{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RO4IVPUNAS2TBE6YKOBHN3E2ZU","short_pith_number":"pith:RO4IVPUN","canonical_record":{"source":{"id":"2507.14988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-20T14:48:48Z","cross_cats_sorted":[],"title_canon_sha256":"01f1f45f08c26eb387bffacabc4d9c3f9546cdd7edb7ecc7b31903d4dea2c3bc","abstract_canon_sha256":"9a91f3ff3082eeda2690a575461aa57302270cedf17ff24de349f18509bebfea"},"schema_version":"1.0"},"canonical_sha256":"8bb88abe8d04b53093d8538276ec9acd372d3ca54af2bd3f7be4908f4ca346b2","source":{"kind":"arxiv","id":"2507.14988","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14988","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14988v1","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14988","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"pith_short_12","alias_value":"RO4IVPUNAS2T","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"pith_short_16","alias_value":"RO4IVPUNAS2TBE6Y","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"pith_short_8","alias_value":"RO4IVPUN","created_at":"2026-07-05T11:40:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RO4IVPUNAS2TBE6YKOBHN3E2ZU","target":"record","payload":{"canonical_record":{"source":{"id":"2507.14988","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-20T14:48:48Z","cross_cats_sorted":[],"title_canon_sha256":"01f1f45f08c26eb387bffacabc4d9c3f9546cdd7edb7ecc7b31903d4dea2c3bc","abstract_canon_sha256":"9a91f3ff3082eeda2690a575461aa57302270cedf17ff24de349f18509bebfea"},"schema_version":"1.0"},"canonical_sha256":"8bb88abe8d04b53093d8538276ec9acd372d3ca54af2bd3f7be4908f4ca346b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:16.328264Z","signature_b64":"SQDsChlhyRRgd6JS64OEy0sUgv/tSiwJoSkOZ9bYgCvJr1Ytgfx1sKvEZTmFE7LuiY8ZDpF2bGwu2O1w3ZklBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bb88abe8d04b53093d8538276ec9acd372d3ca54af2bd3f7be4908f4ca346b2","last_reissued_at":"2026-07-05T11:40:16.327796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:16.327796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.14988","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":"2026-07-05T11:40:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svVhaOlNY4qgIMle70wTH3D9tt+Z8IE1rjhI6p/64NVngey23EjYtm+fwWqSmX/mRI1JVUdUSgCbfW3GKoUnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:58:25.118166Z"},"content_sha256":"254f08a13d6c9ddfa7225b269674bc605cc2eb0dc94adcee31aad17292b95ffe","schema_version":"1.0","event_id":"sha256:254f08a13d6c9ddfa7225b269674bc605cc2eb0dc94adcee31aad17292b95ffe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RO4IVPUNAS2TBE6YKOBHN3E2ZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Cheng Niu, Fei Tao, Juntong Song, Kaifeng Xu, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2025-07-20T14:48:48Z","abstract_excerpt":"Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric optimization for speech generation components, but duration prediction remained unoptimized. This paper presents DMOSpeech 2, which extends metric optimization to the duration predictor through a reinforcement learning approach. The proposed system implements a novel duration policy framework using group relative preference optimization (GRPO) with speaker similari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14988","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/2507.14988/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":"2026-07-05T11:40:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3o9HFE55btSKTrM6tayxVMUmVSZVyEMeZ1dn49PkXMiuvOFuRKkwzz2rg1XipFsdpDX9qMxFi+RoQVbVOI+GCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:58:25.118571Z"},"content_sha256":"8db4682b463009bc2710f908ec057dc729571eb2c7ebef634fbe2f1a907ff57c","schema_version":"1.0","event_id":"sha256:8db4682b463009bc2710f908ec057dc729571eb2c7ebef634fbe2f1a907ff57c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU/bundle.json","state_url":"https://pith.science/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU/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":"2026-07-08T13:58:25Z","links":{"resolver":"https://pith.science/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU","bundle":"https://pith.science/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU/bundle.json","state":"https://pith.science/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RO4IVPUNAS2TBE6YKOBHN3E2ZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RO4IVPUNAS2TBE6YKOBHN3E2ZU","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":"9a91f3ff3082eeda2690a575461aa57302270cedf17ff24de349f18509bebfea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-20T14:48:48Z","title_canon_sha256":"01f1f45f08c26eb387bffacabc4d9c3f9546cdd7edb7ecc7b31903d4dea2c3bc"},"schema_version":"1.0","source":{"id":"2507.14988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14988","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14988v1","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14988","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"pith_short_12","alias_value":"RO4IVPUNAS2T","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"pith_short_16","alias_value":"RO4IVPUNAS2TBE6Y","created_at":"2026-07-05T11:40:16Z"},{"alias_kind":"pith_short_8","alias_value":"RO4IVPUN","created_at":"2026-07-05T11:40:16Z"}],"graph_snapshots":[{"event_id":"sha256:8db4682b463009bc2710f908ec057dc729571eb2c7ebef634fbe2f1a907ff57c","target":"graph","created_at":"2026-07-05T11:40:16Z","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/2507.14988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric optimization for speech generation components, but duration prediction remained unoptimized. This paper presents DMOSpeech 2, which extends metric optimization to the duration predictor through a reinforcement learning approach. The proposed system implements a novel duration policy framework using group relative preference optimization (GRPO) with speaker similari","authors_text":"Cheng Niu, Fei Tao, Juntong Song, Kaifeng Xu, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-20T14:48:48Z","title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14988","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":"sha256:254f08a13d6c9ddfa7225b269674bc605cc2eb0dc94adcee31aad17292b95ffe","target":"record","created_at":"2026-07-05T11:40:16Z","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":"9a91f3ff3082eeda2690a575461aa57302270cedf17ff24de349f18509bebfea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-20T14:48:48Z","title_canon_sha256":"01f1f45f08c26eb387bffacabc4d9c3f9546cdd7edb7ecc7b31903d4dea2c3bc"},"schema_version":"1.0","source":{"id":"2507.14988","kind":"arxiv","version":1}},"canonical_sha256":"8bb88abe8d04b53093d8538276ec9acd372d3ca54af2bd3f7be4908f4ca346b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bb88abe8d04b53093d8538276ec9acd372d3ca54af2bd3f7be4908f4ca346b2","first_computed_at":"2026-07-05T11:40:16.327796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:16.327796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SQDsChlhyRRgd6JS64OEy0sUgv/tSiwJoSkOZ9bYgCvJr1Ytgfx1sKvEZTmFE7LuiY8ZDpF2bGwu2O1w3ZklBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:16.328264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:254f08a13d6c9ddfa7225b269674bc605cc2eb0dc94adcee31aad17292b95ffe","sha256:8db4682b463009bc2710f908ec057dc729571eb2c7ebef634fbe2f1a907ff57c"],"state_sha256":"722b5717f7e98c0444b8db2111440ed23f7d1fd20a75c4ce1c5bf7908467d7b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2Ylk0ltDgZ7exbYeYDL5PhPef9IcIABj9vCQide5zLSaoPLZn+Ax1aXBUIrLjYA6+xiOqq7mUd36yZiCc6nCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:58:25.120717Z","bundle_sha256":"070c15dcfd854bca01d308a5a11c6c8e4a1acc980835db0f54cf5f04e505be1e"}}