{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O6DUJDZWWLIBRX2DERY4PJNHL4","short_pith_number":"pith:O6DUJDZW","schema_version":"1.0","canonical_sha256":"7787448f36b2d018df432471c7a5a75f3117d59eaf0da4a63883881b6a92eb3e","source":{"kind":"arxiv","id":"2407.16537","version":2},"attestation_state":"computed","paper":{"title":"Quantifying the Role of Textual Predictability in Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ewan Dunbar, Gerald Penn, Sean Robertson","submitted_at":"2024-07-23T14:47:25Z","abstract_excerpt":"A long-standing question in automatic speech recognition research is how to attribute errors to the ability of a model to model the acoustics, versus its ability to leverage higher-order context (lexicon, morphology, syntax, semantics). We validate a novel approach which models error rates as a function of relative textual predictability, and yields a single number, $k$, which measures the effect of textual predictability on the recognizer. We use this method to demonstrate that a Wav2Vec 2.0-based model makes greater stronger use of textual context than a hybrid ASR model, in spite of not usi"},"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":"2407.16537","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T14:47:25Z","cross_cats_sorted":[],"title_canon_sha256":"54502b7f750695f1834221e1d6292e7c002e7d0526f95e6ca5a7d59092283b77","abstract_canon_sha256":"7fb105efd30c2ab71d04fd5c054d0167ac2b1ddee3bfdc333f63826eb5dd846f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:19.839633Z","signature_b64":"4C0QMwBhn7CD+KVpTzuxjBA1x3CSdpWhh2TKc2syJfdXWYXPmiePpqRFqhIES7pgwsr+32Qcd2pt3xANJU7fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7787448f36b2d018df432471c7a5a75f3117d59eaf0da4a63883881b6a92eb3e","last_reissued_at":"2026-07-05T09:16:19.839139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:19.839139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Role of Textual Predictability in Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ewan Dunbar, Gerald Penn, Sean Robertson","submitted_at":"2024-07-23T14:47:25Z","abstract_excerpt":"A long-standing question in automatic speech recognition research is how to attribute errors to the ability of a model to model the acoustics, versus its ability to leverage higher-order context (lexicon, morphology, syntax, semantics). We validate a novel approach which models error rates as a function of relative textual predictability, and yields a single number, $k$, which measures the effect of textual predictability on the recognizer. We use this method to demonstrate that a Wav2Vec 2.0-based model makes greater stronger use of textual context than a hybrid ASR model, in spite of not usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16537","kind":"arxiv","version":2},"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/2407.16537/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":"2407.16537","created_at":"2026-07-05T09:16:19.839205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16537v2","created_at":"2026-07-05T09:16:19.839205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16537","created_at":"2026-07-05T09:16:19.839205+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6DUJDZWWLIB","created_at":"2026-07-05T09:16:19.839205+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6DUJDZWWLIBRX2D","created_at":"2026-07-05T09:16:19.839205+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6DUJDZW","created_at":"2026-07-05T09:16:19.839205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12979","citing_title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4","json":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4.json","graph_json":"https://pith.science/api/pith-number/O6DUJDZWWLIBRX2DERY4PJNHL4/graph.json","events_json":"https://pith.science/api/pith-number/O6DUJDZWWLIBRX2DERY4PJNHL4/events.json","paper":"https://pith.science/paper/O6DUJDZW"},"agent_actions":{"view_html":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4","download_json":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4.json","view_paper":"https://pith.science/paper/O6DUJDZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16537&json=true","fetch_graph":"https://pith.science/api/pith-number/O6DUJDZWWLIBRX2DERY4PJNHL4/graph.json","fetch_events":"https://pith.science/api/pith-number/O6DUJDZWWLIBRX2DERY4PJNHL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4/action/storage_attestation","attest_author":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4/action/author_attestation","sign_citation":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4/action/citation_signature","submit_replication":"https://pith.science/pith/O6DUJDZWWLIBRX2DERY4PJNHL4/action/replication_record"}},"created_at":"2026-07-05T09:16:19.839205+00:00","updated_at":"2026-07-05T09:16:19.839205+00:00"}