{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZSKGUDQ4IUAHFEQVP3UV4GYKVS","short_pith_number":"pith:ZSKGUDQ4","schema_version":"1.0","canonical_sha256":"cc946a0e1c45007292157ee95e1b0aaca5e9330cbd37f715e6eea8483046f3b8","source":{"kind":"arxiv","id":"2501.12979","version":1},"attestation_state":"computed","paper":{"title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Moreno La Quatra, Sabato Marco Siniscalchi, Valerio Mario Salerno, Yu Tsao","submitted_at":"2025-01-22T16:06:04Z","abstract_excerpt":"In this paper, we present an encoder-decoder model leveraging Flan-T5 for post-Automatic Speech Recognition (ASR) Generative Speech Error Correction (GenSEC), and we refer to it as FlanEC. We explore its application within the GenSEC framework to enhance ASR outputs by mapping n-best hypotheses into a single output sentence. By utilizing n-best lists from ASR models, we aim to improve the linguistic correctness, accuracy, and grammaticality of final ASR transcriptions. Specifically, we investigate whether scaling the training data and incorporating diverse datasets can lead to significant impr"},"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":"2501.12979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:06:04Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"bbc905695824d2c82137c471343deab1b59da85952429ff3a59a58d74d7002a4","abstract_canon_sha256":"949b4664852a1ce88dc0e27e1489c5b78cd4af1f814e93b499a6ec5cdf3938dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:01.261624Z","signature_b64":"aCJmmSLIDfznJvS4NCWXsC2jV2AIS+hPlIl2J07oDoh/RkL0ipVxH/i6nsIsOqGOSEn1XqJG/ZC/TCGN/3jjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc946a0e1c45007292157ee95e1b0aaca5e9330cbd37f715e6eea8483046f3b8","last_reissued_at":"2026-07-05T10:04:01.261153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:01.261153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlanEC: Exploring Flan-T5 for Post-ASR Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Moreno La Quatra, Sabato Marco Siniscalchi, Valerio Mario Salerno, Yu Tsao","submitted_at":"2025-01-22T16:06:04Z","abstract_excerpt":"In this paper, we present an encoder-decoder model leveraging Flan-T5 for post-Automatic Speech Recognition (ASR) Generative Speech Error Correction (GenSEC), and we refer to it as FlanEC. We explore its application within the GenSEC framework to enhance ASR outputs by mapping n-best hypotheses into a single output sentence. By utilizing n-best lists from ASR models, we aim to improve the linguistic correctness, accuracy, and grammaticality of final ASR transcriptions. Specifically, we investigate whether scaling the training data and incorporating diverse datasets can lead to significant impr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12979","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/2501.12979/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":"2501.12979","created_at":"2026-07-05T10:04:01.261211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12979v1","created_at":"2026-07-05T10:04:01.261211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12979","created_at":"2026-07-05T10:04:01.261211+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSKGUDQ4IUAH","created_at":"2026-07-05T10:04:01.261211+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSKGUDQ4IUAHFEQV","created_at":"2026-07-05T10:04:01.261211+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSKGUDQ4","created_at":"2026-07-05T10:04:01.261211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS","json":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS.json","graph_json":"https://pith.science/api/pith-number/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/graph.json","events_json":"https://pith.science/api/pith-number/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/events.json","paper":"https://pith.science/paper/ZSKGUDQ4"},"agent_actions":{"view_html":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS","download_json":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS.json","view_paper":"https://pith.science/paper/ZSKGUDQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12979&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/action/storage_attestation","attest_author":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/action/author_attestation","sign_citation":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/action/citation_signature","submit_replication":"https://pith.science/pith/ZSKGUDQ4IUAHFEQVP3UV4GYKVS/action/replication_record"}},"created_at":"2026-07-05T10:04:01.261211+00:00","updated_at":"2026-07-05T10:04:01.261211+00:00"}