{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6FOHAJI2JEICMB5NDW5CNLO4E2","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":"a0cabc3ed0a7e460726bff0037e216a0f7dd91138731e6c242b9c16fc6d13c55","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T08:47:11Z","title_canon_sha256":"4f46e6124eda14ea1395509dd0925d3f0e1949c0da9f3a5ff871b7e6e110ce0d"},"schema_version":"1.0","source":{"id":"2505.05056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05056","created_at":"2026-07-05T11:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05056v1","created_at":"2026-07-05T11:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05056","created_at":"2026-07-05T11:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"6FOHAJI2JEIC","created_at":"2026-07-05T11:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"6FOHAJI2JEICMB5N","created_at":"2026-07-05T11:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"6FOHAJI2","created_at":"2026-07-05T11:00:18Z"}],"graph_snapshots":[{"event_id":"sha256:604c926ea33e6d537ceb0735afd072b7376a2ec04c7f00b7e335fe70efbe904f","target":"graph","created_at":"2026-07-05T11:00:18Z","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/2505.05056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper reports the construction of the Teochew-Wild, a speech corpus of the Teochew dialect. The corpus includes 18.9 hours of in-the-wild Teochew speech data from multiple speakers, covering both formal and colloquial expressions, with precise orthographic and pinyin annotations. Additionally, we provide supplementary text processing tools and resources to propel research and applications in speech tasks for this low-resource language, such as automatic speech recognition (ASR) and text-to-speech (TTS). To the best of our knowledge, this is the first publicly available Teochew dataset wit","authors_text":"Chenglong Jiang, Gaoze Hou, Linrong Pan, Ying Gao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T08:47:11Z","title":"Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05056","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:cfd7dc19570b8def9f3a1b892c72dda7b62b13bd03da1df31d80f244f9695e0d","target":"record","created_at":"2026-07-05T11:00:18Z","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":"a0cabc3ed0a7e460726bff0037e216a0f7dd91138731e6c242b9c16fc6d13c55","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T08:47:11Z","title_canon_sha256":"4f46e6124eda14ea1395509dd0925d3f0e1949c0da9f3a5ff871b7e6e110ce0d"},"schema_version":"1.0","source":{"id":"2505.05056","kind":"arxiv","version":1}},"canonical_sha256":"f15c70251a49102607ad1dba26addc26b8da53916c0dd6da963de8fe3052104c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f15c70251a49102607ad1dba26addc26b8da53916c0dd6da963de8fe3052104c","first_computed_at":"2026-07-05T11:00:18.366226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:18.366226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U6DYhFd9FDcLC9A8gdsZ6oUtJE5t0a5HXVvrgsO66JL6VZilcDRyJot+pd0S20CTanQliyhswXHXdphvznGzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:18.366745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfd7dc19570b8def9f3a1b892c72dda7b62b13bd03da1df31d80f244f9695e0d","sha256:604c926ea33e6d537ceb0735afd072b7376a2ec04c7f00b7e335fe70efbe904f"],"state_sha256":"3e6b61ef2990d173197c27707575571625743c73b54a910ba8e1bc77b6a31e29"}