{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RBBNZTDFKSCERWGWWEBCV7LDGE","short_pith_number":"pith:RBBNZTDF","schema_version":"1.0","canonical_sha256":"8842dccc65548448d8d6b1022afd6331206a6fd78fa273fcfcf5d55488a60dcb","source":{"kind":"arxiv","id":"2305.16307","version":3},"attestation_state":"computed","paper":{"title":"IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Anupama Sujatha, Aswanth Kumar, Janki Nawale, Jay Gala, Mitesh M. Khapra, Pranjal A. Chitale, Pratyush Kumar, Raghavan AK, Raj Dabre, Ratish Puduppully, Sumanth Doddapaneni, Varun Gumma, Vivek Raghavan","submitted_at":"2023-05-25T17:57:43Z","abstract_excerpt":"India has a rich linguistic landscape with languages from 4 major language families spoken by over a billion people. 22 of these languages are listed in the Constitution of India (referred to as scheduled languages) are the focus of this work. Given the linguistic diversity, high-quality and accessible Machine Translation (MT) systems are essential in a country like India. Prior to this work, there was (i) no parallel training data spanning all 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models"},"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":"2305.16307","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T17:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"044eed29be241cb2ca6cc2dc836e9edd1ed8776f34e2eaff1522438ab6452946","abstract_canon_sha256":"1096fcd37e653d1cb89530e7eb19750b99df3781546558e7728c255a47a970ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:14.484200Z","signature_b64":"17b9z4wqjH0ao5mFMeKWaLqZ0szb2oWLHZn/uR8MwYCquCC088T/tYVAObtkG4ZtxWyZQ20QUliI3S56pQkjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8842dccc65548448d8d6b1022afd6331206a6fd78fa273fcfcf5d55488a60dcb","last_reissued_at":"2026-07-05T07:26:14.483733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:14.483733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Anupama Sujatha, Aswanth Kumar, Janki Nawale, Jay Gala, Mitesh M. Khapra, Pranjal A. Chitale, Pratyush Kumar, Raghavan AK, Raj Dabre, Ratish Puduppully, Sumanth Doddapaneni, Varun Gumma, Vivek Raghavan","submitted_at":"2023-05-25T17:57:43Z","abstract_excerpt":"India has a rich linguistic landscape with languages from 4 major language families spoken by over a billion people. 22 of these languages are listed in the Constitution of India (referred to as scheduled languages) are the focus of this work. Given the linguistic diversity, high-quality and accessible Machine Translation (MT) systems are essential in a country like India. Prior to this work, there was (i) no parallel training data spanning all 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16307","kind":"arxiv","version":3},"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/2305.16307/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":"2305.16307","created_at":"2026-07-05T07:26:14.483785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16307v3","created_at":"2026-07-05T07:26:14.483785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16307","created_at":"2026-07-05T07:26:14.483785+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBBNZTDFKSCE","created_at":"2026-07-05T07:26:14.483785+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBBNZTDFKSCERWGW","created_at":"2026-07-05T07:26:14.483785+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBBNZTDF","created_at":"2026-07-05T07:26:14.483785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25365","citing_title":"Neural Machine Translation for Low-Resource Tangkhul--English","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08272","citing_title":"AgriGov: A Structured Multilingual Dataset Curation for Indian Government Schemes for Farmers","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20712","citing_title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28796","citing_title":"Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29379","citing_title":"BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20712","citing_title":"SCRIBE: Diagnostic Evaluation and Rich Transcription Models for Indic ASR","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18914","citing_title":"MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18423","citing_title":"BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE","json":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE.json","graph_json":"https://pith.science/api/pith-number/RBBNZTDFKSCERWGWWEBCV7LDGE/graph.json","events_json":"https://pith.science/api/pith-number/RBBNZTDFKSCERWGWWEBCV7LDGE/events.json","paper":"https://pith.science/paper/RBBNZTDF"},"agent_actions":{"view_html":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE","download_json":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE.json","view_paper":"https://pith.science/paper/RBBNZTDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16307&json=true","fetch_graph":"https://pith.science/api/pith-number/RBBNZTDFKSCERWGWWEBCV7LDGE/graph.json","fetch_events":"https://pith.science/api/pith-number/RBBNZTDFKSCERWGWWEBCV7LDGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE/action/storage_attestation","attest_author":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE/action/author_attestation","sign_citation":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE/action/citation_signature","submit_replication":"https://pith.science/pith/RBBNZTDFKSCERWGWWEBCV7LDGE/action/replication_record"}},"created_at":"2026-07-05T07:26:14.483785+00:00","updated_at":"2026-07-05T07:26:14.483785+00:00"}