{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VGJ736LEDSUFNDLUC6PFYGHCZT","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":"b80b2af548008c3b70a058251cbe9d6aafe02cb06ba515c8a5b760e7d0c2beb6","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-08T17:12:14Z","title_canon_sha256":"4f56eb2f02ac03482d50d40c6987ceb1e1b3481d5ea0c85bac751593b3953ce8"},"schema_version":"1.0","source":{"id":"2309.04516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.04516","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2309.04516v1","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.04516","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"VGJ736LEDSUF","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"VGJ736LEDSUFNDLU","created_at":"2026-07-05T06:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"VGJ736LE","created_at":"2026-07-05T06:49:04Z"}],"graph_snapshots":[{"event_id":"sha256:edc422024f0b9c022712ce2af6b377c004ccc819a3c1d068bacb1f40b3e11943","target":"graph","created_at":"2026-07-05T06:49:04Z","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/2309.04516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Roth, Giulio Duregon, Saksham Bassi, Siddhartha Jalagam","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-08T17:12:14Z","title":"End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.04516","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":"sha256:33fd635f06cf6e79cacb3434834cdfd0cf3cf2834db531f14d24f1eb47e207ba","target":"record","created_at":"2026-07-05T06:49:04Z","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":"b80b2af548008c3b70a058251cbe9d6aafe02cb06ba515c8a5b760e7d0c2beb6","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-08T17:12:14Z","title_canon_sha256":"4f56eb2f02ac03482d50d40c6987ceb1e1b3481d5ea0c85bac751593b3953ce8"},"schema_version":"1.0","source":{"id":"2309.04516","kind":"arxiv","version":1}},"canonical_sha256":"a993fdf9641ca8568d74179e5c18e2ccf9923ca94b92b4b975a5cf9268bddb62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a993fdf9641ca8568d74179e5c18e2ccf9923ca94b92b4b975a5cf9268bddb62","first_computed_at":"2026-07-05T06:49:04.119253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:49:04.119253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHRDSiB3v19L+76zemoPYQCEKVkP1McxKBN4woOWZFLHKy1gZnULbTbaFSMV6bjQbaVLEFls+k6rvZBU0Uz7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:49:04.119700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.04516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33fd635f06cf6e79cacb3434834cdfd0cf3cf2834db531f14d24f1eb47e207ba","sha256:edc422024f0b9c022712ce2af6b377c004ccc819a3c1d068bacb1f40b3e11943"],"state_sha256":"ea4f2e8cf2d25fb5d0d0ddfe5e7524d0891c25f04bab68baf7ae6c811aafb5f7"}