{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EIWIXE4OHTFD5UKUNYKFWQ56ZC","short_pith_number":"pith:EIWIXE4O","schema_version":"1.0","canonical_sha256":"222c8b938e3cca3ed1546e145b43bec89be45daa1b76bd73fafcce5e0b6113dc","source":{"kind":"arxiv","id":"2212.08703","version":1},"attestation_state":"computed","paper":{"title":"Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IT","cs.LG","math.IT"],"primary_cat":"eess.AS","authors_text":"Aleksandr Laptev, Boris Ginsburg","submitted_at":"2022-12-16T20:27:40Z","abstract_excerpt":"This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per unit and per word for Connectionist Temporal Classification (CTC) and Recurrent Neural Network Transducer (RNN-T) models. Proposed methods have similar computational complexity to the traditional method based on the maximum per-frame probability, but they are more adjustable, have a wider effective threshold range, and better push apart the confidence distribut"},"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":"2212.08703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-12-16T20:27:40Z","cross_cats_sorted":["cs.CL","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"e90ed09858b88024d57e3c10ff5d113b47f602cfdbc01dca9957d7a63c06a78b","abstract_canon_sha256":"9c06815112f1e994e27e4d3496a5785369ae541a110fe65ffa9c8657136afd86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:54.898738Z","signature_b64":"bRWX2JYZ4gcAXD81FAgv5WiSBl6FDEwW6vKGfjxJbhXLu722WSZtxGfM+CKgYbXnl1NycFR1NpRaJDRkkQZECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"222c8b938e3cca3ed1546e145b43bec89be45daa1b76bd73fafcce5e0b6113dc","last_reissued_at":"2026-07-05T05:39:54.898323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:54.898323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IT","cs.LG","math.IT"],"primary_cat":"eess.AS","authors_text":"Aleksandr Laptev, Boris Ginsburg","submitted_at":"2022-12-16T20:27:40Z","abstract_excerpt":"This paper presents a class of new fast non-trainable entropy-based confidence estimation methods for automatic speech recognition. We show how per-frame entropy values can be normalized and aggregated to obtain a confidence measure per unit and per word for Connectionist Temporal Classification (CTC) and Recurrent Neural Network Transducer (RNN-T) models. Proposed methods have similar computational complexity to the traditional method based on the maximum per-frame probability, but they are more adjustable, have a wider effective threshold range, and better push apart the confidence distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08703","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/2212.08703/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":"2212.08703","created_at":"2026-07-05T05:39:54.898379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08703v1","created_at":"2026-07-05T05:39:54.898379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08703","created_at":"2026-07-05T05:39:54.898379+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIWIXE4OHTFD","created_at":"2026-07-05T05:39:54.898379+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIWIXE4OHTFD5UKU","created_at":"2026-07-05T05:39:54.898379+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIWIXE4O","created_at":"2026-07-05T05:39:54.898379+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/EIWIXE4OHTFD5UKUNYKFWQ56ZC","json":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC.json","graph_json":"https://pith.science/api/pith-number/EIWIXE4OHTFD5UKUNYKFWQ56ZC/graph.json","events_json":"https://pith.science/api/pith-number/EIWIXE4OHTFD5UKUNYKFWQ56ZC/events.json","paper":"https://pith.science/paper/EIWIXE4O"},"agent_actions":{"view_html":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC","download_json":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC.json","view_paper":"https://pith.science/paper/EIWIXE4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08703&json=true","fetch_graph":"https://pith.science/api/pith-number/EIWIXE4OHTFD5UKUNYKFWQ56ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/EIWIXE4OHTFD5UKUNYKFWQ56ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC/action/storage_attestation","attest_author":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC/action/author_attestation","sign_citation":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC/action/citation_signature","submit_replication":"https://pith.science/pith/EIWIXE4OHTFD5UKUNYKFWQ56ZC/action/replication_record"}},"created_at":"2026-07-05T05:39:54.898379+00:00","updated_at":"2026-07-05T05:39:54.898379+00:00"}