{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YI37BSGL4O7H36M55V45OK3FMG","short_pith_number":"pith:YI37BSGL","canonical_record":{"source":{"id":"2607.26698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T09:45:13Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"379d273e205fbaed9ceea3401539018d9d0096d4348babf1643ab50ba12c0c85","abstract_canon_sha256":"1f1b7434e6b1016e54503dfd0eeab413dfc22c84588f1ebab756ab1260abe158"},"schema_version":"1.0"},"canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","source":{"kind":"arxiv","id":"2607.26698","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26698","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26698v1","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26698","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"YI37BSGL4O7H","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"YI37BSGL4O7H36M5","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"YI37BSGL","created_at":"2026-07-30T01:21:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YI37BSGL4O7H36M55V45OK3FMG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T09:45:13Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"379d273e205fbaed9ceea3401539018d9d0096d4348babf1643ab50ba12c0c85","abstract_canon_sha256":"1f1b7434e6b1016e54503dfd0eeab413dfc22c84588f1ebab756ab1260abe158"},"schema_version":"1.0"},"canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","last_reissued_at":"2026-07-30T01:21:58.218405Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:21:58.218405Z"},"source_kind":"arxiv","source_id":"2607.26698","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":"2026-07-30T01:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udfbYoLFzOgAjoPm98SHxkq6kll4nKnopLKbqmbolgJt8kUp26XMe/qO8sA/iY9VDSNEJRcGvYWLVHsSXt+rDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T02:08:22.805906Z"},"content_sha256":"d9365955a1fec8c34cf5aaf01bdf7202f1efd17178c324c389f494603d67ae52","schema_version":"1.0","event_id":"sha256:d9365955a1fec8c34cf5aaf01bdf7202f1efd17178c324c389f494603d67ae52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YI37BSGL4O7H36M55V45OK3FMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chih-Pin Tan, Fang-Duo Tsai, Hsuan-Yu Yeh, Ting-Yi Hu, Wei-Jaw Lee, Yi-Hsuan Yang","submitted_at":"2026-07-29T09:45:13Z","abstract_excerpt":"Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we propose MPEcho, which integrates a phoneme encoder and a length regulator (LR) into the SongEcho framework. By providing explicit phoneme-level conditioning and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26698","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/2607.26698/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":"2026-07-30T01:21:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zRVTGq8hqC5v9VyHSU4UQNYlUKqlohzs1ENH2WyMpGZQ4i7ZsYXrScNc7dJH9pu9Ze/eYBHTQssLJssliW8KBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T02:08:22.806435Z"},"content_sha256":"aaed60ee798a4aab696338f8b18530a3c593d50a230394fb89ab7cce8cf2e64e","schema_version":"1.0","event_id":"sha256:aaed60ee798a4aab696338f8b18530a3c593d50a230394fb89ab7cce8cf2e64e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/bundle.json","state_url":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YI37BSGL4O7H36M55V45OK3FMG/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":"2026-08-02T02:08:22Z","links":{"resolver":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG","bundle":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/bundle.json","state":"https://pith.science/pith/YI37BSGL4O7H36M55V45OK3FMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YI37BSGL4O7H36M55V45OK3FMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YI37BSGL4O7H36M55V45OK3FMG","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":"1f1b7434e6b1016e54503dfd0eeab413dfc22c84588f1ebab756ab1260abe158","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T09:45:13Z","title_canon_sha256":"379d273e205fbaed9ceea3401539018d9d0096d4348babf1643ab50ba12c0c85"},"schema_version":"1.0","source":{"id":"2607.26698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26698","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26698v1","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26698","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_12","alias_value":"YI37BSGL4O7H","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_16","alias_value":"YI37BSGL4O7H36M5","created_at":"2026-07-30T01:21:58Z"},{"alias_kind":"pith_short_8","alias_value":"YI37BSGL","created_at":"2026-07-30T01:21:58Z"}],"graph_snapshots":[{"event_id":"sha256:aaed60ee798a4aab696338f8b18530a3c593d50a230394fb89ab7cce8cf2e64e","target":"graph","created_at":"2026-07-30T01:21:58Z","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/2607.26698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components. The state-of-the-art model SongEcho utilizes $F_0$ sequences and voiced/unvoiced (V/UV) tags for conditioning; however, implicit linguistic information from V/UV tags cannot guarantee lyric accuracy, leading to a high phoneme error rate (PER). Inspired by singing voice synthesis (SVS), we propose MPEcho, which integrates a phoneme encoder and a length regulator (LR) into the SongEcho framework. By providing explicit phoneme-level conditioning and","authors_text":"Chih-Pin Tan, Fang-Duo Tsai, Hsuan-Yu Yeh, Ting-Yi Hu, Wei-Jaw Lee, Yi-Hsuan Yang","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T09:45:13Z","title":"MPEcho: A Melody and Phoneme-Aware Generative Framework for Controllable Cover Song Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26698","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:d9365955a1fec8c34cf5aaf01bdf7202f1efd17178c324c389f494603d67ae52","target":"record","created_at":"2026-07-30T01:21:58Z","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":"1f1b7434e6b1016e54503dfd0eeab413dfc22c84588f1ebab756ab1260abe158","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-29T09:45:13Z","title_canon_sha256":"379d273e205fbaed9ceea3401539018d9d0096d4348babf1643ab50ba12c0c85"},"schema_version":"1.0","source":{"id":"2607.26698","kind":"arxiv","version":1}},"canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c237f0c8cbe3be7df99ded79d72b6561972c4cbb241d36c1f08b533c44c7ef89","first_computed_at":"2026-07-30T01:21:58.218405Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:21:58.218405Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9365955a1fec8c34cf5aaf01bdf7202f1efd17178c324c389f494603d67ae52","sha256:aaed60ee798a4aab696338f8b18530a3c593d50a230394fb89ab7cce8cf2e64e"],"state_sha256":"c713f59d83e3a34cc101299cdbeebbc811e4e44bd2a02e6df8782d011d12ab52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QUaCHLPwNmRa6yM3EpLQH4op8+OmWM6XkeaQA6lFa4rKbQCafwwm2mNjKTgFfbPMsS9VpDsL48sKOulqCNVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T02:08:22.810820Z","bundle_sha256":"77e66fdf7b647930e57565f4c0ca1ef07c05949e3bfde5517a0f044a962afee0"}}