{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SNLGBPSOF6FDLDOCRNT3AY5C2Q","short_pith_number":"pith:SNLGBPSO","canonical_record":{"source":{"id":"2302.08229","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T11:27:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3a2ed4ab8085d124f08e46530cd5c3eaffde4d23770e2484d15933fd41693c4f","abstract_canon_sha256":"b4875b92ba14b4919fbac172e1b7862520b37799fac6d9803f74606721cd7e40"},"schema_version":"1.0"},"canonical_sha256":"935660be4e2f8a358dc28b67b063a2d43d25fda21ecd81b113b7c592a1a925e8","source":{"kind":"arxiv","id":"2302.08229","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08229","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08229v1","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08229","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"SNLGBPSOF6FD","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"pith_short_16","alias_value":"SNLGBPSOF6FDLDOC","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"pith_short_8","alias_value":"SNLGBPSO","created_at":"2026-07-05T05:42:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SNLGBPSOF6FDLDOCRNT3AY5C2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2302.08229","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T11:27:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3a2ed4ab8085d124f08e46530cd5c3eaffde4d23770e2484d15933fd41693c4f","abstract_canon_sha256":"b4875b92ba14b4919fbac172e1b7862520b37799fac6d9803f74606721cd7e40"},"schema_version":"1.0"},"canonical_sha256":"935660be4e2f8a358dc28b67b063a2d43d25fda21ecd81b113b7c592a1a925e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:35.853200Z","signature_b64":"N8gAmH118DXR8ozQIABTv5roKwKiyJ/FPAEai2qOkvIeUJK83w5eI2gC6E8fBj0rYNkGDTRYbTu8pT+8duT5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"935660be4e2f8a358dc28b67b063a2d43d25fda21ecd81b113b7c592a1a925e8","last_reissued_at":"2026-07-05T05:42:35.852818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:35.852818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.08229","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":"2026-07-05T05:42:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6d8Pvk6UnBaWJU4eo15DTAJtlbtudIHEge7e+fsthIJWI/AYu0c3uJPoQE8M0ofUIzLJ02mJlTsRPZcrzi8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:55:55.549028Z"},"content_sha256":"f4249af14a63aea8f1a159be4708eaf946e431671c09626e9210e9ce11fb37cd","schema_version":"1.0","event_id":"sha256:f4249af14a63aea8f1a159be4708eaf946e431671c09626e9210e9ce11fb37cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SNLGBPSOF6FDLDOCRNT3AY5C2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Spoken Language Identification with Map-Mix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Eng Siong Chng, Kriti Anandan, Shangeth Rajaa, Swaraj Dalmia, Tarun Gupta","submitted_at":"2023-02-16T11:27:46Z","abstract_excerpt":"The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for example, in the case of dialects. Low resource dialect classification remains a challenging problem to solve. We present a new data augmentation method that leverages model training dynamics of individual data points to improve sampling for latent mixup. The method works well in low-resource settings where generalization is paramount. Our datamaps-based mixup tec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08229","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/2302.08229/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":"2026-07-05T05:42:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XU6B+99CJ1W/8q7ZRtVUssfNfdfJb5gWDgOweGp14WWrbZcaXT5p5rWhiN+jEt72O20FdfgeF6uDxoQjsDebAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:55:55.549577Z"},"content_sha256":"f81fe6082f7429f38626ed1fbb78a7eef2954ed1e232c27edd1dea2712a38401","schema_version":"1.0","event_id":"sha256:f81fe6082f7429f38626ed1fbb78a7eef2954ed1e232c27edd1dea2712a38401"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q/bundle.json","state_url":"https://pith.science/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q/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":"2026-08-04T00:55:55Z","links":{"resolver":"https://pith.science/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q","bundle":"https://pith.science/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q/bundle.json","state":"https://pith.science/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNLGBPSOF6FDLDOCRNT3AY5C2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SNLGBPSOF6FDLDOCRNT3AY5C2Q","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":"b4875b92ba14b4919fbac172e1b7862520b37799fac6d9803f74606721cd7e40","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T11:27:46Z","title_canon_sha256":"3a2ed4ab8085d124f08e46530cd5c3eaffde4d23770e2484d15933fd41693c4f"},"schema_version":"1.0","source":{"id":"2302.08229","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.08229","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"2302.08229v1","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08229","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"SNLGBPSOF6FD","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"pith_short_16","alias_value":"SNLGBPSOF6FDLDOC","created_at":"2026-07-05T05:42:35Z"},{"alias_kind":"pith_short_8","alias_value":"SNLGBPSO","created_at":"2026-07-05T05:42:35Z"}],"graph_snapshots":[{"event_id":"sha256:f81fe6082f7429f38626ed1fbb78a7eef2954ed1e232c27edd1dea2712a38401","target":"graph","created_at":"2026-07-05T05:42:35Z","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/2302.08229/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pre-trained multi-lingual XLSR model generalizes well for language identification after fine-tuning on unseen languages. However, the performance significantly degrades when the languages are not very distinct from each other, for example, in the case of dialects. Low resource dialect classification remains a challenging problem to solve. We present a new data augmentation method that leverages model training dynamics of individual data points to improve sampling for latent mixup. The method works well in low-resource settings where generalization is paramount. Our datamaps-based mixup tec","authors_text":"Eng Siong Chng, Kriti Anandan, Shangeth Rajaa, Swaraj Dalmia, Tarun Gupta","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T11:27:46Z","title":"Improving Spoken Language Identification with Map-Mix"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08229","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:f4249af14a63aea8f1a159be4708eaf946e431671c09626e9210e9ce11fb37cd","target":"record","created_at":"2026-07-05T05:42:35Z","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":"b4875b92ba14b4919fbac172e1b7862520b37799fac6d9803f74606721cd7e40","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-16T11:27:46Z","title_canon_sha256":"3a2ed4ab8085d124f08e46530cd5c3eaffde4d23770e2484d15933fd41693c4f"},"schema_version":"1.0","source":{"id":"2302.08229","kind":"arxiv","version":1}},"canonical_sha256":"935660be4e2f8a358dc28b67b063a2d43d25fda21ecd81b113b7c592a1a925e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"935660be4e2f8a358dc28b67b063a2d43d25fda21ecd81b113b7c592a1a925e8","first_computed_at":"2026-07-05T05:42:35.852818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:35.852818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N8gAmH118DXR8ozQIABTv5roKwKiyJ/FPAEai2qOkvIeUJK83w5eI2gC6E8fBj0rYNkGDTRYbTu8pT+8duT5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:35.853200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.08229","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4249af14a63aea8f1a159be4708eaf946e431671c09626e9210e9ce11fb37cd","sha256:f81fe6082f7429f38626ed1fbb78a7eef2954ed1e232c27edd1dea2712a38401"],"state_sha256":"0493aab969bf21e82c8bf92c1f9433414c1828ea1d19c54d989ce7f25a881a49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AL/+i7OlHvfSPYeJdLZYV7IPROdgRF3uoQE6rEtEB19+tXN+K1JTGOsAWaxX0W/NTXlO6InhikAqRAoWmv9bBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:55:55.553293Z","bundle_sha256":"147b0aca4b7c2a99de0d7c7437f49c0e079ed549e088628ccf145e2e17566979"}}