{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OSS4LXK5COD4JSKF55OML6I5AL","short_pith_number":"pith:OSS4LXK5","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"},"canonical_sha256":"74a5c5dd5d1387c4c945ef5cc5f91d02da8d188cf43506af9e91fd1d3e1a21bb","source":{"kind":"arxiv","id":"2606.18597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18597","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18597v1","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18597","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"OSS4LXK5COD4","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"OSS4LXK5COD4JSKF","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"OSS4LXK5","created_at":"2026-06-19T16:11:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OSS4LXK5COD4JSKF55OML6I5AL","target":"record","payload":{"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"},"canonical_sha256":"74a5c5dd5d1387c4c945ef5cc5f91d02da8d188cf43506af9e91fd1d3e1a21bb","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"},"source_kind":"arxiv","source_id":"2606.18597","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":"2026-06-19T16:11:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIVnkU18HFXOIufvqm6OxBgk2XtzmA2uzfPirr3a4cfZg6fRCQKl4vEg1Rj+EAc94gZY59xrgvUIW1tNljjHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T16:07:28.894681Z"},"content_sha256":"ad2f278a2c20ef9ad6173e6e5e5520375f5e1197a42e95a454725777c88746ed","schema_version":"1.0","event_id":"sha256:ad2f278a2c20ef9ad6173e6e5e5520375f5e1197a42e95a454725777c88746ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OSS4LXK5COD4JSKF55OML6I5AL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:11:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AyhpW8Ctr0xAvKoLYw/nnDtgogEwmGfUNI0UJAT8NqtO3pd6zd9xla4cCvlKARUsOlI9JIe5pXZhza4DGatJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T16:07:28.895043Z"},"content_sha256":"2aedadecc8e62f2dd5dc41396863f9991265d269dd2c139a40f84be246c627a3","schema_version":"1.0","event_id":"sha256:2aedadecc8e62f2dd5dc41396863f9991265d269dd2c139a40f84be246c627a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/bundle.json","state_url":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSS4LXK5COD4JSKF55OML6I5AL/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":"2026-07-03T16:07:28Z","links":{"resolver":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL","bundle":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/bundle.json","state":"https://pith.science/pith/OSS4LXK5COD4JSKF55OML6I5AL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSS4LXK5COD4JSKF55OML6I5AL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OSS4LXK5COD4JSKF55OML6I5AL","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":"9e69f4d99b80f09914c15aac7d3bcac084b92e66d2e02a19cae9e99e52080770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T01:46:41Z","title_canon_sha256":"cbecba32a08d97d7561525c764bc1d2896de3240a0ce81f2d95728b5e0f25082"},"schema_version":"1.0","source":{"id":"2606.18597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18597","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18597v1","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18597","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"OSS4LXK5COD4","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"OSS4LXK5COD4JSKF","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"OSS4LXK5","created_at":"2026-06-19T16:11:42Z"}],"graph_snapshots":[{"event_id":"sha256:2aedadecc8e62f2dd5dc41396863f9991265d269dd2c139a40f84be246c627a3","target":"graph","created_at":"2026-06-19T16:11:42Z","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/2606.18597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fan Xu, Keyu Yan, Mingwen Wang, Yangjie Dan, Yong Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T01:46:41Z","title":"Low-resource Language Discrimination Towards Chinese Dialects with Transfer learning and Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18597","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:ad2f278a2c20ef9ad6173e6e5e5520375f5e1197a42e95a454725777c88746ed","target":"record","created_at":"2026-06-19T16:11:42Z","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":"9e69f4d99b80f09914c15aac7d3bcac084b92e66d2e02a19cae9e99e52080770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T01:46:41Z","title_canon_sha256":"cbecba32a08d97d7561525c764bc1d2896de3240a0ce81f2d95728b5e0f25082"},"schema_version":"1.0","source":{"id":"2606.18597","kind":"arxiv","version":1}},"canonical_sha256":"74a5c5dd5d1387c4c945ef5cc5f91d02da8d188cf43506af9e91fd1d3e1a21bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74a5c5dd5d1387c4c945ef5cc5f91d02da8d188cf43506af9e91fd1d3e1a21bb","first_computed_at":"2026-06-19T16:11:42.084264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:42.084264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jvGpYeV04kORRJSbJAPbfLxO+zeZgOnQzz8gx/RPke2Gt7ee5yG73eWFURf1rcYE4QkId6zoF1HZicpWkhPMDg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:42.084658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad2f278a2c20ef9ad6173e6e5e5520375f5e1197a42e95a454725777c88746ed","sha256:2aedadecc8e62f2dd5dc41396863f9991265d269dd2c139a40f84be246c627a3"],"state_sha256":"12729750c0b8f3f340eb43031f5728e67fe03508bf227ff4d9b08bf3a40e89c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgx4Mu4s6ow3yavNcccTsUKpf4+u4btzjEMW7kPZke82s0CSprtN8FJePCIkzG6UkUCj7NufP9sDACTTouSvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T16:07:28.897017Z","bundle_sha256":"358f58829c2206046e8f57d06c881ea0667231aca45949360f6b4429ef36611a"}}