{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MCELLE2LSKG6FTIEFDV6R45BKW","short_pith_number":"pith:MCELLE2L","schema_version":"1.0","canonical_sha256":"6088b5934b928de2cd0428ebe8f3a15594a67880a5d5164404f173172f566bdf","source":{"kind":"arxiv","id":"2501.10734","version":1},"attestation_state":"computed","paper":{"title":"GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Amin Robatian, Fatemeh Rajabi, Iman Gholampour, Mohammad Hajipour, Mohammad Reza Peyghan, Sajjad Amini, Shahrokh Ghaemmaghami","submitted_at":"2025-01-18T11:53:22Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems have demonstrated remarkable performance across various applications. However, limited data and the unique language features of specific domains, such as low-resource languages, significantly degrade their performance and lead to higher Word Error Rates (WER). In this study, we propose Generative Error Correction via Retrieval-Augmented Generation (GEC-RAG), a novel approach designed to improve ASR accuracy for low-resource domains, like Persian. Our approach treats the ASR system as a black-box, a common practice in cloud-based services, and proposes"},"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":"2501.10734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-01-18T11:53:22Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ebfca39d77935deea3ec27b8f6a57070546496a8045c3ce1528600f00cfa9eaf","abstract_canon_sha256":"6e1b5a7051284ebb4801c50db7fdbd0286fcae7cd916e4424855dc34231ffaf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:59.324574Z","signature_b64":"A8xAomev3iAvPutR556Alrlu+dqbm5sSblGKSxfimR6NTAwEOmu3PyTIgrQsrOSIdXPl9zirOjQ5lrgriltTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6088b5934b928de2cd0428ebe8f3a15594a67880a5d5164404f173172f566bdf","last_reissued_at":"2026-07-05T10:02:59.323979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:59.323979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Amin Robatian, Fatemeh Rajabi, Iman Gholampour, Mohammad Hajipour, Mohammad Reza Peyghan, Sajjad Amini, Shahrokh Ghaemmaghami","submitted_at":"2025-01-18T11:53:22Z","abstract_excerpt":"Automatic Speech Recognition (ASR) systems have demonstrated remarkable performance across various applications. However, limited data and the unique language features of specific domains, such as low-resource languages, significantly degrade their performance and lead to higher Word Error Rates (WER). In this study, we propose Generative Error Correction via Retrieval-Augmented Generation (GEC-RAG), a novel approach designed to improve ASR accuracy for low-resource domains, like Persian. Our approach treats the ASR system as a black-box, a common practice in cloud-based services, and proposes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10734","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/2501.10734/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":"2501.10734","created_at":"2026-07-05T10:02:59.324058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10734v1","created_at":"2026-07-05T10:02:59.324058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10734","created_at":"2026-07-05T10:02:59.324058+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCELLE2LSKG6","created_at":"2026-07-05T10:02:59.324058+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCELLE2LSKG6FTIE","created_at":"2026-07-05T10:02:59.324058+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCELLE2L","created_at":"2026-07-05T10:02:59.324058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24915","citing_title":"Error-Aware TF-IDF Retrieval-Augmented Generation for ASR Error Correction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07285","citing_title":"Non-Intrusive Automatic Speech Recognition Refinement: A Survey","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW","json":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW.json","graph_json":"https://pith.science/api/pith-number/MCELLE2LSKG6FTIEFDV6R45BKW/graph.json","events_json":"https://pith.science/api/pith-number/MCELLE2LSKG6FTIEFDV6R45BKW/events.json","paper":"https://pith.science/paper/MCELLE2L"},"agent_actions":{"view_html":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW","download_json":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW.json","view_paper":"https://pith.science/paper/MCELLE2L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10734&json=true","fetch_graph":"https://pith.science/api/pith-number/MCELLE2LSKG6FTIEFDV6R45BKW/graph.json","fetch_events":"https://pith.science/api/pith-number/MCELLE2LSKG6FTIEFDV6R45BKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW/action/storage_attestation","attest_author":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW/action/author_attestation","sign_citation":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW/action/citation_signature","submit_replication":"https://pith.science/pith/MCELLE2LSKG6FTIEFDV6R45BKW/action/replication_record"}},"created_at":"2026-07-05T10:02:59.324058+00:00","updated_at":"2026-07-05T10:02:59.324058+00:00"}