{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KRV4RSGW5II2YYXPV5K4XPMI3P","short_pith_number":"pith:KRV4RSGW","canonical_record":{"source":{"id":"1703.10135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-29T16:55:13Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"1e88c28ca4a58545fccea024907587e8d3ed14a7ed91a4c3206b946e21690875","abstract_canon_sha256":"f93c43ec9b45696b8367c4fbd15bbc4e2be42b0cc0ffb8b4eba22c932247d738"},"schema_version":"1.0"},"canonical_sha256":"546bc8c8d6ea11ac62efaf55cbbd88dbd5ebecb0bab8aad066ae27f6cba74ccd","source":{"kind":"arxiv","id":"1703.10135","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10135","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10135v2","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10135","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"KRV4RSGW5II2","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KRV4RSGW5II2YYXP","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KRV4RSGW","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KRV4RSGW5II2YYXPV5K4XPMI3P","target":"record","payload":{"canonical_record":{"source":{"id":"1703.10135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-29T16:55:13Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"1e88c28ca4a58545fccea024907587e8d3ed14a7ed91a4c3206b946e21690875","abstract_canon_sha256":"f93c43ec9b45696b8367c4fbd15bbc4e2be42b0cc0ffb8b4eba22c932247d738"},"schema_version":"1.0"},"canonical_sha256":"546bc8c8d6ea11ac62efaf55cbbd88dbd5ebecb0bab8aad066ae27f6cba74ccd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:51.196935Z","signature_b64":"hd7nzDQTwri0GMzY+hT0s4Vu/21O+2xqWVrCj0RUNWKi8n29pqB44P3l/VbHw9aUFaxtThW9Ur+GNwX/THx/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"546bc8c8d6ea11ac62efaf55cbbd88dbd5ebecb0bab8aad066ae27f6cba74ccd","last_reissued_at":"2026-05-18T00:46:51.196230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:51.196230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.10135","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":"2026-05-18T00:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9GoUz4WSVwp+xdTaBzYUh0tDYDnSOipJdoTEUM1ZR/JKVutWRoP0wFwm9jxSCp5zXL7C+blWwnvO0oEYzBkNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:11:42.184635Z"},"content_sha256":"aae7b1045da34c7916c2f5bf8a0d9c33cd78969e6efd70cf2e4279a289dfc1ab","schema_version":"1.0","event_id":"sha256:aae7b1045da34c7916c2f5bf8a0d9c33cd78969e6efd70cf2e4279a289dfc1ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KRV4RSGW5II2YYXPV5K4XPMI3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tacotron: Towards End-to-End Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"cs.CL","authors_text":"Daisy Stanton, Navdeep Jaitly, Quoc Le, Rif A. Saurous, RJ Skerry-Ryan, Rob Clark, Ron J. Weiss, Samy Bengio, Yannis Agiomyrgiannakis, Ying Xiao, Yonghui Wu, Yuxuan Wang, Zhifeng Chen, Zongheng Yang","submitted_at":"2017-03-29T16:55:13Z","abstract_excerpt":"A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10135","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":""},"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":"2026-05-18T00:46:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+FzAKF2I6PQ+CNBm4jBkQlBE+rsFFVN3ekid9j+9o/xwKNtyrUjUNu7QgFj5Hg724N6RqbV0TjVdP54NxTygAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T00:11:42.185193Z"},"content_sha256":"27e9cdb034c0bac086b0030097b6e9c210a0d5ec3da7b0174940ea858edfcb9f","schema_version":"1.0","event_id":"sha256:27e9cdb034c0bac086b0030097b6e9c210a0d5ec3da7b0174940ea858edfcb9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KRV4RSGW5II2YYXPV5K4XPMI3P/bundle.json","state_url":"https://pith.science/pith/KRV4RSGW5II2YYXPV5K4XPMI3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KRV4RSGW5II2YYXPV5K4XPMI3P/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":"2026-05-30T00:11:42Z","links":{"resolver":"https://pith.science/pith/KRV4RSGW5II2YYXPV5K4XPMI3P","bundle":"https://pith.science/pith/KRV4RSGW5II2YYXPV5K4XPMI3P/bundle.json","state":"https://pith.science/pith/KRV4RSGW5II2YYXPV5K4XPMI3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KRV4RSGW5II2YYXPV5K4XPMI3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KRV4RSGW5II2YYXPV5K4XPMI3P","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":"f93c43ec9b45696b8367c4fbd15bbc4e2be42b0cc0ffb8b4eba22c932247d738","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-29T16:55:13Z","title_canon_sha256":"1e88c28ca4a58545fccea024907587e8d3ed14a7ed91a4c3206b946e21690875"},"schema_version":"1.0","source":{"id":"1703.10135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.10135","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"arxiv_version","alias_value":"1703.10135v2","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10135","created_at":"2026-05-18T00:46:51Z"},{"alias_kind":"pith_short_12","alias_value":"KRV4RSGW5II2","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"KRV4RSGW5II2YYXP","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"KRV4RSGW","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:27e9cdb034c0bac086b0030097b6e9c210a0d5ec3da7b0174940ea858edfcb9f","target":"graph","created_at":"2026-05-18T00:46:51Z","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"},"paper":{"abstract_excerpt":"A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this c","authors_text":"Daisy Stanton, Navdeep Jaitly, Quoc Le, Rif A. Saurous, RJ Skerry-Ryan, Rob Clark, Ron J. Weiss, Samy Bengio, Yannis Agiomyrgiannakis, Ying Xiao, Yonghui Wu, Yuxuan Wang, Zhifeng Chen, Zongheng Yang","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-29T16:55:13Z","title":"Tacotron: Towards End-to-End Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10135","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:aae7b1045da34c7916c2f5bf8a0d9c33cd78969e6efd70cf2e4279a289dfc1ab","target":"record","created_at":"2026-05-18T00:46:51Z","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":"f93c43ec9b45696b8367c4fbd15bbc4e2be42b0cc0ffb8b4eba22c932247d738","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-29T16:55:13Z","title_canon_sha256":"1e88c28ca4a58545fccea024907587e8d3ed14a7ed91a4c3206b946e21690875"},"schema_version":"1.0","source":{"id":"1703.10135","kind":"arxiv","version":2}},"canonical_sha256":"546bc8c8d6ea11ac62efaf55cbbd88dbd5ebecb0bab8aad066ae27f6cba74ccd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"546bc8c8d6ea11ac62efaf55cbbd88dbd5ebecb0bab8aad066ae27f6cba74ccd","first_computed_at":"2026-05-18T00:46:51.196230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:51.196230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hd7nzDQTwri0GMzY+hT0s4Vu/21O+2xqWVrCj0RUNWKi8n29pqB44P3l/VbHw9aUFaxtThW9Ur+GNwX/THx/Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:51.196935Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.10135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aae7b1045da34c7916c2f5bf8a0d9c33cd78969e6efd70cf2e4279a289dfc1ab","sha256:27e9cdb034c0bac086b0030097b6e9c210a0d5ec3da7b0174940ea858edfcb9f"],"state_sha256":"e8393f008a946e9a6c3e30cd6dea2203767fd2335f29b44f5e57779276c9c880"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9mLpqHfy32Jsmdkm5M7nCuVByemn324Ond5WmjpFWjBQe9L9Tb+hsNAaEI2xTOMjYoay7rh/6lkHi/vUrRoYBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T00:11:42.189628Z","bundle_sha256":"7413d9bf087abc260a0c8308a2ffde62bda64b2792583be5cf7de0e3fd980f8e"}}