{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W3LZ3V3NPRB2FESE2XRYFIZJWU","short_pith_number":"pith:W3LZ3V3N","schema_version":"1.0","canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","source":{"kind":"arxiv","id":"2312.04764","version":1},"attestation_state":"computed","paper":{"title":"First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya Kalita, Atnafu Lambebo Tonja, Jugal Kalita, Melkamu Mersha, Olga Kolesnikova","submitted_at":"2023-12-08T00:28:41Z","abstract_excerpt":"This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of langu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.04764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T00:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"9d8b9b322da8f9f6697436458d5018b40a61958932ada10cf76eaa6dd3db58d3","abstract_canon_sha256":"a609210190713fde878985ada671b5e33558b890e4e420b2ca52cb3e48552011"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:51.047376Z","signature_b64":"HgDodxaP13/f7EmIVf/s2dhudYadzRCKQrH3MSLcnh+iqTXdCy2wV2rzkWkv60pElpyJ0hLl1Pna54hCDPYeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","last_reissued_at":"2026-07-05T07:21:51.046898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:51.046898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya Kalita, Atnafu Lambebo Tonja, Jugal Kalita, Melkamu Mersha, Olga Kolesnikova","submitted_at":"2023-12-08T00:28:41Z","abstract_excerpt":"This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04764","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.04764/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.04764","created_at":"2026-07-05T07:21:51.046957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04764v1","created_at":"2026-07-05T07:21:51.046957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04764","created_at":"2026-07-05T07:21:51.046957+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3LZ3V3NPRB2","created_at":"2026-07-05T07:21:51.046957+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3LZ3V3NPRB2FESE","created_at":"2026-07-05T07:21:51.046957+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3LZ3V3N","created_at":"2026-07-05T07:21:51.046957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03484","citing_title":"Explainable AI: XAI-Guided Context-Aware Data Augmentation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU","json":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU.json","graph_json":"https://pith.science/api/pith-number/W3LZ3V3NPRB2FESE2XRYFIZJWU/graph.json","events_json":"https://pith.science/api/pith-number/W3LZ3V3NPRB2FESE2XRYFIZJWU/events.json","paper":"https://pith.science/paper/W3LZ3V3N"},"agent_actions":{"view_html":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU","download_json":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU.json","view_paper":"https://pith.science/paper/W3LZ3V3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04764&json=true","fetch_graph":"https://pith.science/api/pith-number/W3LZ3V3NPRB2FESE2XRYFIZJWU/graph.json","fetch_events":"https://pith.science/api/pith-number/W3LZ3V3NPRB2FESE2XRYFIZJWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/action/storage_attestation","attest_author":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/action/author_attestation","sign_citation":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/action/citation_signature","submit_replication":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/action/replication_record"}},"created_at":"2026-07-05T07:21:51.046957+00:00","updated_at":"2026-07-05T07:21:51.046957+00:00"}