{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SNYC2IEVGM3AUDYTH72MLMDRFO","short_pith_number":"pith:SNYC2IEV","canonical_record":{"source":{"id":"2505.07916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:25:20Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"12d5c94147c5895eb6f16b393914ff24d5119329befcc69658aa000ea1fa38d5","abstract_canon_sha256":"97b1151ff722c462ec38d98151926c34fa6098b7d33523bc2a7a5fec1cb2082d"},"schema_version":"1.0"},"canonical_sha256":"93702d209533360a0f133ff4c5b0712bbb90c4c01e1ab03ddead12ac18a81a2d","source":{"kind":"arxiv","id":"2505.07916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07916","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07916v1","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07916","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"SNYC2IEVGM3A","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"SNYC2IEVGM3AUDYT","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"SNYC2IEV","created_at":"2026-07-05T11:01:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SNYC2IEVGM3AUDYTH72MLMDRFO","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:25:20Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"12d5c94147c5895eb6f16b393914ff24d5119329befcc69658aa000ea1fa38d5","abstract_canon_sha256":"97b1151ff722c462ec38d98151926c34fa6098b7d33523bc2a7a5fec1cb2082d"},"schema_version":"1.0"},"canonical_sha256":"93702d209533360a0f133ff4c5b0712bbb90c4c01e1ab03ddead12ac18a81a2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:59.616825Z","signature_b64":"s5hAKGU7OAGurpL0n1Oe1iMHsuf7iBHC6pXfdirPcNiMzBydU8OBC1NdgxtTZ/QfRrloywHNr1i/+eEkSYGPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93702d209533360a0f133ff4c5b0712bbb90c4c01e1ab03ddead12ac18a81a2d","last_reissued_at":"2026-07-05T11:01:59.616275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:59.616275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07916","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":"2026-07-05T11:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I143PykQv70v+a4kpNwZJ8as9F5pz2/O4GUtFFaSHjlSyb5LlvpGtBBc8VatwCHh/mRv2ZUbFC6/NVzfzhQ1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:57:55.525117Z"},"content_sha256":"7321857d30ee07875df540046cfc150b0ec9d4eda631717e6004522cad692aab","schema_version":"1.0","event_id":"sha256:7321857d30ee07875df540046cfc150b0ec9d4eda631717e6004522cad692aab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SNYC2IEVGM3AUDYTH72MLMDRFO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bowen Zhang, Congchao Guo, Geng Yang, Hang Yu, Haozhe Zhang, Heidi Lei, Jialong Mai, Junjie Yan, Kaiyue Yang, Mingqi Yang, Peikai Huang, Ruiyang Jin, Sitan Jiang, Weihua Cheng, Yawei Li, Yichen Xiao, Yiying Zhou, Yongmao Zhang, Yuan Lu, Yucen He","submitted_at":"2025-05-12T14:25:20Z","abstract_excerpt":"We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without requiring its transcription. This enables MiniMax-Speech to produce highly expressive speech with timbre consistent with the reference in a zero-shot manner, while also supporting one-shot voice cloning with exceptionally high similarity to the reference voice. In addition, the overall quality of the synthesized audio is enhanced through the proposed Flow-V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07916","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/2505.07916/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":"2026-07-05T11:01:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRGTpUl1htxGsZNe2Q3IYWGbj3cpkQXxK6ti0hZXFcZllzgDZZOfXPE+TRBItCnaQSvr4gDLeOdAeAVGxbSyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:57:55.525675Z"},"content_sha256":"0407ab2154bb43d515f88afc72e69f8c271f98772efc58e8cf7975bc0aaa0dc0","schema_version":"1.0","event_id":"sha256:0407ab2154bb43d515f88afc72e69f8c271f98772efc58e8cf7975bc0aaa0dc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNYC2IEVGM3AUDYTH72MLMDRFO/bundle.json","state_url":"https://pith.science/pith/SNYC2IEVGM3AUDYTH72MLMDRFO