{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZPWUGNHG2PESRR2BNAHETGFAU5","short_pith_number":"pith:ZPWUGNHG","canonical_record":{"source":{"id":"2312.06668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T01:32:20Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bffe645e28e43fa9b7165552e0df989f5b60353f059c92017bb998110b6d0a0a","abstract_canon_sha256":"38015e3bf02bc0a927e8cbd549f845f16895e91b67dce97b1c343f43fb1c299b"},"schema_version":"1.0"},"canonical_sha256":"cbed4334e6d3c928c741680e4998a0a745d833f4d61b7d41d0df2d15a7fcef34","source":{"kind":"arxiv","id":"2312.06668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06668","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06668v1","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06668","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZPWUGNHG2PES","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZPWUGNHG2PESRR2B","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZPWUGNHG","created_at":"2026-07-05T07:22:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZPWUGNHG2PESRR2BNAHETGFAU5","target":"record","payload":{"canonical_record":{"source":{"id":"2312.06668","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T01:32:20Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bffe645e28e43fa9b7165552e0df989f5b60353f059c92017bb998110b6d0a0a","abstract_canon_sha256":"38015e3bf02bc0a927e8cbd549f845f16895e91b67dce97b1c343f43fb1c299b"},"schema_version":"1.0"},"canonical_sha256":"cbed4334e6d3c928c741680e4998a0a745d833f4d61b7d41d0df2d15a7fcef34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:51.150637Z","signature_b64":"GWstREYF59rAAufX5u/7VQu/PXEKAEu6mQ0yrnYt7rWEt9mnR5aFzcATmHliMRGME/7IejilJ3QpGRK+sxpKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbed4334e6d3c928c741680e4998a0a745d833f4d61b7d41d0df2d15a7fcef34","last_reissued_at":"2026-07-05T07:22:51.150178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:51.150178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.06668","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":"2026-07-05T07:22:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CriywQqtpM5M3mtrasMZV5zNZp6eEIWXB1Muy68AYAw1Z39myhR/Nxq7g55o6EtSzWvE4D2ieN+FiUl/nVoMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:56:13.898339Z"},"content_sha256":"61a21dabd30ecc3c398e0ef7858e29fba89c34ef842d0a76ee6fb0a3388069ac","schema_version":"1.0","event_id":"sha256:61a21dabd30ecc3c398e0ef7858e29fba89c34ef842d0a76ee6fb0a3388069ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZPWUGNHG2PESRR2BNAHETGFAU5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Self-supervised Speech Models on a Taiwanese Hokkien Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alice Wen-Hsin Bi, Bryan Y. Chen, Carol Yang, Chenxuan Cui, Iu-Tshian Phoann, Jiatong Shi, Jo-Peng Chiang, Kalvin Chang, Meng-Ju Wu, Noel Chen, Po-Yen Yeh, Rong-Wei Pai, Winnie Chang, Winston Ou, Yi-Hui Chou","submitted_at":"2023-12-06T01:32:20Z","abstract_excerpt":"Taiwanese Hokkien is declining in use and status due to a language shift towards Mandarin in Taiwan. This is partly why it is a low resource language in NLP and speech research today. To ensure that the state of the art in speech processing does not leave Taiwanese Hokkien behind, we contribute a 1.5-hour dataset of Taiwanese Hokkien to ML-SUPERB's hidden set. Evaluating ML-SUPERB's suite of self-supervised learning (SSL) speech representations on our dataset, we find that model size does not consistently determine performance. In fact, certain smaller models outperform larger ones. Furthermor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06668","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/2312.06668/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":"2026-07-05T07:22:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5nDannBCGB41+5xLyNxu0Dt88ih2n+kh6gh45UlTjazLtZN34FnJlj5p0wq1QFB0GvT0/eXLaIjCZ5zavlzNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:56:13.899015Z"},"content_sha256":"9ad528be1fe908eee37bd14f90f4e664e249411a0a07d2d4510ec68e23832575","schema_version":"1.0","event_id":"sha256:9ad528be1fe908eee37bd14f90f4e664e249411a0a07d2d4510ec68e23832575"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPWUGNHG2PESRR2BNAHETGFAU5/bundle.json","state_url":