{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OQS54J4UKUC6IZMAXBNGCPDCEA","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":"fc2d630076d489134b16ad5293cc3bf0733d8194b1b82ece3da9f0b5f5c36f6b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-26T17:28:38Z","title_canon_sha256":"476826a7e82ac8f817eba1494f3d0d921d8f35be7efad349b7d03903547475de"},"schema_version":"1.0","source":{"id":"2206.12931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12931","created_at":"2026-07-05T04:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12931v1","created_at":"2026-07-05T04:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12931","created_at":"2026-07-05T04:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"OQS54J4UKUC6","created_at":"2026-07-05T04:42:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQS54J4UKUC6IZMA","created_at":"2026-07-05T04:42:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQS54J4U","created_at":"2026-07-05T04:42:36Z"}],"graph_snapshots":[{"event_id":"sha256:be61c22685198b619a3eb68dbda0fb0fb68dc7d389658da05b84e5cbf52e082a","target":"graph","created_at":"2026-07-05T04:42:36Z","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/2206.12931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we discuss an in-progress work on the development of a speech corpus for four low-resource Indo-Aryan languages -- Awadhi, Bhojpuri, Braj and Magahi using the field methods of linguistic data collection. The total size of the corpus currently stands at approximately 18 hours (approx. 4-5 hours each language) and it is transcribed and annotated with grammatical information such as part-of-speech tags, morphological features and Universal dependency relationships. We discuss our methodology for data collection in these languages, most of which was done in the middle of the COVID-19","authors_text":"Atul Kr. Ojha, Bornini Lahiri, Kalika Bali, Mohit Raj, Ritesh Kumar, Shyam Ratan, Siddharth Singh, Sonal Sinha, Vivek Seshadri","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-26T17:28:38Z","title":"Annotated Speech Corpus for Low Resource Indian Languages: Awadhi, Bhojpuri, Braj and Magahi"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12931","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":"sha256:04d82879a3a8d8145cb013fcdae0d4a9d10eb51de33e2f42cfd8ac1abb2f10ca","target":"record","created_at":"2026-07-05T04:42:36Z","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":"fc2d630076d489134b16ad5293cc3bf0733d8194b1b82ece3da9f0b5f5c36f6b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-26T17:28:38Z","title_canon_sha256":"476826a7e82ac8f817eba1494f3d0d921d8f35be7efad349b7d03903547475de"},"schema_version":"1.0","source":{"id":"2206.12931","kind":"arxiv","version":1}},"canonical_sha256":"7425de27945505e46580b85a613c62200a135361d6412ecba1518f7bc9846338","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7425de27945505e46580b85a613c62200a135361d6412ecba1518f7bc9846338","first_computed_at":"2026-07-05T04:42:36.729386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:36.729386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WJuVaVgiphK30Z5twTpqgy8WBs6iyhmcd7qdJlBZxcWUCCNAGVue3eHYpOhDD/sAUMNQTyzSup2J7uczuIPSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:36.729881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04d82879a3a8d8145cb013fcdae0d4a9d10eb51de33e2f42cfd8ac1abb2f10ca","sha256:be61c22685198b619a3eb68dbda0fb0fb68dc7d389658da05b84e5cbf52e082a"],"state_sha256":"0997dcec584f38773244cf9afdc80a9bd81b070c9e8592a58261738a948ca1bd"}