{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4WGJVPXGTJLHUVVKY6XQHFNLKD","short_pith_number":"pith:4WGJVPXG","canonical_record":{"source":{"id":"2205.03018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-06T05:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"85e02f4ff40d69e06cc29e117c17298404cd3b6df0ef353a034d00493ee028da","abstract_canon_sha256":"76a470a48af669140d81af57cb51617367174d73b6bf14f3b192c54669c9103a"},"schema_version":"1.0"},"canonical_sha256":"e58c9abee69a567a56aac7af0395ab50d6c86c64efc675e5a24914981fb6daea","source":{"kind":"arxiv","id":"2205.03018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03018","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03018v2","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03018","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"4WGJVPXGTJLH","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"4WGJVPXGTJLHUVVK","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"4WGJVPXG","created_at":"2026-07-05T07:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4WGJVPXGTJLHUVVKY6XQHFNLKD","target":"record","payload":{"canonical_record":{"source":{"id":"2205.03018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-06T05:13:12Z","cross_cats_sorted":[],"title_canon_sha256":"85e02f4ff40d69e06cc29e117c17298404cd3b6df0ef353a034d00493ee028da","abstract_canon_sha256":"76a470a48af669140d81af57cb51617367174d73b6bf14f3b192c54669c9103a"},"schema_version":"1.0"},"canonical_sha256":"e58c9abee69a567a56aac7af0395ab50d6c86c64efc675e5a24914981fb6daea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:04.546612Z","signature_b64":"vIuDK3ivmAa/xdlf8NW8Z3LIbvkX30eUHYN0v7LTAxIYlnZqqAxl7pzJMSKhDkwXzeFz6LHp7oCqAbCMd4PVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e58c9abee69a567a56aac7af0395ab50d6c86c64efc675e5a24914981fb6daea","last_reissued_at":"2026-07-05T07:05:04.546063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:04.546063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.03018","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zINatjcEJd3WCA/qUH7kuGOqbcLV0UC+TpLTGi/4N2RP0AshIRHXfQOXZeLcDH1LRLex4zuwxUqIeOa2haWACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:03:44.495333Z"},"content_sha256":"b3bd01c3ad6f625b8cadd7903276cc925688119e117a87b59a78ca1fe286866c","schema_version":"1.0","event_id":"sha256:b3bd01c3ad6f625b8cadd7903276cc925688119e117a87b59a78ca1fe286866c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4WGJVPXGTJLHUVVKY6XQHFNLKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Gokul NC, Mitesh M. Khapra, Pratyush Kumar, Priyanka Bedekar, Ruchi Khapra, Sushane Parthan, Yash Madhani","submitted_at":"2022-05-06T05:13:12Z","abstract_excerpt":"Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs. However, few training and evaluation sets are publicly available. We introduce Aksharantar, the largest publicly available transliteration dataset for Indian languages created by mining from monolingual and parallel corpora, as well as collecting data from human annotators. The dataset contains 26 million transliteration pairs for 21 Indic languages from 3 language families using 12 scripts. Aksharantar is 21 times larger than existing datasets and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03018","kind":"arxiv","version":2},"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/2205.03018/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D6hOxNNIwSPbC50L04mBzue7R9Uh1wyXr9zVuC/69y6nGlGYNO4vttVDyhzTUth0kyZu23iE77uATnkFoHXKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T10:03:44.495944Z"},"content_sha256":"f7d2ddbe64c3f5edd73bb2d919c065f06e48ff15e2a62875bea06269e03c6e43","schema_version":"1.0","event_id":"sha256:f7d2ddbe64c3f5edd73bb2d919c065f06e48ff15e2a62875bea06269e03c6e43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD/bundle.json","state_url":"https://pith.science/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T10:03:44Z","links":{"resolver":"https://pith.science/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD","bundle":"https://pith.science/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD/bundle.json","state":"https://pith.science/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WGJVPXGTJLHUVVKY6XQHFNLKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4WGJVPXGTJLHUVVKY6XQHFNLKD","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":"76a470a48af669140d81af57cb51617367174d73b6bf14f3b192c54669c9103a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-06T05:13:12Z","title_canon_sha256":"85e02f4ff40d69e06cc29e117c17298404cd3b6df0ef353a034d00493ee028da"},"schema_version":"1.0","source":{"id":"2205.03018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03018","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03018v2","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03018","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"4WGJVPXGTJLH","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"4WGJVPXGTJLHUVVK","created_at":"2026-07-05T07:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"4WGJVPXG","created_at":"2026-07-05T07:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:f7d2ddbe64c3f5edd73bb2d919c065f06e48ff15e2a62875bea06269e03c6e43","target":"graph","created_at":"2026-07-05T07:05:04Z","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/2205.03018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs. However, few training and evaluation sets are publicly available. We introduce Aksharantar, the largest publicly available transliteration dataset for Indian languages created by mining from monolingual and parallel corpora, as well as collecting data from human annotators. The dataset contains 26 million transliteration pairs for 21 Indic languages from 3 language families using 12 scripts. Aksharantar is 21 times larger than existing datasets and i","authors_text":"Anoop Kunchukuttan, Gokul NC, Mitesh M. Khapra, Pratyush Kumar, Priyanka Bedekar, Ruchi Khapra, Sushane Parthan, Yash Madhani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-06T05:13:12Z","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03018","kind":"arxiv","version":2},"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:b3bd01c3ad6f625b8cadd7903276cc925688119e117a87b59a78ca1fe286866c","target":"record","created_at":"2026-07-05T07:05:04Z","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":"76a470a48af669140d81af57cb51617367174d73b6bf14f3b192c54669c9103a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-06T05:13:12Z","title_canon_sha256":"85e02f4ff40d69e06cc29e117c17298404cd3b6df0ef353a034d00493ee028da"},"schema_version":"1.0","source":{"id":"2205.03018","kind":"arxiv","version":2}},"canonical_sha256":"e58c9abee69a567a56aac7af0395ab50d6c86c64efc675e5a24914981fb6daea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e58c9abee69a567a56aac7af0395ab50d6c86c64efc675e5a24914981fb6daea","first_computed_at":"2026-07-05T07:05:04.546063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:04.546063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vIuDK3ivmAa/xdlf8NW8Z3LIbvkX30eUHYN0v7LTAxIYlnZqqAxl7pzJMSKhDkwXzeFz6LHp7oCqAbCMd4PVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:04.546612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.03018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3bd01c3ad6f625b8cadd7903276cc925688119e117a87b59a78ca1fe286866c","sha256:f7d2ddbe64c3f5edd73bb2d919c065f06e48ff15e2a62875bea06269e03c6e43"],"state_sha256":"f8a2a2add824ba57408ab32d9f9e475e5f3c87fff015cb9f77e5a6c18ba95a1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/P5cMNrY4gxmzIlmhIt5axU7OvzlL/V3HW4hZfuntQjlIXD7TjHPOx0XVb66S6MAMdyTya/L6BRm4fa4ENEiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T10:03:44.511782Z","bundle_sha256":"47b48b9efe87ae02769fc9ce3813d4f3e7ef9d713d983936a6b5e80926b4717d"}}