{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6YCNU5VDALZW4NWYJA2FJR75TM","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":"7742ce085c3c25118cdbb6120c645b3556efcee97d48e2ee8afab12a0011a2e1","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2021-01-26T15:35:35Z","title_canon_sha256":"9a24486d3cc895622846c28ab0254c151be6b635d9f41e821e05f3619c4d1d8d"},"schema_version":"1.0","source":{"id":"2101.10877","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.10877","created_at":"2026-07-05T02:20:31Z"},{"alias_kind":"arxiv_version","alias_value":"2101.10877v3","created_at":"2026-07-05T02:20:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10877","created_at":"2026-07-05T02:20:31Z"},{"alias_kind":"pith_short_12","alias_value":"6YCNU5VDALZW","created_at":"2026-07-05T02:20:31Z"},{"alias_kind":"pith_short_16","alias_value":"6YCNU5VDALZW4NWY","created_at":"2026-07-05T02:20:31Z"},{"alias_kind":"pith_short_8","alias_value":"6YCNU5VD","created_at":"2026-07-05T02:20:31Z"}],"graph_snapshots":[{"event_id":"sha256:f6635fc5dbb6c15f248de1034f3a8cc2ea977642cb9f58a66d829f4c27264755","target":"graph","created_at":"2026-07-05T02:20:31Z","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/2101.10877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"\"Transcription bottlenecks\", created by a shortage of effective human transcribers are one of the main challenges to endangered language (EL) documentation. Automatic speech recognition (ASR) has been suggested as a tool to overcome such bottlenecks. Following this suggestion, we investigated the effectiveness for EL documentation of end-to-end ASR, which unlike Hidden Markov Model ASR systems, eschews linguistic resources but is instead more dependent on large-data settings. We open source a Yolox\\'ochitl Mixtec EL corpus. First, we review our method in building an end-to-end ASR system in a ","authors_text":"Esteban Guadalupe Sierra, Jiatong Shi, Jonathan D. Amith, Kevin Duh, Rey Castillo Garc\\'ia, Shinji Watanabe","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2021-01-26T15:35:35Z","title":"Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yolox\\'ochitl Mixtec"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10877","kind":"arxiv","version":3},"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":"sha256:8d71681c35bf1f11d8238e2b2dd27b49799a55671adf95000cef0b6d84633a16","target":"record","created_at":"2026-07-05T02:20:31Z","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":"7742ce085c3c25118cdbb6120c645b3556efcee97d48e2ee8afab12a0011a2e1","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2021-01-26T15:35:35Z","title_canon_sha256":"9a24486d3cc895622846c28ab0254c151be6b635d9f41e821e05f3619c4d1d8d"},"schema_version":"1.0","source":{"id":"2101.10877","kind":"arxiv","version":3}},"canonical_sha256":"f604da76a302f36e36d8483454c7fd9b2a2296b30359a6fe6feb36c3f04132f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f604da76a302f36e36d8483454c7fd9b2a2296b30359a6fe6feb36c3f04132f7","first_computed_at":"2026-07-05T02:20:31.741170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:31.741170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9Us2opo7kUbZpJhQmF1Xx1FI3Ha9ODBl/PvfTryzCeoNE+GH1lYWA1igLBkAXOl82TKBPK/3s6xcvjg/6mRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:31.741612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.10877","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d71681c35bf1f11d8238e2b2dd27b49799a55671adf95000cef0b6d84633a16","sha256:f6635fc5dbb6c15f248de1034f3a8cc2ea977642cb9f58a66d829f4c27264755"],"state_sha256":"0691340cd77bbabb4594638492fd130b0adf2b1cc2b4f6c303c0752df4c1304f"}