{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IE5FR6SYNSTBKC2KJXHNOZ5KTT","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":"7888a4f24bc61441ab41942ad851f0e2422a7bda5e915f5c4137cd398441d60a","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-17T17:09:21Z","title_canon_sha256":"2c32df4af21cfca84b0824f08dd7df8e875f0032dc5e8ade1e23ad84d0db8352"},"schema_version":"1.0","source":{"id":"2106.09660","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09660","created_at":"2026-07-05T02:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09660v2","created_at":"2026-07-05T02:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09660","created_at":"2026-07-05T02:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"IE5FR6SYNSTB","created_at":"2026-07-05T02:50:47Z"},{"alias_kind":"pith_short_16","alias_value":"IE5FR6SYNSTBKC2K","created_at":"2026-07-05T02:50:47Z"},{"alias_kind":"pith_short_8","alias_value":"IE5FR6SY","created_at":"2026-07-05T02:50:47Z"}],"graph_snapshots":[{"event_id":"sha256:6ce7984dd6215854121f27ea8c35215f2fd618be5e2dd5d8af9a1fc853ec7470","target":"graph","created_at":"2026-07-05T02:50:47Z","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/2106.09660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces WaveGrad 2, a non-autoregressive generative model for text-to-speech synthesis. WaveGrad 2 is trained to estimate the gradient of the log conditional density of the waveform given a phoneme sequence. The model takes an input phoneme sequence, and through an iterative refinement process, generates an audio waveform. This contrasts to the original WaveGrad vocoder which conditions on mel-spectrogram features, generated by a separate model. The iterative refinement process starts from Gaussian noise, and through a series of refinement steps (e.g., 50 steps), progressively re","authors_text":"Heiga Zen, Mohammad Norouzi, Najim Dehak, Nanxin Chen, Ron J. Weiss, William Chan, Yu Zhang","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-17T17:09:21Z","title":"WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09660","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":"sha256:35ee6637ed107210d945ffa2ef3dc09b101cedab801467c7f2ffc8fd377ecbf2","target":"record","created_at":"2026-07-05T02:50:47Z","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":"7888a4f24bc61441ab41942ad851f0e2422a7bda5e915f5c4137cd398441d60a","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-17T17:09:21Z","title_canon_sha256":"2c32df4af21cfca84b0824f08dd7df8e875f0032dc5e8ade1e23ad84d0db8352"},"schema_version":"1.0","source":{"id":"2106.09660","kind":"arxiv","version":2}},"canonical_sha256":"413a58fa586ca6150b4a4dced767aa9cd95fd5ac7849c388af11f2553372b239","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"413a58fa586ca6150b4a4dced767aa9cd95fd5ac7849c388af11f2553372b239","first_computed_at":"2026-07-05T02:50:47.877232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:47.877232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2APUmr7wXq6serjLYfXccC7cMIFEuJSce1P/o0OTEdXsU/PzGt4T4aVKtkeag5FGKB4jCoXQIYQlGZmrM87xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:47.877600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09660","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35ee6637ed107210d945ffa2ef3dc09b101cedab801467c7f2ffc8fd377ecbf2","sha256:6ce7984dd6215854121f27ea8c35215f2fd618be5e2dd5d8af9a1fc853ec7470"],"state_sha256":"8cdf3242c84b6bd310cb40aa7520bb034c2170818d6885b1704e2b73b4eda447"}