{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VGJ736LEDSUFNDLUC6PFYGHCZT","short_pith_number":"pith:VGJ736LE","schema_version":"1.0","canonical_sha256":"a993fdf9641ca8568d74179e5c18e2ccf9923ca94b92b4b975a5cf9268bddb62","source":{"kind":"arxiv","id":"2309.04516","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"David Roth, Giulio Duregon, Saksham Bassi, Siddhartha Jalagam","submitted_at":"2023-09-08T17:12:14Z","abstract_excerpt":"The SOTA in transcription of disfluent and conversational speech has in recent years favored two-stage models, with separate transcription and cleaning stages. We believe that previous attempts at end-to-end disfluency removal have fallen short because of the representational advantage that large-scale language model pretraining has given to lexical models. Until recently, the high dimensionality and limited availability of large audio datasets inhibited the development of large-scale self-supervised pretraining objectives for learning effective audio representations, giving a relative advanta"},"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":"2309.04516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-08T17:12:14Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"4f56eb2f02ac03482d50d40c6987ceb1e1b3481d5ea0c85bac751593b3953ce8","abstract_canon_sha256":"b80b2af548008c3b70a058251cbe9d6aafe02cb06ba515c8a5b760e7d0c2beb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:04.119700Z","signature_b64":"EHRDSiB3v19L+76zemoPYQCEKVkP1McxKBN4woOWZFLHKy1gZnULbTbaFSMV6bjQbaVLEFls+k6rvZBU0Uz7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a993fdf9641ca8568d74179e5c18e2ccf9923ca94b92b4b975a5cf9268bddb62","last_reissued_at":"2026-07-05T06:49:04.119253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:04.119253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"David Roth, Giulio Duregon, Saksham Bassi, Siddhartha Jalagam","submitted_at":"2023-09-08T17:12:14Z","abstract_excerpt":"The SOTA in transcription of disfluent and conversational speech has in recent years favored two-stage models, with separate transcription and cleaning stages. We believe that previous attempts at end-to-end disfluency removal have fallen short because of the representational advantage that large-scale language model pretraining has given to lexical models. Until recently, the high dimensionality and limited availability of large audio datasets inhibited the development of large-scale self-supervised pretraining objectives for learning effective audio representations, giving a relative advanta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04516","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/2309.04516/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":"2309.04516","created_at":"2026-07-05T06:49:04.119309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.04516v1","created_at":"2026-07-05T06:49:04.119309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04516","created_at":"2026-07-05T06:49:04.119309+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGJ736LEDSUF","created_at":"2026-07-05T06:49:04.119309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGJ736LEDSUFNDLU","created_at":"2026-07-05T06:49:04.119309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGJ736LE","created_at":"2026-07-05T06:49:04.119309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05612","citing_title":"Rambler in the Wild: A Diary Study of LLM-Assisted Writing With Speech","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT","json":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT.json","graph_json":"https://pith.science/api/pith-number/VGJ736LEDSUFNDLUC6PFYGHCZT/graph.json","events_json":"https://pith.science/api/pith-number/VGJ736LEDSUFNDLUC6PFYGHCZT/events.json","paper":"https://pith.science/paper/VGJ736LE"},"agent_actions":{"view_html":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT","download_json":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT.json","view_paper":"https://pith.science/paper/VGJ736LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.04516&json=true","fetch_graph":"https://pith.science/api/pith-number/VGJ736LEDSUFNDLUC6PFYGHCZT/graph.json","fetch_events":"https://pith.science/api/pith-number/VGJ736LEDSUFNDLUC6PFYGHCZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT/action/storage_attestation","attest_author":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT/action/author_attestation","sign_citation":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT/action/citation_signature","submit_replication":"https://pith.science/pith/VGJ736LEDSUFNDLUC6PFYGHCZT/action/replication_record"}},"created_at":"2026-07-05T06:49:04.119309+00:00","updated_at":"2026-07-05T06:49:04.119309+00:00"}