{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BBCSJ3TLGWEKSY64AC45Z6GOVE","short_pith_number":"pith:BBCSJ3TL","schema_version":"1.0","canonical_sha256":"084524ee6b3588a963dc00b9dcf8cea90eefa5027243caab64afbc8c22152379","source":{"kind":"arxiv","id":"2306.06892","version":1},"attestation_state":"computed","paper":{"title":"On the N-gram Approximation of Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aravind Krishnan, Dietrich Klakow, Jesujoba Alabi","submitted_at":"2023-06-12T06:42:08Z","abstract_excerpt":"Large pre-trained language models (PLMs) have shown remarkable performance across various natural language understanding (NLU) tasks, particularly in low-resource settings. Nevertheless, their potential in Automatic Speech Recognition (ASR) remains largely unexplored. This study investigates the potential usage of PLMs for language modelling in ASR. We compare the application of large-scale text sampling and probability conversion for approximating GPT-2 into an n-gram model. Furthermore, we introduce a vocabulary-restricted decoding method for random sampling, and evaluate the effects of doma"},"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":"2306.06892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T06:42:08Z","cross_cats_sorted":[],"title_canon_sha256":"0b443d6692fdaac79b3a693d29f20199b59c2a9229b7741d29b88d7818318c7c","abstract_canon_sha256":"e026b455b829e00f0741effe630766399382aa1a0858e4611d7756513f206538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:45.333873Z","signature_b64":"2zlC7XHn3yKwyq1cegdVAC2x6WiejKO87mM+Xt510qafzMeY8yKgUtwZ5tLlEijtcFisYVvopNwjezHSvp5pCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"084524ee6b3588a963dc00b9dcf8cea90eefa5027243caab64afbc8c22152379","last_reissued_at":"2026-07-05T06:19:45.333484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:45.333484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the N-gram Approximation of Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aravind Krishnan, Dietrich Klakow, Jesujoba Alabi","submitted_at":"2023-06-12T06:42:08Z","abstract_excerpt":"Large pre-trained language models (PLMs) have shown remarkable performance across various natural language understanding (NLU) tasks, particularly in low-resource settings. Nevertheless, their potential in Automatic Speech Recognition (ASR) remains largely unexplored. This study investigates the potential usage of PLMs for language modelling in ASR. We compare the application of large-scale text sampling and probability conversion for approximating GPT-2 into an n-gram model. Furthermore, we introduce a vocabulary-restricted decoding method for random sampling, and evaluate the effects of doma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06892","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/2306.06892/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":"2306.06892","created_at":"2026-07-05T06:19:45.333538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06892v1","created_at":"2026-07-05T06:19:45.333538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06892","created_at":"2026-07-05T06:19:45.333538+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBCSJ3TLGWEK","created_at":"2026-07-05T06:19:45.333538+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBCSJ3TLGWEKSY64","created_at":"2026-07-05T06:19:45.333538+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBCSJ3TL","created_at":"2026-07-05T06:19:45.333538+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/BBCSJ3TLGWEKSY64AC45Z6GOVE","json":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE.json","graph_json":"https://pith.science/api/pith-number/BBCSJ3TLGWEKSY64AC45Z6GOVE/graph.json","events_json":"https://pith.science/api/pith-number/BBCSJ3TLGWEKSY64AC45Z6GOVE/events.json","paper":"https://pith.science/paper/BBCSJ3TL"},"agent_actions":{"view_html":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE","download_json":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE.json","view_paper":"https://pith.science/paper/BBCSJ3TL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06892&json=true","fetch_graph":"https://pith.science/api/pith-number/BBCSJ3TLGWEKSY64AC45Z6GOVE/graph.json","fetch_events":"https://pith.science/api/pith-number/BBCSJ3TLGWEKSY64AC45Z6GOVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/action/storage_attestation","attest_author":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/action/author_attestation","sign_citation":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/action/citation_signature","submit_replication":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/action/replication_record"}},"created_at":"2026-07-05T06:19:45.333538+00:00","updated_at":"2026-07-05T06:19:45.333538+00:00"}