{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6KLUMZDH5IJNPF3E54U5MTY3LA","short_pith_number":"pith:6KLUMZDH","canonical_record":{"source":{"id":"2110.03584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T16:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"5948090c759f9d1aa155c656bc3af2113928a9108313dc608231a2351daff6e4","abstract_canon_sha256":"77dfd3f0fac31fa49a0489321954a299f3c388aee03604fd6b315d1ba3bbb032"},"schema_version":"1.0"},"canonical_sha256":"f297466467ea12d79764ef29d64f1b5829537dcf9674975d19e33d4aeef174eb","source":{"kind":"arxiv","id":"2110.03584","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03584","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03584v2","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03584","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"6KLUMZDH5IJN","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"pith_short_16","alias_value":"6KLUMZDH5IJNPF3E","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"pith_short_8","alias_value":"6KLUMZDH","created_at":"2026-07-05T03:24:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6KLUMZDH5IJNPF3E54U5MTY3LA","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T16:07:58Z","cross_cats_sorted":[],"title_canon_sha256":"5948090c759f9d1aa155c656bc3af2113928a9108313dc608231a2351daff6e4","abstract_canon_sha256":"77dfd3f0fac31fa49a0489321954a299f3c388aee03604fd6b315d1ba3bbb032"},"schema_version":"1.0"},"canonical_sha256":"f297466467ea12d79764ef29d64f1b5829537dcf9674975d19e33d4aeef174eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:45.396150Z","signature_b64":"zRKs7o2JOC2ViVeAdauoTB2rrpp/r4NM9QpsrDK52iNRoWMam0riX770rU9DziHtu2avemSQgRqrsIbR/sTdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f297466467ea12d79764ef29d64f1b5829537dcf9674975d19e33d4aeef174eb","last_reissued_at":"2026-07-05T03:24:45.395642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:45.395642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03584","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":"2026-07-05T03:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9JGyWcnwPGFP0oPPNPoXwxDfKwWzdJMabs/WObHtHE35tCiA2r9IOCC5yZCqAmJtVx6DYj+6yGvzGbVAcXp8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:26:02.797730Z"},"content_sha256":"aea59a320456fe3899cd9c865002ddbf87cf16ca3f22dfe7a363e069693e581b","schema_version":"1.0","event_id":"sha256:aea59a320456fe3899cd9c865002ddbf87cf16ca3f22dfe7a363e069693e581b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6KLUMZDH5IJNPF3E54U5MTY3LA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Oktai Tatanov, Stanislav Beliaev","submitted_at":"2021-10-07T16:07:58Z","abstract_excerpt":"This paper describes Mixer-TTS, a non-autoregressive model for mel-spectrogram generation. The model is based on the MLP-Mixer architecture adapted for speech synthesis. The basic Mixer-TTS contains pitch and duration predictors, with the latter being trained with an unsupervised TTS alignment framework. Alongside the basic model, we propose the extended version which additionally uses token embeddings from a pre-trained language model. Basic Mixer-TTS and its extended version achieve a mean opinion score (MOS) of 4.05 and 4.11, respectively, compared to a MOS of 4.27 of original LJSpeech samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03584","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/2110.03584/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":"2026-07-05T03:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BR02/sXaTJkOggYGV07MfhIGioayxYfU3D9SRsQGwN/73inttuN3SU2VunIX/ByKLNLVVGug+onSoO5tcXOhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:26:02.799987Z"},"content_sha256":"268caa673f7c344953c0d8df66f6f265c746a90c22295d9a6dfc8dc3fb69d720","schema_version":"1.0","event_id":"sha256:268caa673f7c344953c0d8df66f6f265c746a90c22295d9a6dfc8dc3fb69d720"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KLUMZDH5IJNPF3E54U5MTY3LA/bundle.json","state_url":"https://pith.science/pith/6KLUMZDH5IJNPF3E54U5MTY3LA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