"https://pith.science/pith/ZPWUGNHG2PESRR2BNAHETGFAU5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPWUGNHG2PESRR2BNAHETGFAU5/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":"2026-07-05T15:56:13Z","links":{"resolver":"https://pith.science/pith/ZPWUGNHG2PESRR2BNAHETGFAU5","bundle":"https://pith.science/pith/ZPWUGNHG2PESRR2BNAHETGFAU5/bundle.json","state":"https://pith.science/pith/ZPWUGNHG2PESRR2BNAHETGFAU5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPWUGNHG2PESRR2BNAHETGFAU5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZPWUGNHG2PESRR2BNAHETGFAU5","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":"38015e3bf02bc0a927e8cbd549f845f16895e91b67dce97b1c343f43fb1c299b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T01:32:20Z","title_canon_sha256":"bffe645e28e43fa9b7165552e0df989f5b60353f059c92017bb998110b6d0a0a"},"schema_version":"1.0","source":{"id":"2312.06668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06668","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06668v1","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06668","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"ZPWUGNHG2PES","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"ZPWUGNHG2PESRR2B","created_at":"2026-07-05T07:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"ZPWUGNHG","created_at":"2026-07-05T07:22:51Z"}],"graph_snapshots":[{"event_id":"sha256:9ad528be1fe908eee37bd14f90f4e664e249411a0a07d2d4510ec68e23832575","target":"graph","created_at":"2026-07-05T07:22:51Z","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/2312.06668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Taiwanese Hokkien is declining in use and status due to a language shift towards Mandarin in Taiwan. This is partly why it is a low resource language in NLP and speech research today. To ensure that the state of the art in speech processing does not leave Taiwanese Hokkien behind, we contribute a 1.5-hour dataset of Taiwanese Hokkien to ML-SUPERB's hidden set. Evaluating ML-SUPERB's suite of self-supervised learning (SSL) speech representations on our dataset, we find that model size does not consistently determine performance. In fact, certain smaller models outperform larger ones. Furthermor","authors_text":"Alice Wen-Hsin Bi, Bryan Y. Chen, Carol Yang, Chenxuan Cui, Iu-Tshian Phoann, Jiatong Shi, Jo-Peng Chiang, Kalvin Chang, Meng-Ju Wu, Noel Chen, Po-Yen Yeh, Rong-Wei Pai, Winnie Chang, Winston Ou, Yi-Hui Chou","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T01:32:20Z","title":"Evaluating Self-supervised Speech Models on a Taiwanese Hokkien Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06668","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":"sha256:61a21dabd30ecc3c398e0ef7858e29fba89c34ef842d0a76ee6fb0a3388069ac","target":"record","created_at":"2026-07-05T07:22:51Z","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":"38015e3bf02bc0a927e8cbd549f845f16895e91b67dce97b1c343f43fb1c299b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T01:32:20Z","title_canon_sha256":"bffe645e28e43fa9b7165552e0df989f5b60353f059c92017bb998110b6d0a0a"},"schema_version":"1.0","source":{"id":"2312.06668","kind":"arxiv","version":1}},"canonical_sha256":"cbed4334e6d3c928c741680e4998a0a745d833f4d61b7d41d0df2d15a7fcef34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbed4334e6d3c928c741680e4998a0a745d833f4d61b7d41d0df2d15a7fcef34","first_computed_at":"2026-07-05T07:22:51.150178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:51.150178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GWstREYF59rAAufX5u/7VQu/PXEKAEu6mQ0yrnYt7rWEt9mnR5aFzcATmHliMRGME/7IejilJ3QpGRK+sxpKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:51.150637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61a21dabd30ecc3c398e0ef7858e29fba89c34ef842d0a76ee6fb0a3388069ac","sha256:9ad528be1fe908eee37bd14f90f4e664e249411a0a07d2d4510ec68e23832575"],"state_sha256":"6f79a27b966449cb816286dc54ba2657be816e0d0fbaf00c20d31129697fbcbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbueQhlz0QYWv1ij7FkPwGj+jql42BY0fH0FxNgJ93mpu4Qxyr8CspDCXWsjr4mGVHDMsJCm0Avm7OfZJzO7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:56:13.902503Z","bundle_sha256":"816bd4f920715fa78e0ec0dcd1514fe26f0867d811f93ad59bad212b00069911"}}