{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LT3QH4IW2IUFPJKC4SJBG5RAWS","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":"69a5e62e3443288806254fbbe4c7001fe89e489096e7a26ddac3b04d134da977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T09:44:03Z","title_canon_sha256":"b32fca7258c46766f269ead942be635aa852a0e84ae6cf2e117ead4728d287f5"},"schema_version":"1.0","source":{"id":"2604.21481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.21481","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2604.21481v2","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.21481","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"LT3QH4IW2IUF","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"LT3QH4IW2IUFPJKC","created_at":"2026-06-24T01:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"LT3QH4IW","created_at":"2026-06-24T01:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:bf43f7608d845ceb3864fbea738fb23d69df43dbc28ea857f7d9e4da4ab2242c","target":"graph","created_at":"2026-06-24T01:14:27Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 120K pairwise comparisons from 1900 native raters, despite acknowledged high variance in speech perception, yield reliable signals for Bradley-Terry leaderboard construction and SHAP interpretation after linguistic controls."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A controlled pairwise evaluation framework for multilingual TTS in 10 Indic languages produces a preference leaderboard using Bradley-Terry modeling and SHAP analysis on 120K+ comparisons."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A controlled pairwise evaluation framework allows reliable ranking of TTS systems for ten Indian languages by collecting multi-dimensional judgments from native speakers."}],"snapshot_sha256":"78ddbe22e34efcfbd6aeda4f8831553801572dbf65a93b724d5671cf2e4378e7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T12:40:52.967609Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T00:57:11.414892Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.21481/integrity.json","findings":[],"snapshot_sha256":"dd694260007003f221b6225f442bb5a62a4a36988f4829e3c41d260416f51476","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to Speech(TTS) introduces high variance due to linguistic diversity and multidimensional nature of speech perception. We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation. Using 5K+ native and code-mixed sentences across 10 Indic languages, we evaluate 7 state-of-the-art TTS systems and collect over 120K pairwise comparisons from over 1900 native raters. In ","authors_text":"Aaditya Pareek, Adish Pandya, Ashwin Sankar, Deepon Halder, Gaurav Yadav, Ishvinder Sethi, Kartik Rajput, Mitesh M Khapra, Mohammed Safi Ur Rahman Khan, Nikhil Narasimhan, Praveen S V, Shobhit Banga, Srija Anand","cross_cats":[],"headline":"A controlled pairwise evaluation framework allows reliable ranking of TTS systems for ten Indian languages by collecting multi-dimensional judgments from native speakers.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T09:44:03Z","title":"Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.21481","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T22:04:56.068757Z","id":"cbff0601-a686-43d4-8b76-45aebeed7aa1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A controlled pairwise evaluation framework for multilingual TTS in 10 Indic languages produces a preference leaderboard using Bradley-Terry modeling and SHAP analysis on 120K+ comparisons.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A controlled pairwise evaluation framework allows reliable ranking of TTS systems for ten Indian languages by collecting multi-dimensional judgments from native speakers.","strongest_claim":"We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation.","weakest_assumption":"That the 120K pairwise comparisons from 1900 native raters, despite acknowledged high variance in speech perception, yield reliable signals for Bradley-Terry leaderboard construction and SHAP interpretation after linguistic controls."}},"verdict_id":"cbff0601-a686-43d4-8b76-45aebeed7aa1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5648bc2993c8f4949fe0e088dedb360b76ed9f7b402389f13e174ec3b72e277","target":"record","created_at":"2026-06-24T01:14:27Z","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":"69a5e62e3443288806254fbbe4c7001fe89e489096e7a26ddac3b04d134da977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-23T09:44:03Z","title_canon_sha256":"b32fca7258c46766f269ead942be635aa852a0e84ae6cf2e117ead4728d287f5"},"schema_version":"1.0","source":{"id":"2604.21481","kind":"arxiv","version":2}},"canonical_sha256":"5cf703f116d22857a542e492137620b49e1bd6337e10fde786a8e2faf9801d04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cf703f116d22857a542e492137620b49e1bd6337e10fde786a8e2faf9801d04","first_computed_at":"2026-06-24T01:14:27.920603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:27.920603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"awTqfTZZIqxvEsE+d4JGNm4NkF/oANpiPBTnR8tfgr9mi+r0gk/lfwKN+lJGGdLuTkGEsrpQ7lIRA+ZOmKtKAg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:27.921094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.21481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5648bc2993c8f4949fe0e088dedb360b76ed9f7b402389f13e174ec3b72e277","sha256:bf43f7608d845ceb3864fbea738fb23d69df43dbc28ea857f7d9e4da4ab2242c"],"state_sha256":"639b3a56a92f0142cc0888dec88afb60c9d2cadd8b4bb108049a820fd484d050"}