KLUMZDH5IJNPF3E54U5MTY3LA/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":"2026-07-31T13:26:02Z","links":{"resolver":"https://pith.science/pith/6KLUMZDH5IJNPF3E54U5MTY3LA","bundle":"https://pith.science/pith/6KLUMZDH5IJNPF3E54U5MTY3LA/bundle.json","state":"https://pith.science/pith/6KLUMZDH5IJNPF3E54U5MTY3LA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KLUMZDH5IJNPF3E54U5MTY3LA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6KLUMZDH5IJNPF3E54U5MTY3LA","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":"77dfd3f0fac31fa49a0489321954a299f3c388aee03604fd6b315d1ba3bbb032","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T16:07:58Z","title_canon_sha256":"5948090c759f9d1aa155c656bc3af2113928a9108313dc608231a2351daff6e4"},"schema_version":"1.0","source":{"id":"2110.03584","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03584","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03584v2","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03584","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"6KLUMZDH5IJN","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"pith_short_16","alias_value":"6KLUMZDH5IJNPF3E","created_at":"2026-07-05T03:24:45Z"},{"alias_kind":"pith_short_8","alias_value":"6KLUMZDH","created_at":"2026-07-05T03:24:45Z"}],"graph_snapshots":[{"event_id":"sha256:268caa673f7c344953c0d8df66f6f265c746a90c22295d9a6dfc8dc3fb69d720","target":"graph","created_at":"2026-07-05T03:24:45Z","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/2110.03584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes Mixer-TTS, a non-autoregressive model for mel-spectrogram generation. The model is based on the MLP-Mixer architecture adapted for speech synthesis. The basic Mixer-TTS contains pitch and duration predictors, with the latter being trained with an unsupervised TTS alignment framework. Alongside the basic model, we propose the extended version which additionally uses token embeddings from a pre-trained language model. Basic Mixer-TTS and its extended version achieve a mean opinion score (MOS) of 4.05 and 4.11, respectively, compared to a MOS of 4.27 of original LJSpeech samp","authors_text":"Boris Ginsburg, Oktai Tatanov, Stanislav Beliaev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T16:07:58Z","title":"Mixer-TTS: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03584","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:aea59a320456fe3899cd9c865002ddbf87cf16ca3f22dfe7a363e069693e581b","target":"record","created_at":"2026-07-05T03:24:45Z","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":"77dfd3f0fac31fa49a0489321954a299f3c388aee03604fd6b315d1ba3bbb032","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-07T16:07:58Z","title_canon_sha256":"5948090c759f9d1aa155c656bc3af2113928a9108313dc608231a2351daff6e4"},"schema_version":"1.0","source":{"id":"2110.03584","kind":"arxiv","version":2}},"canonical_sha256":"f297466467ea12d79764ef29d64f1b5829537dcf9674975d19e33d4aeef174eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f297466467ea12d79764ef29d64f1b5829537dcf9674975d19e33d4aeef174eb","first_computed_at":"2026-07-05T03:24:45.395642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:45.395642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zRKs7o2JOC2ViVeAdauoTB2rrpp/r4NM9QpsrDK52iNRoWMam0riX770rU9DziHtu2avemSQgRqrsIbR/sTdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:45.396150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03584","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aea59a320456fe3899cd9c865002ddbf87cf16ca3f22dfe7a363e069693e581b","sha256:268caa673f7c344953c0d8df66f6f265c746a90c22295d9a6dfc8dc3fb69d720"],"state_sha256":"8f182ee010d40ec6768a720bdd5ceb713ba51f3fdf3be790e99cecf04939746b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6h/UHxPZyO9Jv5yCf8o4/HE3M1Vv8G4zLbXznctR5cdS5A9wq7wlsedgVj2O4tyoN5YBMeH2n+p8ew9MC2s8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:26:02.810847Z","bundle_sha256":"f7233ea9f909d3b0d3ccb10874aceaee0a5fb34c876a8bdae0c4273c0f373d56"}}