{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VBKWOW7XSUUZGXRT2GNOVW4HTM","short_pith_number":"pith:VBKWOW7X","canonical_record":{"source":{"id":"2502.09642","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T09:32:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c115bdf269f4125179e36b9dbd70d5472c88d27689cbecd00782436108d3826","abstract_canon_sha256":"c8abeec11ef1c8c6cbe44ce0f86d5b28cb83531db719e438545ded4b70c4792a"},"schema_version":"1.0"},"canonical_sha256":"a855675bf79529935e33d19aeadb879b267224ac1855343822d750763ed9f873","source":{"kind":"arxiv","id":"2502.09642","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09642","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09642v2","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09642","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"VBKWOW7XSUUZ","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"VBKWOW7XSUUZGXRT","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"VBKWOW7X","created_at":"2026-07-05T10:18:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VBKWOW7XSUUZGXRT2GNOVW4HTM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09642","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T09:32:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c115bdf269f4125179e36b9dbd70d5472c88d27689cbecd00782436108d3826","abstract_canon_sha256":"c8abeec11ef1c8c6cbe44ce0f86d5b28cb83531db719e438545ded4b70c4792a"},"schema_version":"1.0"},"canonical_sha256":"a855675bf79529935e33d19aeadb879b267224ac1855343822d750763ed9f873","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:49.894565Z","signature_b64":"5eUGOkqo4Mni+Og7ZvO9cC+e7luoD97qHVLEUMDNTOHoa2unkcj8HbzWQrVqRX5rgboNEP9dQ9GOpHAnw6sZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a855675bf79529935e33d19aeadb879b267224ac1855343822d750763ed9f873","last_reissued_at":"2026-07-05T10:18:49.894127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:49.894127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09642","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":"2026-07-05T10:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A15rwU/PBAAN40KgD+eExuiSP21CVU7uLP5isRs7ZhFuWwz/rslFhZ1Khp92phnReb3WzhFLgH5dOozStmsVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T06:25:46.378857Z"},"content_sha256":"0c9496da678909c6db395d9a6c02459874a2dea725581786b86dd162c5b904b1","schema_version":"1.0","event_id":"sha256:0c9496da678909c6db395d9a6c02459874a2dea725581786b86dd162c5b904b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VBKWOW7XSUUZGXRT2GNOVW4HTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhinav Ravi, Aditya Kallappa, Akshat Patidar, Arveti Manjunath, Chandra Khatri, Deepak Kumar, Gautam Bhargava, Himanshu Gupta, Kumar Ashish, Palash Kamble, Raghav Awasthi, Shubham Agarwal, Vinayak Dhruv","submitted_at":"2025-02-10T09:32:08Z","abstract_excerpt":"India is a diverse society with unique challenges in developing AI systems, including linguistic diversity, oral traditions, data accessibility, and scalability. Existing foundation models are primarily trained on English, limiting their effectiveness for India's population. Indic languages comprise only 1 percent of Common Crawl corpora despite India representing 18 percent of the global population, leading to linguistic biases. Thousands of regional languages, dialects, and code mixing create additional representation challenges due to sparse training data.\n  We introduce Krutrim LLM, a 2 tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09642","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/2502.09642/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":"2026-07-05T10:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wS/I4/IGiSFF2O8ONdXzGC+ZnRP7ZhTTAEHYfIus6+x/FzYOGCjWtLpzmIrY9+kRV43X4maZiUcflgkAaAp3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T06:25:46.379232Z"},"content_sha256":"bbfc1197b2d2cd5ab7ef0bc95eb465b9d20f045caaa1c656b93f253668c7ddd8","schema_version":"1.0","event_id":"sha256:bbfc1197b2d2cd5ab7ef0bc95eb465b9d20f045caaa1c656b93f253668c7ddd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM/bundle.json","state_url":"https://pith.science/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM/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":"2026-07-06T06:25:46Z","links":{"resolver":"https://pith.science/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM","bundle":"https://pith.science/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM/bundle.json","state":"https://pith.science/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBKWOW7XSUUZGXRT2GNOVW4HTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VBKWOW7XSUUZGXRT2GNOVW4HTM","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":"c8abeec11ef1c8c6cbe44ce0f86d5b28cb83531db719e438545ded4b70c4792a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T09:32:08Z","title_canon_sha256":"8c115bdf269f4125179e36b9dbd70d5472c88d27689cbecd00782436108d3826"},"schema_version":"1.0","source":{"id":"2502.09642","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09642","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09642v2","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09642","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"VBKWOW7XSUUZ","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"VBKWOW7XSUUZGXRT","created_at":"2026-07-05T10:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"VBKWOW7X","created_at":"2026-07-05T10:18:49Z"}],"graph_snapshots":[{"event_id":"sha256:bbfc1197b2d2cd5ab7ef0bc95eb465b9d20f045caaa1c656b93f253668c7ddd8","target":"graph","created_at":"2026-07-05T10:18:49Z","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/2502.09642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"India is a diverse society with unique challenges in developing AI systems, including linguistic diversity, oral traditions, data accessibility, and scalability. Existing foundation models are primarily trained on English, limiting their effectiveness for India's population. Indic languages comprise only 1 percent of Common Crawl corpora despite India representing 18 percent of the global population, leading to linguistic biases. Thousands of regional languages, dialects, and code mixing create additional representation challenges due to sparse training data.\n  We introduce Krutrim LLM, a 2 tr","authors_text":"Abhinav Ravi, Aditya Kallappa, Akshat Patidar, Arveti Manjunath, Chandra Khatri, Deepak Kumar, Gautam Bhargava, Himanshu Gupta, Kumar Ashish, Palash Kamble, Raghav Awasthi, Shubham Agarwal, Vinayak Dhruv","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T09:32:08Z","title":"Krutrim LLM: Multilingual Foundational Model for over a Billion People"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09642","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":"sha256:0c9496da678909c6db395d9a6c02459874a2dea725581786b86dd162c5b904b1","target":"record","created_at":"2026-07-05T10:18:49Z","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":"c8abeec11ef1c8c6cbe44ce0f86d5b28cb83531db719e438545ded4b70c4792a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T09:32:08Z","title_canon_sha256":"8c115bdf269f4125179e36b9dbd70d5472c88d27689cbecd00782436108d3826"},"schema_version":"1.0","source":{"id":"2502.09642","kind":"arxiv","version":2}},"canonical_sha256":"a855675bf79529935e33d19aeadb879b267224ac1855343822d750763ed9f873","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a855675bf79529935e33d19aeadb879b267224ac1855343822d750763ed9f873","first_computed_at":"2026-07-05T10:18:49.894127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:49.894127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5eUGOkqo4Mni+Og7ZvO9cC+e7luoD97qHVLEUMDNTOHoa2unkcj8HbzWQrVqRX5rgboNEP9dQ9GOpHAnw6sZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:49.894565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09642","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c9496da678909c6db395d9a6c02459874a2dea725581786b86dd162c5b904b1","sha256:bbfc1197b2d2cd5ab7ef0bc95eb465b9d20f045caaa1c656b93f253668c7ddd8"],"state_sha256":"80511f2ac0c9c992c8e4298a460075e6a10c0f572fa11aa7cd047c378a97ec5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+faLXdd+E1Bg6coZs2NwkLgodNrIwNSZQWEk3PsojipMWIlMiWvLIAI43mJnAnS6TVK4lqMv1Uk6tyLaPBhDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T06:25:46.381218Z","bundle_sha256":"3e4c0987d6c76bfe32c952ac56a83b2899676c84f06cfcd2d54fe54be44ac6a0"}}