{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OSS4LXK5COD4JSKF55OML6I5AL","short_pith_number":"pith:OSS4LXK5","schema_version":"1.0","canonical_sha256":"74a5c5dd5d1387c4c945ef5cc5f91d02da8d188cf43506af9e91fd1d3e1a21bb","source":{"kind":"arxiv","id":"2606.18597","version":1},"attestation_state":"computed","paper":{"title":"Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Xu, Keyu Yan, Mingwen Wang, Yangjie Dan, Yong Ma","submitted_at":"2026-06-17T01:46:41Z","abstract_excerpt":"Chinese dialects discrimination is a challenging natural language processing task due to scarce annotation resource. In this article, we develop a novel Chinese dialects discrimination framework with transfer learning and data augmentation (CDDTLDA) in order to overcome the shortage of resources. To be more specific, we first use a relatively larger Chinese dialects corpus to train a source-side automatic speech recognition (ASR) model. Then, we adopt a simple but effective data augmentation method (i.e., speed, pitch, and noise disturbance) to augment the target-side low-resource Chinese dial"},"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":"2606.18597","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T01:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"cbecba32a08d97d7561525c764bc1d2896de3240a0ce81f2d95728b5e0f25082","abstract_canon_sha256":"9e69f4d99b80f09914c15aac7d3bcac084b92e66d2e02a19cae9e99e52080770"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:42.084658Z","signature_b64":"jvGpYeV04kORRJSbJAPbfLxO+zeZgOnQzz8gx/RPke2Gt7ee5yG73eWFURf1rcYE4QkId6zoF1HZicpWkhPMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74a5c5dd5d1387c4c945ef5cc5f91d02da8d188cf43506af9e91fd1d3e1a21bb","last_reissued_at":"2026-06-19T16:11:42.084264Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:42.084264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fan Xu, Keyu Yan, Mingwen Wang, Yangjie Dan, Yong Ma","submitted_at":"2026-06-17T01:46:41Z","abstract_excerpt":"Chinese dialects discrimination is a challenging natural language processing task due to scarce annotation resource. In this article, we develop a novel Chinese dialects discrimination framework with transfer learning and data augmentation (CDDTLDA) in order to overcome the shortage of resources. To be more specific, we first use a relatively larger Chinese dialects corpus to train a source-side automatic speech recognition (ASR) model. Then, we adopt a simple but effective data augmentation method (i.e., speed, pitch, and noise disturbance) to augment the target-side low-resource Chinese dial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18597","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/2606.18597/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":"2606.18597","created_at":"2026-06-19T16:11:42.084333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18597v1","created_at":"2026-06-19T16:11:42.084333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18597","created_at":"2026-06-19T16:11:42.084333+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSS4LXK5COD4","created_at":"2026-06-19T16:11:42.084333+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSS4LXK5COD4JSKF","created_at":"2026-06-19T16:11:42.084333+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSS4LXK5","created_at":"2026-06-19T16:11:42.084333+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/OSS4LXK5COD4JSKF55OML6I5AL","json":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL.json","graph_json":"https://pith.science/api/pith-number/OSS4LXK5COD4JSKF55OML6I5AL/graph.json","events_json":"https://pith.science/api/pith-number/OSS4LXK5COD4JSKF55OML6I5AL/events.json","paper":"https://pith.science/paper/OSS4LXK5"},"agent_actions":{"view_html":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL","download_json":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL.json","view_paper":"https://pith.science/paper/OSS4LXK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18597&json=true","fetch_graph":"https://pith.science/api/pith-number/OSS4LXK5COD4JSKF55OML6I5AL/graph.json","fetch_events":"https://pith.science/api/pith-number/OSS4LXK5COD4JSKF55OML6I5AL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/action/storage_attestation","attest_author":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/action/author_attestation","sign_citation":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/action/citation_signature","submit_replication":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/action/replication_record"}},"created_at":"2026-06-19T16:11:42.084333+00:00","updated_at":"2026-06-19T16:11:42.084333+00:00"}