{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UINQU6KYDTSWKPDV4YGVEXHSF5","short_pith_number":"pith:UINQU6KY","canonical_record":{"source":{"id":"2501.06320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T19:50:32Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"468528d502fa1a6cf877efbe314260fae4c7954e3343086eeae86f20bc6efb69","abstract_canon_sha256":"da434af765fd01c8557efc2acce86812a63b045d5b84566c48b19f1c3e056208"},"schema_version":"1.0"},"canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","source":{"kind":"arxiv","id":"2501.06320","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06320","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06320v1","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06320","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"UINQU6KYDTSW","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"pith_short_16","alias_value":"UINQU6KYDTSWKPDV","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"pith_short_8","alias_value":"UINQU6KY","created_at":"2026-07-05T10:49:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UINQU6KYDTSWKPDV4YGVEXHSF5","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T19:50:32Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"468528d502fa1a6cf877efbe314260fae4c7954e3343086eeae86f20bc6efb69","abstract_canon_sha256":"da434af765fd01c8557efc2acce86812a63b045d5b84566c48b19f1c3e056208"},"schema_version":"1.0"},"canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:12.863857Z","signature_b64":"uiScHsiFPhaf/zusWDnlvpCGb3oXaq/vomc3vGp+e+FR+y3B5Y7yd9pkvfrtJ9K/b4ludYk64eLriZnjFzy+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","last_reissued_at":"2026-07-05T10:49:12.863346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:12.863346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06320","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":"2026-07-05T10:49:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h72dT748dLwJnP3NT/hl5cSqJ6x8m9FexOIW4Yc7c2XtNFn/85hXKl8ahGGFZR9+vhNt/TddJhE0k+xLO15ACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:44:56.871198Z"},"content_sha256":"baebdb7453fa464f3af5b2561c28e8c8fa3f3443068ae8aa660c1fb1ee1ac81b","schema_version":"1.0","event_id":"sha256:baebdb7453fa464f3af5b2561c28e8c8fa3f3443068ae8aa660c1fb1ee1ac81b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UINQU6KYDTSWKPDV4YGVEXHSF5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jason Li, Subhankar Ghosh, Vitaly Lavrukhin, Vladimir Bataev","submitted_at":"2025-01-10T19:50:32Z","abstract_excerpt":"This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoiding using explicit duration predictors. Neural audio codecs efficiently compress audio into discrete codes, revealing the possibility of applying text modeling approaches to speech generation. However, the complexity of predicting multiple tokens per frame from several codebooks, as necessitated by a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06320","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/2501.06320/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":"2026-07-05T10:49:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5liRzvHsF3NzwjOrEl9JEMda6946a5mYOHA7vZgHstvAv9WT4NGjBXh1FjnCXgSCtyEpLee8A3Nw2S+H6G7CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:44:56.871591Z"},"content_sha256":"63eba62bcfff903cf52a748d1b12f3aecb155557b7c7a48b68b06dcc3cf0ecbf","schema_version":"1.0","event_id":"sha256:63eba62bcfff903cf52a748d1b12f3aecb155557b7c7a48b68b06dcc3cf0ecbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/bundle.json","state_url":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/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":"2026-07-07T12:44:56Z","links":{"resolver":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5","bundle":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/bundle.json","state":"https://pith.science/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UINQU6KYDTSWKPDV4YGVEXHSF5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UINQU6KYDTSWKPDV4YGVEXHSF5","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":"da434af765fd01c8557efc2acce86812a63b045d5b84566c48b19f1c3e056208","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T19:50:32Z","title_canon_sha256":"468528d502fa1a6cf877efbe314260fae4c7954e3343086eeae86f20bc6efb69"},"schema_version":"1.0","source":{"id":"2501.06320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06320","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06320v1","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06320","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"UINQU6KYDTSW","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"pith_short_16","alias_value":"UINQU6KYDTSWKPDV","created_at":"2026-07-05T10:49:12Z"},{"alias_kind":"pith_short_8","alias_value":"UINQU6KY","created_at":"2026-07-05T10:49:12Z"}],"graph_snapshots":[{"event_id":"sha256:63eba62bcfff903cf52a748d1b12f3aecb155557b7c7a48b68b06dcc3cf0ecbf","target":"graph","created_at":"2026-07-05T10:49:12Z","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/2501.06320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoiding using explicit duration predictors. Neural audio codecs efficiently compress audio into discrete codes, revealing the possibility of applying text modeling approaches to speech generation. However, the complexity of predicting multiple tokens per frame from several codebooks, as necessitated by a","authors_text":"Jason Li, Subhankar Ghosh, Vitaly Lavrukhin, Vladimir Bataev","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T19:50:32Z","title":"TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06320","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:baebdb7453fa464f3af5b2561c28e8c8fa3f3443068ae8aa660c1fb1ee1ac81b","target":"record","created_at":"2026-07-05T10:49:12Z","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":"da434af765fd01c8557efc2acce86812a63b045d5b84566c48b19f1c3e056208","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-10T19:50:32Z","title_canon_sha256":"468528d502fa1a6cf877efbe314260fae4c7954e3343086eeae86f20bc6efb69"},"schema_version":"1.0","source":{"id":"2501.06320","kind":"arxiv","version":1}},"canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a21b0a79581ce5653c75e60d525cf22f72120855a0b57dcb655a7f29417584a8","first_computed_at":"2026-07-05T10:49:12.863346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:12.863346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uiScHsiFPhaf/zusWDnlvpCGb3oXaq/vomc3vGp+e+FR+y3B5Y7yd9pkvfrtJ9K/b4ludYk64eLriZnjFzy+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:12.863857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baebdb7453fa464f3af5b2561c28e8c8fa3f3443068ae8aa660c1fb1ee1ac81b","sha256:63eba62bcfff903cf52a748d1b12f3aecb155557b7c7a48b68b06dcc3cf0ecbf"],"state_sha256":"1da2c34bffa0a70f681e72e27788ba70ec6c7ecc200de110a73a7fa92455a0df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"deex6DhYS1Wtbag/iiS6vO0E7qI4dhAIONSIJm8jHbvB5uBEFPGZSMEHludAric0fwj0klqUBSweQI1BGLPFDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:44:56.873540Z","bundle_sha256":"b3caabd89dc9afef77d5166535bb68c201473f0a8a8042fcf2325bb391d71988"}}