{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FJ4VJMEWN46OWPHKOKVD3AKVHO","short_pith_number":"pith:FJ4VJMEW","schema_version":"1.0","canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","source":{"kind":"arxiv","id":"1803.09405","version":1},"attestation_state":"computed","paper":{"title":"Automatic Identification of Closely-related Indian Languages: Resources and Experiments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdul Basit, Atul Kr. Ojha, Bornini Lahiri, Deepak Alok, Mayank Jain, Ritesh Kumar, Yogesh Dawer","submitted_at":"2018-03-26T04:02:00Z","abstract_excerpt":"In this paper, we discuss an attempt to develop an automatic language identification system for 5 closely-related Indo-Aryan languages of India, Awadhi, Bhojpuri, Braj, Hindi and Magahi. We have compiled a comparable corpora of varying length for these languages from various resources. We discuss the method of creation of these corpora in detail. Using these corpora, a language identification system was developed, which currently gives state of the art accuracy of 96.48\\%. We also used these corpora to study the similarity between the 5 languages at the lexical level, which is the first data-b"},"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":"1803.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-26T04:02:00Z","cross_cats_sorted":[],"title_canon_sha256":"60c8d29582e3ece70c8645974af559a25421be6d6c01034db6138ffbe67728cc","abstract_canon_sha256":"1afd6556b6fb8b57f41e9a031c30c63291f0ab4b68520ef5b928d3e395cd9189"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:11.711970Z","signature_b64":"3DtbQwUikYQbS3+f9UfWqqrS01e9deyAhCaYqE1T8RSleuwaheudjQMVhayg6MEvO+81UMiF+BEl242kTX5nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a7954b0966f3ceb3cea72aa3d81553bb38918a1a210fd13c1f6481e67da1868","last_reissued_at":"2026-05-18T00:20:11.711327Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:11.711327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Identification of Closely-related Indian Languages: Resources and Experiments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdul Basit, Atul Kr. Ojha, Bornini Lahiri, Deepak Alok, Mayank Jain, Ritesh Kumar, Yogesh Dawer","submitted_at":"2018-03-26T04:02:00Z","abstract_excerpt":"In this paper, we discuss an attempt to develop an automatic language identification system for 5 closely-related Indo-Aryan languages of India, Awadhi, Bhojpuri, Braj, Hindi and Magahi. We have compiled a comparable corpora of varying length for these languages from various resources. We discuss the method of creation of these corpora in detail. Using these corpora, a language identification system was developed, which currently gives state of the art accuracy of 96.48\\%. We also used these corpora to study the similarity between the 5 languages at the lexical level, which is the first data-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09405","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":""},"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":"1803.09405","created_at":"2026-05-18T00:20:11.711425+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09405v1","created_at":"2026-05-18T00:20:11.711425+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09405","created_at":"2026-05-18T00:20:11.711425+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJ4VJMEWN46O","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJ4VJMEWN46OWPHK","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJ4VJMEW","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO","json":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO.json","graph_json":"https://pith.science/api/pith-number/FJ4VJMEWN46OWPHKOKVD3AKVHO/graph.json","events_json":"https://pith.science/api/pith-number/FJ4VJMEWN46OWPHKOKVD3AKVHO/events.json","paper":"https://pith.science/paper/FJ4VJMEW"},"agent_actions":{"view_html":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO","download_json":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO.json","view_paper":"https://pith.science/paper/FJ4VJMEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09405&json=true","fetch_graph":"https://pith.science/api/pith-number/FJ4VJMEWN46OWPHKOKVD3AKVHO/graph.json","fetch_events":"https://pith.science/api/pith-number/FJ4VJMEWN46OWPHKOKVD3AKVHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/action/storage_attestation","attest_author":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/action/author_attestation","sign_citation":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/action/citation_signature","submit_replication":"https://pith.science/pith/FJ4VJMEWN46OWPHKOKVD3AKVHO/action/replication_record"}},"created_at":"2026-05-18T00:20:11.711425+00:00","updated_at":"2026-05-18T00:20:11.711425+00:00"}