{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YTYZQBHNFNT3YSOA2SHKS5W6KM","short_pith_number":"pith:YTYZQBHN","schema_version":"1.0","canonical_sha256":"c4f19804ed2b67bc49c0d48ea976de533b40004062642704bf3c15b2187e14a9","source":{"kind":"arxiv","id":"2605.20712","version":1},"attestation_state":"computed","paper":{"title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arghya Bhattacharya, Kavya Manohar, Kumarmanas Nethil, Kush Juvekar","submitted_at":"2026-05-20T05:09:01Z","abstract_excerpt":"Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixing a misrecognized domain term costs far more than inserting a comma. Word error rate (WER) fails on two fronts: it collapses distinct error categories into a single scalar, and it structurally penalizes agglutinative languages where valid sandhi merges inflate scores. We introduce SCRIBE, a diagnostic framework that provides categorical error decomposition into lexical, punctuation, numeral, and domain-entity rates through sandhi-tolerant align"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.20712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T05:09:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56ae632520fea9bc9c0c6d0c6779c85d95030060831627b8eca1dd7859a65f33","abstract_canon_sha256":"ec376b93524374cac9970f8a928cc1b4977d7dd04303874c93e08b76a000bbfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:50.374618Z","signature_b64":"Ci6tAScTaau8K+htSNcjhcqoAAvAJyUH4idvTxCO+6s3qzNWJFswRtc3bgcTgQ7lK6g85EPY2rHIxIboeAL6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f19804ed2b67bc49c0d48ea976de533b40004062642704bf3c15b2187e14a9","last_reissued_at":"2026-05-21T01:04:50.373959Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:50.373959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arghya Bhattacharya, Kavya Manohar, Kumarmanas Nethil, Kush Juvekar","submitted_at":"2026-05-20T05:09:01Z","abstract_excerpt":"Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixing a misrecognized domain term costs far more than inserting a comma. Word error rate (WER) fails on two fronts: it collapses distinct error categories into a single scalar, and it structurally penalizes agglutinative languages where valid sandhi merges inflate scores. We introduce SCRIBE, a diagnostic framework that provides categorical error decomposition into lexical, punctuation, numeral, and domain-entity rates through sandhi-tolerant align"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20712","kind":"arxiv","version":1},"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/2605.20712/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.20712","created_at":"2026-05-21T01:04:50.374056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20712v1","created_at":"2026-05-21T01:04:50.374056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20712","created_at":"2026-05-21T01:04:50.374056+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTYZQBHNFNT3","created_at":"2026-05-21T01:04:50.374056+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTYZQBHNFNT3YSOA","created_at":"2026-05-21T01:04:50.374056+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTYZQBHN","created_at":"2026-05-21T01:04:50.374056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20712","citing_title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM","json":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM.json","graph_json":"https://pith.science/api/pith-number/YTYZQBHNFNT3YSOA2SHKS5W6KM/graph.json","events_json":"https://pith.science/api/pith-number/YTYZQBHNFNT3YSOA2SHKS5W6KM/events.json","paper":"https://pith.science/paper/YTYZQBHN"},"agent_actions":{"view_html":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM","download_json":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM.json","view_paper":"https://pith.science/paper/YTYZQBHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20712&json=true","fetch_graph":"https://pith.science/api/pith-number/YTYZQBHNFNT3YSOA2SHKS5W6KM/graph.json","fetch_events":"https://pith.science/api/pith-number/YTYZQBHNFNT3YSOA2SHKS5W6KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM/action/storage_attestation","attest_author":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM/action/author_attestation","sign_citation":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM/action/citation_signature","submit_replication":"https://pith.science/pith/YTYZQBHNFNT3YSOA2SHKS5W6KM/action/replication_record"}},"created_at":"2026-05-21T01:04:50.374056+00:00","updated_at":"2026-05-21T01:04:50.374056+00:00"}