{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FMOOKZWKVU3ED7V2R4AU73HRUH","short_pith_number":"pith:FMOOKZWK","canonical_record":{"source":{"id":"2212.05409","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-11T04:45:50Z","cross_cats_sorted":[],"title_canon_sha256":"1d74608886f302b750738a692bcc2406f2062d24ccc072a0dafa69d18a5edd82","abstract_canon_sha256":"f77e797d3dffb1f75d8210460cae0972b115f0db5d3a0b65023de814e2c937ca"},"schema_version":"1.0"},"canonical_sha256":"2b1ce566caad3641feba8f014fecf1a1eaff4b8e6f216885ca6b1388753fdab6","source":{"kind":"arxiv","id":"2212.05409","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05409","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05409v3","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05409","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"FMOOKZWKVU3E","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"FMOOKZWKVU3ED7V2","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"FMOOKZWK","created_at":"2026-07-05T06:13:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FMOOKZWKVU3ED7V2R4AU73HRUH","target":"record","payload":{"canonical_record":{"source":{"id":"2212.05409","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-11T04:45:50Z","cross_cats_sorted":[],"title_canon_sha256":"1d74608886f302b750738a692bcc2406f2062d24ccc072a0dafa69d18a5edd82","abstract_canon_sha256":"f77e797d3dffb1f75d8210460cae0972b115f0db5d3a0b65023de814e2c937ca"},"schema_version":"1.0"},"canonical_sha256":"2b1ce566caad3641feba8f014fecf1a1eaff4b8e6f216885ca6b1388753fdab6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:18.009085Z","signature_b64":"MN/V+i08Yf2Z0iva52RoPBdWwfcMczIL2YjPBWowgAgmRpZav9hziC45S6Z7f9qqDWfFTenpMl0b1bZAMkXxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b1ce566caad3641feba8f014fecf1a1eaff4b8e6f216885ca6b1388753fdab6","last_reissued_at":"2026-07-05T06:13:18.008662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:18.008662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.05409","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuKo34MIXmL4nxnVILfgsLsm5KlqvWdtiCpSbXyoV1nWT6WijTOMrzPjK6bh+rF8spI0X+jMxMriDSyvlZphBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:13:37.066846Z"},"content_sha256":"1bff75de2899a2eda72176c03a7c58c6a23a47a9060ec611ae7fd293812518cf","schema_version":"1.0","event_id":"sha256:1bff75de2899a2eda72176c03a7c58c6a23a47a9060ec611ae7fd293812518cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FMOOKZWKVU3ED7V2R4AU73HRUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Gowtham Ramesh, Mitesh M. Khapra, Pratyush Kumar, Rahul Aralikatte, Shreya Goyal, Sumanth Doddapaneni","submitted_at":"2022-12-11T04:45:50Z","abstract_excerpt":"Building Natural Language Understanding (NLU) capabilities for Indic languages, which have a collective speaker base of more than one billion speakers is absolutely crucial. In this work, we aim to improve the NLU capabilities of Indic languages by making contributions along 3 important axes (i) monolingual corpora (ii) NLU testsets (iii) multilingual LLMs focusing on Indic languages. Specifically, we curate the largest monolingual corpora, IndicCorp, with 20.9B tokens covering 24 languages from 4 language families - a 2.3x increase over prior work, while supporting 12 additional languages. Ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05409","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/2212.05409/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":"2026-07-05T06:13:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CTzkUAN+qJdHozcJcBurwvfykd+XhTdLANn12es6b9sW6W+Di3g+8V1BeqJMn+KrOPLcz2qDuSxr2iTE8zreCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:13:37.067377Z"},"content_sha256":"da186c0c3e561d102f6973a18d72ccd3c3cdcce5c56685386c3a36a27d26ca92","schema_version":"1.0","event_id":"sha256:da186c0c3e561d102f6973a18d72ccd3c3cdcce5c56685386c3a36a27d26ca92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMOOKZWKVU3ED7V2R4AU73HRUH/bundle.json","state_url":"https://pith.science/pith/FMOOKZWKVU3ED7V2R4AU73HRUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMOOKZWKVU3ED7V2R4AU73HRUH/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":"2026-08-19T11:13:37Z","links":{"resolver":"https://pith.science/pith/FMOOKZWKVU3ED7V2R4AU73HRUH","bundle":"https://pith.science/pith/FMOOKZWKVU3ED7V2R4AU73HRUH/bundle.json","state":"https://pith.science/pith/FMOOKZWKVU3ED7V2R4AU73HRUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMOOKZWKVU3ED7V2R4AU73HRUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FMOOKZWKVU3ED7V2R4AU73HRUH","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":"f77e797d3dffb1f75d8210460cae0972b115f0db5d3a0b65023de814e2c937ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-11T04:45:50Z","title_canon_sha256":"1d74608886f302b750738a692bcc2406f2062d24ccc072a0dafa69d18a5edd82"},"schema_version":"1.0","source":{"id":"2212.05409","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.05409","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.05409v3","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05409","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"FMOOKZWKVU3E","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"FMOOKZWKVU3ED7V2","created_at":"2026-07-05T06:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"FMOOKZWK","created_at":"2026-07-05T06:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:da186c0c3e561d102f6973a18d72ccd3c3cdcce5c56685386c3a36a27d26ca92","target":"graph","created_at":"2026-07-05T06:13:18Z","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/2212.05409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building Natural Language Understanding (NLU) capabilities for Indic languages, which have a collective speaker base of more than one billion speakers is absolutely crucial. In this work, we aim to improve the NLU capabilities of Indic languages by making contributions along 3 important axes (i) monolingual corpora (ii) NLU testsets (iii) multilingual LLMs focusing on Indic languages. Specifically, we curate the largest monolingual corpora, IndicCorp, with 20.9B tokens covering 24 languages from 4 language families - a 2.3x increase over prior work, while supporting 12 additional languages. Ne","authors_text":"Anoop Kunchukuttan, Gowtham Ramesh, Mitesh M. Khapra, Pratyush Kumar, Rahul Aralikatte, Shreya Goyal, Sumanth Doddapaneni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-11T04:45:50Z","title":"Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05409","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":"sha256:1bff75de2899a2eda72176c03a7c58c6a23a47a9060ec611ae7fd293812518cf","target":"record","created_at":"2026-07-05T06:13:18Z","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":"f77e797d3dffb1f75d8210460cae0972b115f0db5d3a0b65023de814e2c937ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-11T04:45:50Z","title_canon_sha256":"1d74608886f302b750738a692bcc2406f2062d24ccc072a0dafa69d18a5edd82"},"schema_version":"1.0","source":{"id":"2212.05409","kind":"arxiv","version":3}},"canonical_sha256":"2b1ce566caad3641feba8f014fecf1a1eaff4b8e6f216885ca6b1388753fdab6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b1ce566caad3641feba8f014fecf1a1eaff4b8e6f216885ca6b1388753fdab6","first_computed_at":"2026-07-05T06:13:18.008662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:18.008662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MN/V+i08Yf2Z0iva52RoPBdWwfcMczIL2YjPBWowgAgmRpZav9hziC45S6Z7f9qqDWfFTenpMl0b1bZAMkXxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:18.009085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.05409","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bff75de2899a2eda72176c03a7c58c6a23a47a9060ec611ae7fd293812518cf","sha256:da186c0c3e561d102f6973a18d72ccd3c3cdcce5c56685386c3a36a27d26ca92"],"state_sha256":"39ff24e79780325cd4c5a5bb72e7c806e65544edebf508d50efa72179a222005"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isMbBC+cH2EjCZVWl5AGo8LnRkyAHzSWwABP9cm81KbEEqFMG0yuX9TXSnxy0bL7bSyTboQA9HR+QTnGWxM0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:13:37.073129Z","bundle_sha256":"9731d8b30387052c3661e4818c37d2983ba45cfcddc1a8b222516754caf2727c"}}