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNYC2IEVGM3AUDYTH72MLMDRFO/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":"2026-08-04T19:57:55Z","links":{"resolver":"https://pith.science/pith/SNYC2IEVGM3AUDYTH72MLMDRFO","bundle":"https://pith.science/pith/SNYC2IEVGM3AUDYTH72MLMDRFO/bundle.json","state":"https://pith.science/pith/SNYC2IEVGM3AUDYTH72MLMDRFO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNYC2IEVGM3AUDYTH72MLMDRFO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SNYC2IEVGM3AUDYTH72MLMDRFO","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":"97b1151ff722c462ec38d98151926c34fa6098b7d33523bc2a7a5fec1cb2082d","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:25:20Z","title_canon_sha256":"12d5c94147c5895eb6f16b393914ff24d5119329befcc69658aa000ea1fa38d5"},"schema_version":"1.0","source":{"id":"2505.07916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07916","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07916v1","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07916","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_12","alias_value":"SNYC2IEVGM3A","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_16","alias_value":"SNYC2IEVGM3AUDYT","created_at":"2026-07-05T11:01:59Z"},{"alias_kind":"pith_short_8","alias_value":"SNYC2IEV","created_at":"2026-07-05T11:01:59Z"}],"graph_snapshots":[{"event_id":"sha256:0407ab2154bb43d515f88afc72e69f8c271f98772efc58e8cf7975bc0aaa0dc0","target":"graph","created_at":"2026-07-05T11:01:59Z","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/2505.07916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without requiring its transcription. This enables MiniMax-Speech to produce highly expressive speech with timbre consistent with the reference in a zero-shot manner, while also supporting one-shot voice cloning with exceptionally high similarity to the reference voice. In addition, the overall quality of the synthesized audio is enhanced through the proposed Flow-V","authors_text":"Bowen Zhang, Congchao Guo, Geng Yang, Hang Yu, Haozhe Zhang, Heidi Lei, Jialong Mai, Junjie Yan, Kaiyue Yang, Mingqi Yang, Peikai Huang, Ruiyang Jin, Sitan Jiang, Weihua Cheng, Yawei Li, Yichen Xiao, Yiying Zhou, Yongmao Zhang, Yuan Lu, Yucen He","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:25:20Z","title":"MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07916","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":"sha256:7321857d30ee07875df540046cfc150b0ec9d4eda631717e6004522cad692aab","target":"record","created_at":"2026-07-05T11:01:59Z","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":"97b1151ff722c462ec38d98151926c34fa6098b7d33523bc2a7a5fec1cb2082d","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-12T14:25:20Z","title_canon_sha256":"12d5c94147c5895eb6f16b393914ff24d5119329befcc69658aa000ea1fa38d5"},"schema_version":"1.0","source":{"id":"2505.07916","kind":"arxiv","version":1}},"canonical_sha256":"93702d209533360a0f133ff4c5b0712bbb90c4c01e1ab03ddead12ac18a81a2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93702d209533360a0f133ff4c5b0712bbb90c4c01e1ab03ddead12ac18a81a2d","first_computed_at":"2026-07-05T11:01:59.616275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:59.616275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s5hAKGU7OAGurpL0n1Oe1iMHsuf7iBHC6pXfdirPcNiMzBydU8OBC1NdgxtTZ/QfRrloywHNr1i/+eEkSYGPAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:59.616825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7321857d30ee07875df540046cfc150b0ec9d4eda631717e6004522cad692aab","sha256:0407ab2154bb43d515f88afc72e69f8c271f98772efc58e8cf7975bc0aaa0dc0"],"state_sha256":"9cd889e8393003a1c3a90d6bb68353efc0c8d9b51e3222a790681c6c0e93b39a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FMBuPIOqu2mA+b82WLSmjefmj24JM+PmqUMwx5s1tIw8o8MriT2CFQkbC99057Oh+bGzzPQfan6p4pdEWyeDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:57:55.529411Z","bundle_sha256":"037d998b97ac14137130ffb39b4d95b0bfa898cfd419dfb3a39d2388b4b32ff2"}}