{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BYS2AEVS5OFW7T4JJW2XIJNDEI","short_pith_number":"pith:BYS2AEVS","canonical_record":{"source":{"id":"2006.03575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-05T17:41:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"fe55bf676349841e553d96e4a5d9923f24fea2a05675b8d615598afb6661c287","abstract_canon_sha256":"d00efcd576c79cc65225c67763da7bb484f84b7901244566edeedac9e7d46a27"},"schema_version":"1.0"},"canonical_sha256":"0e25a012b2eb8b6fcf894db57425a32219134026e2070f3b531ff34dcc4885de","source":{"kind":"arxiv","id":"2006.03575","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03575","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03575v3","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03575","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"BYS2AEVS5OFW","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"BYS2AEVS5OFW7T4J","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"BYS2AEVS","created_at":"2026-07-05T02:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BYS2AEVS5OFW7T4JJW2XIJNDEI","target":"record","payload":{"canonical_record":{"source":{"id":"2006.03575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-05T17:41:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"fe55bf676349841e553d96e4a5d9923f24fea2a05675b8d615598afb6661c287","abstract_canon_sha256":"d00efcd576c79cc65225c67763da7bb484f84b7901244566edeedac9e7d46a27"},"schema_version":"1.0"},"canonical_sha256":"0e25a012b2eb8b6fcf894db57425a32219134026e2070f3b531ff34dcc4885de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:57.124200Z","signature_b64":"x2B8Vi9rPV7N2RqdOP/+BmyU1FtBIPTSyH/YAQrpOa0se0ZGhVNHyhKKDOAL1gDVmZLGJyrktNy4UL+xxYnIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e25a012b2eb8b6fcf894db57425a32219134026e2070f3b531ff34dcc4885de","last_reissued_at":"2026-07-05T02:23:57.123748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:57.123748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.03575","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iw/tITpMeUUBOD2kpH0z9xAknxd44P3TmitwXh04zD60sVynNwrkSLoUFxgjPLQfwRPCwUwPChE7RfzOwA2YDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:15.436656Z"},"content_sha256":"e7decc4b046da415f8bef6791e7aca70669e60656360d65d71745a5d6e29a1df","schema_version":"1.0","event_id":"sha256:e7decc4b046da415f8bef6791e7aca70669e60656360d65d71745a5d6e29a1df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BYS2AEVS5OFW7T4JJW2XIJNDEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Adversarial Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Erich Elsen, Jeff Donahue, Karen Simonyan, Miko{\\l}aj Bi\\'nkowski, Sander Dieleman","submitted_at":"2020-06-05T17:41:05Z","abstract_excerpt":"Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from normalised text or phonemes in an end-to-end manner, resulting in models which operate directly on character or phoneme input sequences and produce raw speech audio outputs. Our proposed generator is feed-forward and thus efficient for both training and inference, using a differentiable alignment scheme based on token length prediction. It learns to produce hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03575","kind":"arxiv","version":3},"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/2006.03575/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":"2026-07-05T02:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I4siUnXhc8ZZ1lEZ0UO5iEKW/cptPJT8/Z9LNHeqQTH1cnNNUUNm1Zq+am21XuZUo2kFwwMx884aylFcAIADAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:20:15.437186Z"},"content_sha256":"7cfe0d83787f7bc87bc79fe18186a64f23f03cdca979ed012ca5575063dc4ba1","schema_version":"1.0","event_id":"sha256:7cfe0d83787f7bc87bc79fe18186a64f23f03cdca979ed012ca5575063dc4ba1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI/bundle.json","state_url":"https://pith.science/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI/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":"2026-08-03T20:20:15Z","links":{"resolver":"https://pith.science/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI","bundle":"https://pith.science/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI/bundle.json","state":"https://pith.science/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BYS2AEVS5OFW7T4JJW2XIJNDEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BYS2AEVS5OFW7T4JJW2XIJNDEI","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":"d00efcd576c79cc65225c67763da7bb484f84b7901244566edeedac9e7d46a27","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-05T17:41:05Z","title_canon_sha256":"fe55bf676349841e553d96e4a5d9923f24fea2a05675b8d615598afb6661c287"},"schema_version":"1.0","source":{"id":"2006.03575","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03575","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03575v3","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03575","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"BYS2AEVS5OFW","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"BYS2AEVS5OFW7T4J","created_at":"2026-07-05T02:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"BYS2AEVS","created_at":"2026-07-05T02:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:7cfe0d83787f7bc87bc79fe18186a64f23f03cdca979ed012ca5575063dc4ba1","target":"graph","created_at":"2026-07-05T02:23:57Z","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/2006.03575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from normalised text or phonemes in an end-to-end manner, resulting in models which operate directly on character or phoneme input sequences and produce raw speech audio outputs. Our proposed generator is feed-forward and thus efficient for both training and inference, using a differentiable alignment scheme based on token length prediction. It learns to produce hig","authors_text":"Erich Elsen, Jeff Donahue, Karen Simonyan, Miko{\\l}aj Bi\\'nkowski, Sander Dieleman","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-05T17:41:05Z","title":"End-to-End Adversarial Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03575","kind":"arxiv","version":3},"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:e7decc4b046da415f8bef6791e7aca70669e60656360d65d71745a5d6e29a1df","target":"record","created_at":"2026-07-05T02:23:57Z","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":"d00efcd576c79cc65225c67763da7bb484f84b7901244566edeedac9e7d46a27","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-06-05T17:41:05Z","title_canon_sha256":"fe55bf676349841e553d96e4a5d9923f24fea2a05675b8d615598afb6661c287"},"schema_version":"1.0","source":{"id":"2006.03575","kind":"arxiv","version":3}},"canonical_sha256":"0e25a012b2eb8b6fcf894db57425a32219134026e2070f3b531ff34dcc4885de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e25a012b2eb8b6fcf894db57425a32219134026e2070f3b531ff34dcc4885de","first_computed_at":"2026-07-05T02:23:57.123748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:23:57.123748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x2B8Vi9rPV7N2RqdOP/+BmyU1FtBIPTSyH/YAQrpOa0se0ZGhVNHyhKKDOAL1gDVmZLGJyrktNy4UL+xxYnIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:23:57.124200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.03575","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7decc4b046da415f8bef6791e7aca70669e60656360d65d71745a5d6e29a1df","sha256:7cfe0d83787f7bc87bc79fe18186a64f23f03cdca979ed012ca5575063dc4ba1"],"state_sha256":"df7456779bc0a56817295f310a7fb5994af4a8a8f9f7e83c0eec3caba08c1ba0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzByL80Wj2Z+qJj2th/CgBT4AGHHorbz6/1dUeoWLvke/qjkJ1w00fzxYV3MWXjP9qnM2cLJUNzh6NQsTh6SBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:20:15.443070Z","bundle_sha256":"d1bd0eb788036e5f6ec307698ff0a55f8aba26e86b1cf5d45e6ad1274ac66bb5"}}