{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BBCSJ3TLGWEKSY64AC45Z6GOVE","short_pith_number":"pith:BBCSJ3TL","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"},"canonical_sha256":"084524ee6b3588a963dc00b9dcf8cea90eefa5027243caab64afbc8c22152379","source":{"kind":"arxiv","id":"2306.06892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06892","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06892v1","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06892","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"pith_short_12","alias_value":"BBCSJ3TLGWEK","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"pith_short_16","alias_value":"BBCSJ3TLGWEKSY64","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"pith_short_8","alias_value":"BBCSJ3TL","created_at":"2026-07-05T06:19:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BBCSJ3TLGWEKSY64AC45Z6GOVE","target":"record","payload":{"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"},"canonical_sha256":"084524ee6b3588a963dc00b9dcf8cea90eefa5027243caab64afbc8c22152379","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"},"source_kind":"arxiv","source_id":"2306.06892","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qq2OgFA/pUSGLJz26tHlBgYPr+KVJicqLd0SoLQzr2c/gZrMHVTN/uskXGv+RrYmnLVgbxm/brimhYJ0Q3+MCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:03:55.143861Z"},"content_sha256":"109e960e497441f73049c0acaa853a130db3ab0d102676d8bfd717867edef9e9","schema_version":"1.0","event_id":"sha256:109e960e497441f73049c0acaa853a130db3ab0d102676d8bfd717867edef9e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BBCSJ3TLGWEKSY64AC45Z6GOVE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UpSiWlNQL/YzS4AnjXpAlhN0Vx87BZj3lGp8nHGveJr/SpoQG/cFUPaKJYaF8yumfpdxuN1qJg8aB1cEGM79Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:03:55.144335Z"},"content_sha256":"6330ee32d5f7c3b1f116a299d0d21795a0eb13aa6fd6e441f5d21da7bc06d522","schema_version":"1.0","event_id":"sha256:6330ee32d5f7c3b1f116a299d0d21795a0eb13aa6fd6e441f5d21da7bc06d522"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/bundle.json","state_url":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T22:03:55Z","links":{"resolver":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE","bundle":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/bundle.json","state":"https://pith.science/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBCSJ3TLGWEKSY64AC45Z6GOVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BBCSJ3TLGWEKSY64AC45Z6GOVE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e026b455b829e00f0741effe630766399382aa1a0858e4611d7756513f206538","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T06:42:08Z","title_canon_sha256":"0b443d6692fdaac79b3a693d29f20199b59c2a9229b7741d29b88d7818318c7c"},"schema_version":"1.0","source":{"id":"2306.06892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06892","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06892v1","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06892","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"pith_short_12","alias_value":"BBCSJ3TLGWEK","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"pith_short_16","alias_value":"BBCSJ3TLGWEKSY64","created_at":"2026-07-05T06:19:45Z"},{"alias_kind":"pith_short_8","alias_value":"BBCSJ3TL","created_at":"2026-07-05T06:19:45Z"}],"graph_snapshots":[{"event_id":"sha256:6330ee32d5f7c3b1f116a299d0d21795a0eb13aa6fd6e441f5d21da7bc06d522","target":"graph","created_at":"2026-07-05T06:19:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.06892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aravind Krishnan, Dietrich Klakow, Jesujoba Alabi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T06:42:08Z","title":"On the N-gram Approximation of Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06892","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:109e960e497441f73049c0acaa853a130db3ab0d102676d8bfd717867edef9e9","target":"record","created_at":"2026-07-05T06:19:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e026b455b829e00f0741effe630766399382aa1a0858e4611d7756513f206538","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T06:42:08Z","title_canon_sha256":"0b443d6692fdaac79b3a693d29f20199b59c2a9229b7741d29b88d7818318c7c"},"schema_version":"1.0","source":{"id":"2306.06892","kind":"arxiv","version":1}},"canonical_sha256":"084524ee6b3588a963dc00b9dcf8cea90eefa5027243caab64afbc8c22152379","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"084524ee6b3588a963dc00b9dcf8cea90eefa5027243caab64afbc8c22152379","first_computed_at":"2026-07-05T06:19:45.333484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:45.333484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2zlC7XHn3yKwyq1cegdVAC2x6WiejKO87mM+Xt510qafzMeY8yKgUtwZ5tLlEijtcFisYVvopNwjezHSvp5pCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:45.333873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:109e960e497441f73049c0acaa853a130db3ab0d102676d8bfd717867edef9e9","sha256:6330ee32d5f7c3b1f116a299d0d21795a0eb13aa6fd6e441f5d21da7bc06d522"],"state_sha256":"fce779667f75235d43c1fcc5929181905da15e2345b1ffecb732699687beaf2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JXNuoQxKTVW9/dY8LpLuo9QovPtQqIwd0mq0DVlC0BccJsBauE+2my6hGaTTqwkS/cpQgWv7SG1rbrdTwbe5Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:03:55.148819Z","bundle_sha256":"d94e598927eff922f3eb9a3ee54705f9342f1ca2afeee282d7a3731135755d4e"}}