{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KDK4PJJGLRY5G56AGTARJT6AHW","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":"ac055c5eee3e8f58c3db66fa4bb4e6dd85451b6bb23e032b78827bd9153c67bf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-20T19:59:49Z","title_canon_sha256":"27bf48d9fb947a13758b47abd4eb2af5b522ecc7cb9ede79f0b5f9c222a59e53"},"schema_version":"1.0","source":{"id":"2506.17459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17459","created_at":"2026-07-05T11:26:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17459v1","created_at":"2026-07-05T11:26:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17459","created_at":"2026-07-05T11:26:32Z"},{"alias_kind":"pith_short_12","alias_value":"KDK4PJJGLRY5","created_at":"2026-07-05T11:26:32Z"},{"alias_kind":"pith_short_16","alias_value":"KDK4PJJGLRY5G56A","created_at":"2026-07-05T11:26:32Z"},{"alias_kind":"pith_short_8","alias_value":"KDK4PJJG","created_at":"2026-07-05T11:26:32Z"}],"graph_snapshots":[{"event_id":"sha256:02616b1eeea2b88152afe4f495ef79c87a40ac9499772b0a758cf2cd8a478c5b","target":"graph","created_at":"2026-07-05T11:26:32Z","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/2506.17459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including spontaneous speech, environmental noise, and severely constrained datasets from under-documented languages. In this paper, we benchmark the performance of two fine-tuned multilingual ASR models, MMS and XLS-R, on five typologically diverse low-resource languages with control of training data duration. Our findings show that MMS is best suited when extremely small a","authors_text":"Gina-Anne Levow, Siyu Liang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-20T19:59:49Z","title":"Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17459","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":"sha256:0b113028d827b406c011e770e688db792c6522f9ea2dc51cd3d655129087e5ed","target":"record","created_at":"2026-07-05T11:26:32Z","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":"ac055c5eee3e8f58c3db66fa4bb4e6dd85451b6bb23e032b78827bd9153c67bf","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-20T19:59:49Z","title_canon_sha256":"27bf48d9fb947a13758b47abd4eb2af5b522ecc7cb9ede79f0b5f9c222a59e53"},"schema_version":"1.0","source":{"id":"2506.17459","kind":"arxiv","version":1}},"canonical_sha256":"50d5c7a5265c71d377c034c114cfc03da18704c4f29286bcff28fa1e5d105948","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50d5c7a5265c71d377c034c114cfc03da18704c4f29286bcff28fa1e5d105948","first_computed_at":"2026-07-05T11:26:32.601875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:32.601875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUq2o94nLbDkuJuUHhaeLGv2eCLZ4F/hUwfwQAE5BuzdmS3wE/oLxdH4KycnAdUdB7Jur33Nm6yBjCdvhXqxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:32.602349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b113028d827b406c011e770e688db792c6522f9ea2dc51cd3d655129087e5ed","sha256:02616b1eeea2b88152afe4f495ef79c87a40ac9499772b0a758cf2cd8a478c5b"],"state_sha256":"963d29ad88d563f32e4f677aeadcd13f17b444c6d7d87f4f315e69f767b0d8e0"}