{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NTZUHBFW5X6MH45VO7D54XCOG4","short_pith_number":"pith:NTZUHBFW","canonical_record":{"source":{"id":"2507.19374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T15:25:17Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"5fdd14511bdb9615b5d6f065a9eab0d8cc137930c239904975a3ad5bc91afb35","abstract_canon_sha256":"af47ba8afe34590238fb62229464477eb88ec593c12c2e36b8b1a37805259532"},"schema_version":"1.0"},"canonical_sha256":"6cf34384b6edfcc3f3b577c7de5c4e371c3108366bc192cc39eafb75b64553e0","source":{"kind":"arxiv","id":"2507.19374","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19374","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19374v1","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19374","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"NTZUHBFW5X6M","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"NTZUHBFW5X6MH45V","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"NTZUHBFW","created_at":"2026-07-05T11:43:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NTZUHBFW5X6MH45VO7D54XCOG4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19374","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T15:25:17Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"5fdd14511bdb9615b5d6f065a9eab0d8cc137930c239904975a3ad5bc91afb35","abstract_canon_sha256":"af47ba8afe34590238fb62229464477eb88ec593c12c2e36b8b1a37805259532"},"schema_version":"1.0"},"canonical_sha256":"6cf34384b6edfcc3f3b577c7de5c4e371c3108366bc192cc39eafb75b64553e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:24.401387Z","signature_b64":"EHBNah6y7CpvNNA/fNgHnydh6uFzii4XSK4MR59NcgrytakahAVAnqF0m1TqyFjiXwK+rdjJQhWVGoUoGbMlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cf34384b6edfcc3f3b577c7de5c4e371c3108366bc192cc39eafb75b64553e0","last_reissued_at":"2026-07-05T11:43:24.400892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:24.400892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19374","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":"2026-07-05T11:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXTXl6++lZFODaK0OwAtO2qmcRuYtevAmUQ0ZZiwwYX1YnG3c80E+WULgi5GKePlqOmS5Rw2X6GBzarhgT5ADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:48:41.476679Z"},"content_sha256":"2fc27aeecc572236b0c3a9dbd7b004c32af2033af1f064737003d1ffac1a938f","schema_version":"1.0","event_id":"sha256:2fc27aeecc572236b0c3a9dbd7b004c32af2033af1f064737003d1ffac1a938f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NTZUHBFW5X6MH45VO7D54XCOG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Augmentation for Spoken Grammatical 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":"Kate M. Knill, Mark J.F. Gales, Mengjie Qian, Penny Karanasou, Stefano Bann\\`o","submitted_at":"2025-07-25T15:25:17Z","abstract_excerpt":"While there exist strong benchmark datasets for grammatical error correction (GEC), high-quality annotated spoken datasets for Spoken GEC (SGEC) are still under-resourced. In this paper, we propose a fully automated method to generate audio-text pairs with grammatical errors and disfluencies. Moreover, we propose a series of objective metrics that can be used to evaluate the generated data and choose the more suitable dataset for SGEC. The goal is to generate an augmented dataset that maintains the textual and acoustic characteristics of the original data while providing new types of errors. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19374","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/2507.19374/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":"2026-07-05T11:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fhopgVOYVnu3mBUVcLSvZMwjAnvNFe0gdql3xxLp2eq66QV7UaF04GpGVCnFCdr+VRcMC2x8eGjp29ufMMsyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:48:41.477735Z"},"content_sha256":"14c5915076d2d79c791e92c0c1a9c0a45ca1fca93837ed4164464e1b4fc0596d","schema_version":"1.0","event_id":"sha256:14c5915076d2d79c791e92c0c1a9c0a45ca1fca93837ed4164464e1b4fc0596d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTZUHBFW5X6MH45VO7D54XCOG4/bundle.json","state_url":"https://pith.science/pith/NTZUHBFW5X6MH45VO7D54XCOG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTZUHBFW5X6MH45VO7D54XCOG4/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":"2026-08-17T12:48:41Z","links":{"resolver":"https://pith.science/pith/NTZUHBFW5X6MH45VO7D54XCOG4","bundle":"https://pith.science/pith/NTZUHBFW5X6MH45VO7D54XCOG4/bundle.json","state":"https://pith.science/pith/NTZUHBFW5X6MH45VO7D54XCOG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTZUHBFW5X6MH45VO7D54XCOG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NTZUHBFW5X6MH45VO7D54XCOG4","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":"af47ba8afe34590238fb62229464477eb88ec593c12c2e36b8b1a37805259532","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T15:25:17Z","title_canon_sha256":"5fdd14511bdb9615b5d6f065a9eab0d8cc137930c239904975a3ad5bc91afb35"},"schema_version":"1.0","source":{"id":"2507.19374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19374","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19374v1","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19374","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"NTZUHBFW5X6M","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"NTZUHBFW5X6MH45V","created_at":"2026-07-05T11:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"NTZUHBFW","created_at":"2026-07-05T11:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:14c5915076d2d79c791e92c0c1a9c0a45ca1fca93837ed4164464e1b4fc0596d","target":"graph","created_at":"2026-07-05T11:43:24Z","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/2507.19374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While there exist strong benchmark datasets for grammatical error correction (GEC), high-quality annotated spoken datasets for Spoken GEC (SGEC) are still under-resourced. In this paper, we propose a fully automated method to generate audio-text pairs with grammatical errors and disfluencies. Moreover, we propose a series of objective metrics that can be used to evaluate the generated data and choose the more suitable dataset for SGEC. The goal is to generate an augmented dataset that maintains the textual and acoustic characteristics of the original data while providing new types of errors. T","authors_text":"Kate M. Knill, Mark J.F. Gales, Mengjie Qian, Penny Karanasou, Stefano Bann\\`o","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T15:25:17Z","title":"Data Augmentation for Spoken Grammatical Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19374","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":"sha256:2fc27aeecc572236b0c3a9dbd7b004c32af2033af1f064737003d1ffac1a938f","target":"record","created_at":"2026-07-05T11:43:24Z","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":"af47ba8afe34590238fb62229464477eb88ec593c12c2e36b8b1a37805259532","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-25T15:25:17Z","title_canon_sha256":"5fdd14511bdb9615b5d6f065a9eab0d8cc137930c239904975a3ad5bc91afb35"},"schema_version":"1.0","source":{"id":"2507.19374","kind":"arxiv","version":1}},"canonical_sha256":"6cf34384b6edfcc3f3b577c7de5c4e371c3108366bc192cc39eafb75b64553e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cf34384b6edfcc3f3b577c7de5c4e371c3108366bc192cc39eafb75b64553e0","first_computed_at":"2026-07-05T11:43:24.400892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:24.400892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EHBNah6y7CpvNNA/fNgHnydh6uFzii4XSK4MR59NcgrytakahAVAnqF0m1TqyFjiXwK+rdjJQhWVGoUoGbMlCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:24.401387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fc27aeecc572236b0c3a9dbd7b004c32af2033af1f064737003d1ffac1a938f","sha256:14c5915076d2d79c791e92c0c1a9c0a45ca1fca93837ed4164464e1b4fc0596d"],"state_sha256":"be89115e0f861d41809e0d88745f228078f6bf2d3d5e627b2492333c60f06727"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1+GyS4IT4gvpf9KO+l44Idpr0iXLbl8KN2LqbMrm3Dgd6oCsvHlrM6VeoA65hQLWJ1zeuBvlT6bZwEbr2f+7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:48:41.538177Z","bundle_sha256":"e271b792ec8fe55036116efb72a72adce1a0a5b134f18de007f96e6e1bb2c215"}}