{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MFSL6STCRCU3H3MDDTIOYLRGFI","short_pith_number":"pith:MFSL6STC","schema_version":"1.0","canonical_sha256":"6164bf4a6288a9b3ed831cd0ec2e262a3ded726cc54752586f9feafbffb7f1f6","source":{"kind":"arxiv","id":"2505.21137","version":1},"attestation_state":"computed","paper":{"title":"Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kate M. Knill, Mark J.F. Gales, Mengjie Qian, Rao Ma, Stefano Bann\\`o","submitted_at":"2025-05-27T12:50:53Z","abstract_excerpt":"Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection (DD) and removal and one for GEC. With the rise of end-to-end (E2E) speech foundation models, we investigate their effectiveness in SGEC and feedback generation. This work introduces a pseudo-labelling process to address the challenge of limited labelled data, expanding the training data size from 77 hours to approximately 2500 hours, leading to improved pe"},"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":"2505.21137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"eac4739cdd89791a7b36b7c1dc94663930817ffa35c9115e4d925275d7e1e077","abstract_canon_sha256":"e5efe0899f09a8781c4dc7219e5a5d8f5a69db957da0d736cba75037df3e212a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:24.246904Z","signature_b64":"WRjLzOcek8HCtQdCIPjSOzAIB9hngk4s9VtNWGilq+Rw0DmD/jxzL92yHecFL2ef27W8gGdUNh+hjq4haetwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6164bf4a6288a9b3ed831cd0ec2e262a3ded726cc54752586f9feafbffb7f1f6","last_reissued_at":"2026-07-05T11:10:24.246421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:24.246421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Kate M. Knill, Mark J.F. Gales, Mengjie Qian, Rao Ma, Stefano Bann\\`o","submitted_at":"2025-05-27T12:50:53Z","abstract_excerpt":"Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection (DD) and removal and one for GEC. With the rise of end-to-end (E2E) speech foundation models, we investigate their effectiveness in SGEC and feedback generation. This work introduces a pseudo-labelling process to address the challenge of limited labelled data, expanding the training data size from 77 hours to approximately 2500 hours, leading to improved pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21137","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/2505.21137/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":"2505.21137","created_at":"2026-07-05T11:10:24.246474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21137v1","created_at":"2026-07-05T11:10:24.246474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21137","created_at":"2026-07-05T11:10:24.246474+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFSL6STCRCU3","created_at":"2026-07-05T11:10:24.246474+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFSL6STCRCU3H3MD","created_at":"2026-07-05T11:10:24.246474+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFSL6STC","created_at":"2026-07-05T11:10:24.246474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21137","citing_title":"Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI","json":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI.json","graph_json":"https://pith.science/api/pith-number/MFSL6STCRCU3H3MDDTIOYLRGFI/graph.json","events_json":"https://pith.science/api/pith-number/MFSL6STCRCU3H3MDDTIOYLRGFI/events.json","paper":"https://pith.science/paper/MFSL6STC"},"agent_actions":{"view_html":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI","download_json":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI.json","view_paper":"https://pith.science/paper/MFSL6STC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21137&json=true","fetch_graph":"https://pith.science/api/pith-number/MFSL6STCRCU3H3MDDTIOYLRGFI/graph.json","fetch_events":"https://pith.science/api/pith-number/MFSL6STCRCU3H3MDDTIOYLRGFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/action/storage_attestation","attest_author":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/action/author_attestation","sign_citation":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/action/citation_signature","submit_replication":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/action/replication_record"}},"created_at":"2026-07-05T11:10:24.246474+00:00","updated_at":"2026-07-05T11:10:24.246474+00:00"}