{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:334WYZOPJDI4C4A6KZACROIXDA","short_pith_number":"pith:334WYZOP","schema_version":"1.0","canonical_sha256":"def96c65cf48d1c1701e564028b917183ca45143de2717a94ffcff2b21b7fb60","source":{"kind":"arxiv","id":"2405.10025","version":1},"attestation_state":"computed","paper":{"title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Chen, Chengwei Qin, Eng Siong Chng, Qiushi Zhu, Ruizhe Li, Yuchen Hu","submitted_at":"2024-05-16T12:05:45Z","abstract_excerpt":"Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which aims to predict the ground-truth transcription from the decoded N-best hypotheses. Thanks to the strong language generation ability of LLMs and rich information in the N-best list, GER shows great effectiveness in enhancing ASR results. However, it still suffers from two limitations: 1) LLMs are unaware of the source speech during GER, which may lead to results that are grammatically correct but violate the source speech content, 2) N-best hypotheses usu"},"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":"2405.10025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T12:05:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"bbdba6cde87b45f472bf6cec4b2e86e199cbbf48202d2b89ffade76d8612aa57","abstract_canon_sha256":"4ce5497ff597bf7435bb8fed25a854006895c3df39408343554361babad5a6ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:51.826563Z","signature_b64":"78TyfkvLNi4/mwWRlXyQYFllNmVRRBzF2SjUgLvwkRyWWUsFWYOJ7t7abbPn5Lpu/HrCqauc4/M5R+M79T1/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"def96c65cf48d1c1701e564028b917183ca45143de2717a94ffcff2b21b7fb60","last_reissued_at":"2026-07-05T08:19:51.826078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:51.826078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Chen, Chengwei Qin, Eng Siong Chng, Qiushi Zhu, Ruizhe Li, Yuchen Hu","submitted_at":"2024-05-16T12:05:45Z","abstract_excerpt":"Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR), which aims to predict the ground-truth transcription from the decoded N-best hypotheses. Thanks to the strong language generation ability of LLMs and rich information in the N-best list, GER shows great effectiveness in enhancing ASR results. However, it still suffers from two limitations: 1) LLMs are unaware of the source speech during GER, which may lead to results that are grammatically correct but violate the source speech content, 2) N-best hypotheses usu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10025","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/2405.10025/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":"2405.10025","created_at":"2026-07-05T08:19:51.826136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10025v1","created_at":"2026-07-05T08:19:51.826136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10025","created_at":"2026-07-05T08:19:51.826136+00:00"},{"alias_kind":"pith_short_12","alias_value":"334WYZOPJDI4","created_at":"2026-07-05T08:19:51.826136+00:00"},{"alias_kind":"pith_short_16","alias_value":"334WYZOPJDI4C4A6","created_at":"2026-07-05T08:19:51.826136+00:00"},{"alias_kind":"pith_short_8","alias_value":"334WYZOP","created_at":"2026-07-05T08:19:51.826136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07510","citing_title":"DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA","json":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA.json","graph_json":"https://pith.science/api/pith-number/334WYZOPJDI4C4A6KZACROIXDA/graph.json","events_json":"https://pith.science/api/pith-number/334WYZOPJDI4C4A6KZACROIXDA/events.json","paper":"https://pith.science/paper/334WYZOP"},"agent_actions":{"view_html":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA","download_json":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA.json","view_paper":"https://pith.science/paper/334WYZOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10025&json=true","fetch_graph":"https://pith.science/api/pith-number/334WYZOPJDI4C4A6KZACROIXDA/graph.json","fetch_events":"https://pith.science/api/pith-number/334WYZOPJDI4C4A6KZACROIXDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA/action/storage_attestation","attest_author":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA/action/author_attestation","sign_citation":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA/action/citation_signature","submit_replication":"https://pith.science/pith/334WYZOPJDI4C4A6KZACROIXDA/action/replication_record"}},"created_at":"2026-07-05T08:19:51.826136+00:00","updated_at":"2026-07-05T08:19:51.826136+00:00"}