{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MFSL6STCRCU3H3MDDTIOYLRGFI","short_pith_number":"pith:MFSL6STC","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"},"canonical_sha256":"6164bf4a6288a9b3ed831cd0ec2e262a3ded726cc54752586f9feafbffb7f1f6","source":{"kind":"arxiv","id":"2505.21137","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21137","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21137v1","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21137","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"MFSL6STCRCU3","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"MFSL6STCRCU3H3MD","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"MFSL6STC","created_at":"2026-07-05T11:10:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MFSL6STCRCU3H3MDDTIOYLRGFI","target":"record","payload":{"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"},"canonical_sha256":"6164bf4a6288a9b3ed831cd0ec2e262a3ded726cc54752586f9feafbffb7f1f6","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"},"source_kind":"arxiv","source_id":"2505.21137","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/JaWroVo+RfPjgozJtFf7EQplhhrD5b23ejwitGnvexbYmZhQa8/rxdrdp7X8CMONfI+SWaQntLUj1X7qdGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:41:29.550399Z"},"content_sha256":"010ccc325b06c18e5a06789f8583741c3f1532e4b2a951c50589cee3a90b4b8e","schema_version":"1.0","event_id":"sha256:010ccc325b06c18e5a06789f8583741c3f1532e4b2a951c50589cee3a90b4b8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MFSL6STCRCU3H3MDDTIOYLRGFI","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:10:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DaHR/gxCdwz5SOJ6V51skFs5jov++PBOVg3qNVPe1f1TnbeZwZps5TktfS+e1NzLlHs5uZx1xwJ3hnYour6pCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:41:29.550894Z"},"content_sha256":"9558177e6f937a7bf19fd3319d78ec78d64031f7f44f2b3a764f3ffe010f73e9","schema_version":"1.0","event_id":"sha256:9558177e6f937a7bf19fd3319d78ec78d64031f7f44f2b3a764f3ffe010f73e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/bundle.json","state_url":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T00:41:29Z","links":{"resolver":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI","bundle":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/bundle.json","state":"https://pith.science/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFSL6STCRCU3H3MDDTIOYLRGFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MFSL6STCRCU3H3MDDTIOYLRGFI","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":"e5efe0899f09a8781c4dc7219e5a5d8f5a69db957da0d736cba75037df3e212a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:53Z","title_canon_sha256":"eac4739cdd89791a7b36b7c1dc94663930817ffa35c9115e4d925275d7e1e077"},"schema_version":"1.0","source":{"id":"2505.21137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21137","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21137v1","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21137","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"MFSL6STCRCU3","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"MFSL6STCRCU3H3MD","created_at":"2026-07-05T11:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"MFSL6STC","created_at":"2026-07-05T11:10:24Z"}],"graph_snapshots":[{"event_id":"sha256:9558177e6f937a7bf19fd3319d78ec78d64031f7f44f2b3a764f3ffe010f73e9","target":"graph","created_at":"2026-07-05T11:10:24Z","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/2505.21137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kate M. Knill, Mark J.F. Gales, Mengjie Qian, Rao Ma, Stefano Bann\\`o","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:53Z","title":"Scaling and Prompting for Improved End-to-End Spoken Grammatical Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21137","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":"sha256:010ccc325b06c18e5a06789f8583741c3f1532e4b2a951c50589cee3a90b4b8e","target":"record","created_at":"2026-07-05T11:10:24Z","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":"e5efe0899f09a8781c4dc7219e5a5d8f5a69db957da0d736cba75037df3e212a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T12:50:53Z","title_canon_sha256":"eac4739cdd89791a7b36b7c1dc94663930817ffa35c9115e4d925275d7e1e077"},"schema_version":"1.0","source":{"id":"2505.21137","kind":"arxiv","version":1}},"canonical_sha256":"6164bf4a6288a9b3ed831cd0ec2e262a3ded726cc54752586f9feafbffb7f1f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6164bf4a6288a9b3ed831cd0ec2e262a3ded726cc54752586f9feafbffb7f1f6","first_computed_at":"2026-07-05T11:10:24.246421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:24.246421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WRjLzOcek8HCtQdCIPjSOzAIB9hngk4s9VtNWGilq+Rw0DmD/jxzL92yHecFL2ef27W8gGdUNh+hjq4haetwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:24.246904Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:010ccc325b06c18e5a06789f8583741c3f1532e4b2a951c50589cee3a90b4b8e","sha256:9558177e6f937a7bf19fd3319d78ec78d64031f7f44f2b3a764f3ffe010f73e9"],"state_sha256":"7cd70e9ebd6802c777caead0be4d2864b7eb353b3d41af24b4f0cf531306082d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aX0ZAU+apsn+U3UNz52wnmKAvnsEYbpEF2KSpSdAuLc5Siqt9wwphBkRG5Z5GipdxQfhv+eP+Em3bA+dAQ0sCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:41:29.554519Z","bundle_sha256":"e035eb0c8cd9c120ac57739ec4452e24dfd98d31f1d12167a16e217175e1037e"}}