{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MMAL53XDLKZNGYLVS4EEHUSW67","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":"d730b08e18e256353ee36e78482613dbe623808446a13b2aa2ca04a14a248e1e","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-16T12:55:34Z","title_canon_sha256":"7e974350c90a54dcaedd78bfd78d1300d30162003dfb9e3da6ec22be16951a65"},"schema_version":"1.0","source":{"id":"1910.07323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.07323","created_at":"2026-07-05T00:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"1910.07323v1","created_at":"2026-07-05T00:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07323","created_at":"2026-07-05T00:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"MMAL53XDLKZN","created_at":"2026-07-05T00:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"MMAL53XDLKZNGYLV","created_at":"2026-07-05T00:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"MMAL53XD","created_at":"2026-07-05T00:12:34Z"}],"graph_snapshots":[{"event_id":"sha256:eb66545cfae4ab059646259bab9beef2f307b7df80ca6cfcae0f65b60bf5ca83","target":"graph","created_at":"2026-07-05T00:12:34Z","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/1910.07323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors. Usually, either a quality control stage discards transcriptions with too many errors, or the noisy transcriptions are used as is. We introduce Lead2Gold, a method to train an ASR system that exploits the full potential of noisy transcriptions. Based on a noise model of transcription errors, Lead2Gold searches for better transcriptions of the training data with a beam search that takes this noise model into account. The beam search is differentiable and does not require a forced alignment step, thu","authors_text":"Adrien Dufraux, Armelle Brun, Awni Hannun, Emmanuel Vincent, Matthijs Douze","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-16T12:55:34Z","title":"Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07323","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:d0c38deb0b8e654734d9f47ac67caaf4a4c63b1aeb3fb49b7e327dd4b85f7b14","target":"record","created_at":"2026-07-05T00:12:34Z","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":"d730b08e18e256353ee36e78482613dbe623808446a13b2aa2ca04a14a248e1e","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-16T12:55:34Z","title_canon_sha256":"7e974350c90a54dcaedd78bfd78d1300d30162003dfb9e3da6ec22be16951a65"},"schema_version":"1.0","source":{"id":"1910.07323","kind":"arxiv","version":1}},"canonical_sha256":"6300beeee35ab2d36175970843d256f7e2195ff4f516eb3884c620f0a35fb452","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6300beeee35ab2d36175970843d256f7e2195ff4f516eb3884c620f0a35fb452","first_computed_at":"2026-07-05T00:12:34.749913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:12:34.749913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qMnnsDU7b3CDS8SDnpa2zS/b7hZU+u79SXdCFo9Nre6LTJ3hYF5+rJ3ZI26vl4gX8u4K37PaMfqQeQ09EXd7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:12:34.750249Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.07323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0c38deb0b8e654734d9f47ac67caaf4a4c63b1aeb3fb49b7e327dd4b85f7b14","sha256:eb66545cfae4ab059646259bab9beef2f307b7df80ca6cfcae0f65b60bf5ca83"],"state_sha256":"05777295a7efc05e7ccff9c7bc87cab0f8659f32cf7aabbd6e69149956c585b1"}