{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HEGEGVG7AJ3ABYU55R4CVYNRAF","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":"3a3e175f0079c8e3f33b6bca79e6aec11dffd064081c8c24ba7e78b69867fd5d","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T07:53:23Z","title_canon_sha256":"85d24268ef5725053ba415673c91df4f2e27ca39954d877e47a82e5efe9b6cfa"},"schema_version":"1.0","source":{"id":"2305.15814","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15814","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15814v3","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15814","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"HEGEGVG7AJ3A","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"HEGEGVG7AJ3ABYU5","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"HEGEGVG7","created_at":"2026-07-05T07:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:426a90db040436c61ea917f6c5290cff9a4fc20603a2684719b6b5da86a974ec","target":"graph","created_at":"2026-07-05T07:05:09Z","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/2305.15814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We create publicly available language identification (LID) datasets and models in all 22 Indian languages listed in the Indian constitution in both native-script and romanized text. First, we create Bhasha-Abhijnaanam, a language identification test set for native-script as well as romanized text which spans all 22 Indic languages. We also train IndicLID, a language identifier for all the above-mentioned languages in both native and romanized script. For native-script text, it has better language coverage than existing LIDs and is competitive or better than other LIDs. IndicLID is the first LI","authors_text":"Anoop Kunchukuttan, Mitesh M. Khapra, Yash Madhani","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T07:53:23Z","title":"Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15814","kind":"arxiv","version":3},"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:c6ac3032187d6c0ebdfa7a8b7696106095ced44642ebac30505ea740c35ea54c","target":"record","created_at":"2026-07-05T07:05:09Z","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":"3a3e175f0079c8e3f33b6bca79e6aec11dffd064081c8c24ba7e78b69867fd5d","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T07:53:23Z","title_canon_sha256":"85d24268ef5725053ba415673c91df4f2e27ca39954d877e47a82e5efe9b6cfa"},"schema_version":"1.0","source":{"id":"2305.15814","kind":"arxiv","version":3}},"canonical_sha256":"390c4354df027600e29dec782ae1b101573502861552324db3042258a25ff61c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"390c4354df027600e29dec782ae1b101573502861552324db3042258a25ff61c","first_computed_at":"2026-07-05T07:05:09.158294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:09.158294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"46n+fYQs5zoLLIo/Y7dO4lljp51JmCFDKjC1CFUh1Pxgt0pk7NIMdxcl4g1TL5LJK7erdVBkQNglRtuPP3T9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:09.158827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15814","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6ac3032187d6c0ebdfa7a8b7696106095ced44642ebac30505ea740c35ea54c","sha256:426a90db040436c61ea917f6c5290cff9a4fc20603a2684719b6b5da86a974ec"],"state_sha256":"1bb61dd13006ee5cc623fdb18ec729191f736b681e312ff3279a039bd879761b"}