{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PXQP3MZ5QKL6DK5M3SDE2JHIUK","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":"8cb0be24c7f945b2fc36498492c025943eb597f2459a446fbec5578ee6f420b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:06:27Z","title_canon_sha256":"b66efe9dd54889d0043e391d56359527db74211f50016f9d3e6a68e93f7953ef"},"schema_version":"1.0","source":{"id":"2407.12481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12481","created_at":"2026-07-05T10:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12481v2","created_at":"2026-07-05T10:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12481","created_at":"2026-07-05T10:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"PXQP3MZ5QKL6","created_at":"2026-07-05T10:42:36Z"},{"alias_kind":"pith_short_16","alias_value":"PXQP3MZ5QKL6DK5M","created_at":"2026-07-05T10:42:36Z"},{"alias_kind":"pith_short_8","alias_value":"PXQP3MZ5","created_at":"2026-07-05T10:42:36Z"}],"graph_snapshots":[{"event_id":"sha256:c62f7eafcef203e17a69623d2e5277018ed151e9d7178fcee2d6a937ee305281","target":"graph","created_at":"2026-07-05T10:42:36Z","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/2407.12481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel approach to data preparation for developing multilingual Indic large language model. Our meticulous data acquisition spans open-source and proprietary sources, including Common Crawl, Indic books, news articles, and Wikipedia, ensuring a diverse and rich linguistic representation. For each Indic language, we design a custom preprocessing pipeline to effectively eliminate redundant and low-quality text content. Additionally, we perform deduplication on Common Crawl data to address the redundancy present in 70% of the crawled web pages. This study focuses on developing high-qu","authors_text":"Chandra Khatri, Daud Ibrahim, Deepak Kumarr, Divyansh Rajput, Gautam Bhargava, Pidathala Sowjanya, Rahul Kumar, Rishabh Nahata, Shubham Kakde","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:06:27Z","title":"Krutrim LLM: A Novel Tokenization Strategy for Multilingual Indic Languages with Petabyte-Scale Data Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12481","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":"sha256:35bc3e6a35e054bf36a0fac1a806e2b98335ce223757cf22ae377c90d52617f0","target":"record","created_at":"2026-07-05T10:42:36Z","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":"8cb0be24c7f945b2fc36498492c025943eb597f2459a446fbec5578ee6f420b3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-17T11:06:27Z","title_canon_sha256":"b66efe9dd54889d0043e391d56359527db74211f50016f9d3e6a68e93f7953ef"},"schema_version":"1.0","source":{"id":"2407.12481","kind":"arxiv","version":2}},"canonical_sha256":"7de0fdb33d8297e1abacdc864d24e8a28f4892d7ade4e8b71fd8dfe56e4debcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7de0fdb33d8297e1abacdc864d24e8a28f4892d7ade4e8b71fd8dfe56e4debcb","first_computed_at":"2026-07-05T10:42:36.222012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:36.222012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"izdpLVsLqrfST6rA+R5battj5D95XEgMvrCxyVBHsdnFn/BO4KRbhzHBnIiTt1N3ebf3kDtnF/XtDi91hfK2Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:36.222543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35bc3e6a35e054bf36a0fac1a806e2b98335ce223757cf22ae377c90d52617f0","sha256:c62f7eafcef203e17a69623d2e5277018ed151e9d7178fcee2d6a937ee305281"],"state_sha256":"5dc6b2de3cb6221fd62a572ee7f5deb00ef298fa2a4a85519b46ce5316a05a5f"}