id":"sha256:a7c6b3ccd21c49fcddb8ca881c5c554260b74c72ce3c1c2d528ae8160f01d4a2","target":"graph","created_at":"2026-07-05T11:15:48Z","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/2506.03364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce the task of singing voice deepfake source attribution (SVDSA). We hypothesize that multimodal foundation models (MMFMs) such as ImageBind, LanguageBind will be most effective for SVDSA as they are better equipped for capturing subtle source-specific characteristics-such as unique timbre, pitch manipulation, or synthesis artifacts of each singing voice deepfake source due to their cross-modality pre-training. Our experiments with MMFMs, speech foundation models and music foundation models verify the hypothesis that MMFMs are the most effective for SVDSA. Furthermore, ","authors_text":"Arun Balaji Buduru, Girish, Mohd Mujtaba Akhtar, Orchid Chetia Phukan, Pailla Balakrishna Reddy, Priyabrata Mallick, Rajesh Sharma, Swarup Ranjan Behera","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-03T20:16:41Z","title":"Towards Source Attribution of Singing Voice Deepfake with Multimodal Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03364","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:c27b0c369f4ac86675b9b7098a897d324856bc479564ff4a1fea6b72421bf297","target":"record","created_at":"2026-07-05T11:15:48Z","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":"0f205153e0b20cfdd11d33567be516e402e9cee0c98ce482de8165479554f7d2","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-03T20:16:41Z","title_canon_sha256":"e5f0ac475af8710cca31df047d529f68cb634a138877360bf1460b64914ea6ce"},"schema_version":"1.0","source":{"id":"2506.03364","kind":"arxiv","version":1}},"canonical_sha256":"e23cee35ecd3fd96ea200e0b9cc332a844aea8b551e9cf010badafbe90ca995b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e23cee35ecd3fd96ea200e0b9cc332a844aea8b551e9cf010badafbe90ca995b","first_computed_at":"2026-07-05T11:15:48.336756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:48.336756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kwKKoWnNo1PwYADtqSVHJ1yQkbbLahM6PSJWHaNFstY72+8Fsgm2Ksl1lz/1y64qbUa2lJwl7Q7xRWCqMHjRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:48.337273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03364","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c27b0c369f4ac86675b9b7098a897d324856bc479564ff4a1fea6b72421bf297","sha256:a7c6b3ccd21c49fcddb8ca881c5c554260b74c72ce3c1c2d528ae8160f01d4a2"],"state_sha256":"9987bc621e380b9ea4dacd50582b57eaa0054ab042329b67c12db28f5dc33767"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZfo/6tLa4743Z9nBuCV6XMkgJuf3zzPNK6rajnkzZ7T1jHc4ghN7Tbrair7S3GZXBZf13qfNSY5q/pUcBu6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T06:55:44.141224Z","bundle_sha256":"b567cffa17169645c0bcd903d0298b0513bc50f9f4dd4da0afedc18b3beab8ec"}}