{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4OAJCZXPGWDRXPCT4K76ATWPTL","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":"c72c92cca63cf88790f6feed99f5da140c99233cbd39beb0ab4b30ab916462fe","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-23T01:44:45Z","title_canon_sha256":"f9920043d33bbe1f002ce39eb1466a5c1cbc3fc7afbdcc44558a376ebfc64205"},"schema_version":"1.0","source":{"id":"2603.21478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.21478","created_at":"2026-06-23T02:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"2603.21478v2","created_at":"2026-06-23T02:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21478","created_at":"2026-06-23T02:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"4OAJCZXPGWDR","created_at":"2026-06-23T02:12:48Z"},{"alias_kind":"pith_short_16","alias_value":"4OAJCZXPGWDRXPCT","created_at":"2026-06-23T02:12:48Z"},{"alias_kind":"pith_short_8","alias_value":"4OAJCZXP","created_at":"2026-06-23T02:12:48Z"}],"graph_snapshots":[{"event_id":"sha256:709e91f639cfee3f30e606224ef1a34bf683f31d95c002b144b4f41367669c8d","target":"graph","created_at":"2026-06-23T02:12:48Z","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/2603.21478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we introduce \\textbf{TaigiSpeech}, a real-world speech intent dataset in Taiwanese Taigi (aka Taiwanese Hokkien/Southern Min), which is a low-resource and primarily spoken language. The dataset is collected from older adults, comprising 21 speakers with a total of 3k utterances. It is designed for practical intent detection scenarios, including healthcare and home assistant applications. To address the scarcity of labeled da","authors_text":"Chien-Cheng Chen, Huang-Cheng Chou, Hung-yi Lee, James Glass, Kai-Wei Chang, Shrikanth Narayanan, Wenze Ren, Yi-Cheng Lin, Yuan-Fu Liao, Yu-Han Huang, Yun-Shao Tsai, Yu Tsao","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-23T01:44:45Z","title":"TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.21478","kind":"arxiv","version":2},"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":"sha256:272729eb2ca6db6504c2e3c1cbd8efbeda655a9a8aa56dd34f3078ee868d668e","target":"record","created_at":"2026-06-23T02:12:48Z","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":"c72c92cca63cf88790f6feed99f5da140c99233cbd39beb0ab4b30ab916462fe","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-23T01:44:45Z","title_canon_sha256":"f9920043d33bbe1f002ce39eb1466a5c1cbc3fc7afbdcc44558a376ebfc64205"},"schema_version":"1.0","source":{"id":"2603.21478","kind":"arxiv","version":2}},"canonical_sha256":"e3809166ef35871bbc53e2bfe04ecf9aff1ab22201d9de78590a5320718b2b44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3809166ef35871bbc53e2bfe04ecf9aff1ab22201d9de78590a5320718b2b44","first_computed_at":"2026-06-23T02:12:48.394379Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:12:48.394379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GqXeIGDMdUZgYpkii1LX0PxA75JOAkr1wedfoTOY+gb+w+1rxtqve6aVoKGIJGWdBIJthyZWA+0uFJRwHN3IBg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:12:48.394886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.21478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:272729eb2ca6db6504c2e3c1cbd8efbeda655a9a8aa56dd34f3078ee868d668e","sha256:709e91f639cfee3f30e606224ef1a34bf683f31d95c002b144b4f41367669c8d"],"state_sha256":"14ec0abda524a7671aff433298d77d996646f1ece3971b9b98afdee5f4229d27"}