{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WIUPLPKWMHW4HEHUQWYLRF2NOU","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":"4af0ed086a670127dcb9977049b8767bbe7122eca488094c3537c55b5a705448","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T22:21:30Z","title_canon_sha256":"ce75d99e52fadac150f270602cbd853144941d4e9f76ee35ab2e7e659cd7be57"},"schema_version":"1.0","source":{"id":"2402.08093","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08093","created_at":"2026-07-05T07:45:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08093v2","created_at":"2026-07-05T07:45:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08093","created_at":"2026-07-05T07:45:33Z"},{"alias_kind":"pith_short_12","alias_value":"WIUPLPKWMHW4","created_at":"2026-07-05T07:45:33Z"},{"alias_kind":"pith_short_16","alias_value":"WIUPLPKWMHW4HEHU","created_at":"2026-07-05T07:45:33Z"},{"alias_kind":"pith_short_8","alias_value":"WIUPLPKW","created_at":"2026-07-05T07:45:33Z"}],"graph_snapshots":[{"event_id":"sha256:306dfcee638f09933f1206c2469250e819480396d3067546c4b100a8ba437b07","target":"graph","created_at":"2026-07-05T07:45:33Z","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/2402.08093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\\textbf{B}$ig $\\textbf{A}$daptive $\\textbf{S}$treamable TTS with $\\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes (\"speechcodes\") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are b","authors_text":"Adam Michalski, Alexis Moinet, \\'Alvaro Mart\\'in-Cortinas, Ammar Abbas, Arent van Korlaar, Arnaud Joly, Bartosz Putrycz, Elena Sokolova, Ewa Muszy\\'nska, Fan Yang, Fatih Beyhan, Guillermo C\\'ambara, Haohan Guo, Kayeon Yoo, Mateusz {\\L}ajszczak, Soledad L\\'opez Gambino, Sri Karlapati, Thomas Drugman, Yang Li","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T22:21:30Z","title":"BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08093","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":"sha256:56f7cc2ef07134292f9148899822ae2a317ccea42b1c6a84efd7035b20347506","target":"record","created_at":"2026-07-05T07:45:33Z","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":"4af0ed086a670127dcb9977049b8767bbe7122eca488094c3537c55b5a705448","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T22:21:30Z","title_canon_sha256":"ce75d99e52fadac150f270602cbd853144941d4e9f76ee35ab2e7e659cd7be57"},"schema_version":"1.0","source":{"id":"2402.08093","kind":"arxiv","version":2}},"canonical_sha256":"b228f5bd5661edc390f485b0b8974d752458c673ea8a96c0b6405508fea8d4ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b228f5bd5661edc390f485b0b8974d752458c673ea8a96c0b6405508fea8d4ad","first_computed_at":"2026-07-05T07:45:33.687050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:33.687050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IKxQNnDZoJwVFtpG8WG8g/dWCiNMroubLdyUPDtTvbpMHT5C3+XAiTZELu7EqrcO/scYnOdbRnQvHp7DCdHxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:33.687913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08093","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56f7cc2ef07134292f9148899822ae2a317ccea42b1c6a84efd7035b20347506","sha256:306dfcee638f09933f1206c2469250e819480396d3067546c4b100a8ba437b07"],"state_sha256":"c3b138cc9671ccec38a7c6135ebf012cc427dea1715c57c310119f54ab508ff8"}