{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7Q4LM7ZESY6HA35I7AMX3PEMPC","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":"bf06b1e9048a2f5fcfa94718405ac90b09e070630506a9697d3031f76338d374","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-08T15:18:42Z","title_canon_sha256":"8b82ee82c4425b9bc06ef8a4f614a0cd9f7a232ab244cdd7989ab480eff5e6d1"},"schema_version":"1.0","source":{"id":"2501.14788","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14788","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14788v2","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14788","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"7Q4LM7ZESY6H","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"7Q4LM7ZESY6HA35I","created_at":"2026-07-05T10:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"7Q4LM7ZE","created_at":"2026-07-05T10:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:a95feb8036821d2357abe75661b908dda85cbca33647c164879b7879a5ec927b","target":"graph","created_at":"2026-07-05T10:10:48Z","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/2501.14788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study explores methods to increase data volume for low-resource languages using techniques such as crowdsourcing, pseudo-labeling, advanced data preprocessing and various permissive data sources such as audiobooks, Common Voice, YouTube. While these methods are well-explored for highresource languages, their application for low-resource languages remains underexplored. Using Armenian and Georgian as case studies, we demonstrate how linguistic and resource-specific characteristics influence the success of these methods. This work provides practical guidance for researchers to choose cost-e","authors_text":"Alexan Ayrapetyan, Ara Yeroyan, Boris Ginsburg, Mher Yerznkanyan, Nikolay Karpov, Nune Tadevosyan, Sofia Kostandian, Vitaly Lavrukhin","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-08T15:18:42Z","title":"Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14788","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":"sha256:9ae8a251d140c7cb49253d9da9b9727af9ddf00591229d8e22eeaf699647b46d","target":"record","created_at":"2026-07-05T10:10:48Z","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":"bf06b1e9048a2f5fcfa94718405ac90b09e070630506a9697d3031f76338d374","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-08T15:18:42Z","title_canon_sha256":"8b82ee82c4425b9bc06ef8a4f614a0cd9f7a232ab244cdd7989ab480eff5e6d1"},"schema_version":"1.0","source":{"id":"2501.14788","kind":"arxiv","version":2}},"canonical_sha256":"fc38b67f24963c706fa8f8197dbc8c788114f74998e895d99a02eb4d2614a089","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc38b67f24963c706fa8f8197dbc8c788114f74998e895d99a02eb4d2614a089","first_computed_at":"2026-07-05T10:10:48.283265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:48.283265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q7uxDihZ5gAU8bGFwTdQzN4aYwii7MR4VaNLdK30s6JhBqDNSHmjcRFtKDNmV5ynmv8/tminrBkiGWlDAiVdDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:48.283744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14788","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ae8a251d140c7cb49253d9da9b9727af9ddf00591229d8e22eeaf699647b46d","sha256:a95feb8036821d2357abe75661b908dda85cbca33647c164879b7879a5ec927b"],"state_sha256":"e569cfb6ec1ec0ca490fe52ebcdca0b738f479ed145695c1126b8caee5b14225"}