{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BCZGVNF2VJHXFO6NJSK5XN4HYN","short_pith_number":"pith:BCZGVNF2","schema_version":"1.0","canonical_sha256":"08b26ab4baaa4f72bbcd4c95dbb787c3592fea74f453707137b47433bb6e89b9","source":{"kind":"arxiv","id":"2505.23627","version":1},"attestation_state":"computed","paper":{"title":"Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dianna Yee, Griffin Dietz Smith, Jennifer King Chen, Leah Findlater","submitted_at":"2025-05-29T16:34:47Z","abstract_excerpt":"Identifying mistakes (i.e., miscues) made while reading aloud is commonly approached post-hoc by comparing automatic speech recognition (ASR) transcriptions to the target reading text. However, post-hoc methods perform poorly when ASR inaccurately transcribes verbatim speech. To improve on current methods for reading error annotation, we propose a novel end-to-end architecture that incorporates the target reading text via prompting and is trained for both improved verbatim transcription and direct miscue detection. Our contributions include: first, demonstrating that incorporating reading text"},"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":"2505.23627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T16:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"8afe9c968ac38b1d85ec29ff937dbb86c770ee4886ecfa9f92b784ad99ba4b59","abstract_canon_sha256":"f7e7d2b2f7ff13277aba7a08c1bc22de805aa4559b6f5fca60795a6ceff28a93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:04.927266Z","signature_b64":"E55ZE4O1FsVnh9E7Wt1wc4+9eOZnfc8JEkUBLna+dW2Lmvs1s0Z36Ls2DXAluDYFE4WPhv/PQMU515uw66k7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b26ab4baaa4f72bbcd4c95dbb787c3592fea74f453707137b47433bb6e89b9","last_reissued_at":"2026-07-05T11:12:04.926795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:04.926795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompting Whisper for Improved Verbatim Transcription and End-to-end Miscue Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dianna Yee, Griffin Dietz Smith, Jennifer King Chen, Leah Findlater","submitted_at":"2025-05-29T16:34:47Z","abstract_excerpt":"Identifying mistakes (i.e., miscues) made while reading aloud is commonly approached post-hoc by comparing automatic speech recognition (ASR) transcriptions to the target reading text. However, post-hoc methods perform poorly when ASR inaccurately transcribes verbatim speech. To improve on current methods for reading error annotation, we propose a novel end-to-end architecture that incorporates the target reading text via prompting and is trained for both improved verbatim transcription and direct miscue detection. Our contributions include: first, demonstrating that incorporating reading text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23627","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/2505.23627/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":"2505.23627","created_at":"2026-07-05T11:12:04.926844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23627v1","created_at":"2026-07-05T11:12:04.926844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23627","created_at":"2026-07-05T11:12:04.926844+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCZGVNF2VJHX","created_at":"2026-07-05T11:12:04.926844+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCZGVNF2VJHXFO6N","created_at":"2026-07-05T11:12:04.926844+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCZGVNF2","created_at":"2026-07-05T11:12:04.926844+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN","json":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN.json","graph_json":"https://pith.science/api/pith-number/BCZGVNF2VJHXFO6NJSK5XN4HYN/graph.json","events_json":"https://pith.science/api/pith-number/BCZGVNF2VJHXFO6NJSK5XN4HYN/events.json","paper":"https://pith.science/paper/BCZGVNF2"},"agent_actions":{"view_html":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN","download_json":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN.json","view_paper":"https://pith.science/paper/BCZGVNF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23627&json=true","fetch_graph":"https://pith.science/api/pith-number/BCZGVNF2VJHXFO6NJSK5XN4HYN/graph.json","fetch_events":"https://pith.science/api/pith-number/BCZGVNF2VJHXFO6NJSK5XN4HYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN/action/storage_attestation","attest_author":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN/action/author_attestation","sign_citation":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN/action/citation_signature","submit_replication":"https://pith.science/pith/BCZGVNF2VJHXFO6NJSK5XN4HYN/action/replication_record"}},"created_at":"2026-07-05T11:12:04.926844+00:00","updated_at":"2026-07-05T11:12:04.926844+00:00"}