{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LZC43PAMHYG564HSKG33ZAOXJG","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":"d9d17a3130aa39ec806baa54453ae1165d7bd08e9d0b287581b9c97161a03ddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T09:16:14Z","title_canon_sha256":"1edd9e9ba034488d9461e47b5961c010b031697100734db5d352476a0aeeaa14"},"schema_version":"1.0","source":{"id":"2505.18609","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18609","created_at":"2026-07-05T11:10:38Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18609v2","created_at":"2026-07-05T11:10:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18609","created_at":"2026-07-05T11:10:38Z"},{"alias_kind":"pith_short_12","alias_value":"LZC43PAMHYG5","created_at":"2026-07-05T11:10:38Z"},{"alias_kind":"pith_short_16","alias_value":"LZC43PAMHYG564HS","created_at":"2026-07-05T11:10:38Z"},{"alias_kind":"pith_short_8","alias_value":"LZC43PAM","created_at":"2026-07-05T11:10:38Z"}],"graph_snapshots":[{"event_id":"sha256:5aeff2ddd1254f87bc0314b74392f5c893b3070da20fbcec2aa6f25038b7a0f3","target":"graph","created_at":"2026-07-05T11:10:38Z","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/2505.18609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce RASMALAI, a large-scale speech dataset with rich text descriptions, designed to advance controllable and expressive text-to-speech (TTS) synthesis for 23 Indian languages and English. It comprises 13,000 hours of speech and 24 million text-description annotations with fine-grained attributes like speaker identity, accent, emotion, style, and background conditions. Using RASMALAI, we develop IndicParlerTTS, the first open-source, text-description-guided TTS for Indian languages. Systematic evaluation demonstrates its ability to generate high-quality speech for named speakers, relia","authors_text":"Ashwin Sankar, Mitesh M Khapra, Praveen Srinivasa Varadhan, Sanchit Gandhi, Sherry Thomas, Yoach Lacombe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T09:16:14Z","title":"RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18609","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":"sha256:74b40ae94f06b03775a295da7321aa08670504fb762e85c8dfde5576367591f9","target":"record","created_at":"2026-07-05T11:10:38Z","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":"d9d17a3130aa39ec806baa54453ae1165d7bd08e9d0b287581b9c97161a03ddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T09:16:14Z","title_canon_sha256":"1edd9e9ba034488d9461e47b5961c010b031697100734db5d352476a0aeeaa14"},"schema_version":"1.0","source":{"id":"2505.18609","kind":"arxiv","version":2}},"canonical_sha256":"5e45cdbc0c3e0ddf70f251b7bc81d749ab1213437f52171d705b28d9298d5fe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e45cdbc0c3e0ddf70f251b7bc81d749ab1213437f52171d705b28d9298d5fe2","first_computed_at":"2026-07-05T11:10:38.298305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:38.298305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vrBdpZ5JVjEKrYkg5aIxS3JRS0NT1M+VmvtXbtkOnnWf4AMm8qUcVWRTR++QfCY2EDex2A6osIphH9ELySsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:38.298832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18609","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74b40ae94f06b03775a295da7321aa08670504fb762e85c8dfde5576367591f9","sha256:5aeff2ddd1254f87bc0314b74392f5c893b3070da20fbcec2aa6f25038b7a0f3"],"state_sha256":"189adcd7ab26c23949117e080a94efec2da66f295654ec7054244850e34b1d6e"}