{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VQCA5572YI3T26C27PEUTHQJUT","short_pith_number":"pith:VQCA5572","canonical_record":{"source":{"id":"2504.09753","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T23:10:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb5657e99adb29d2cb7e42f6093b9da100e4c090d7c18c298cd2e699234a670f","abstract_canon_sha256":"b92b543d364c724a6715bfce8e0e7b6399752e68cebd1aafc552d5335a297122"},"schema_version":"1.0"},"canonical_sha256":"ac040ef7fac2373d785afbc9499e09a4c0a8d42a3c275f19c40a4df561e00228","source":{"kind":"arxiv","id":"2504.09753","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09753","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09753v3","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09753","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"VQCA5572YI3T","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"VQCA5572YI3T26C2","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"VQCA5572","created_at":"2026-07-05T11:45:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VQCA5572YI3T26C27PEUTHQJUT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09753","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T23:10:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb5657e99adb29d2cb7e42f6093b9da100e4c090d7c18c298cd2e699234a670f","abstract_canon_sha256":"b92b543d364c724a6715bfce8e0e7b6399752e68cebd1aafc552d5335a297122"},"schema_version":"1.0"},"canonical_sha256":"ac040ef7fac2373d785afbc9499e09a4c0a8d42a3c275f19c40a4df561e00228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:57.281736Z","signature_b64":"yaFPSSEMEyLOvfQFd3mRj0pHaM8eeye7VpK4dKuwsJ4K/fYLnJDAOx1RbU/fMWlqTr6e3uot4TrBv51EsMYMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac040ef7fac2373d785afbc9499e09a4c0a8d42a3c275f19c40a4df561e00228","last_reissued_at":"2026-07-05T11:45:57.281203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:57.281203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09753","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":"2026-07-05T11:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SH1PmBCMuijJSklUFToK4JzP5IIFB92pvriPywG6CMiIlIUCxT9/dW9G6TFoe5/d4VdSkjt+82uu3YcITnnzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:40:31.266248Z"},"content_sha256":"a196c5e7087cf3eb81c36597de41c10d5c73de3986dd84d5c301887c4c803d0f","schema_version":"1.0","event_id":"sha256:a196c5e7087cf3eb81c36597de41c10d5c73de3986dd84d5c301887c4c803d0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VQCA5572YI3T26C27PEUTHQJUT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Drishti Sharma, Hamza Farooq, Jebish Purbey, Kanwal Mehreen, Muhammad Arham, Ram Mohan Rao Kadiyala, Siddartha Pullakhandam, Siddhant Gupta, Suman Debnath","submitted_at":"2025-04-13T23:10:13Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities, but their development has primarily focused on English and other high-resource languages, leaving many languages underserved. We present our latest Hindi-English bi-lingual LLM \\textbf{Mantra-14B} with ~3\\% average improvement in benchmark scores over both languages, outperforming models twice its size. Using a curated dataset composed of English and Hindi instruction data of 485K samples, we instruction tuned models such as Qwen-2.5-14B-Instruct and Phi-4 to improve performance over both English and Hindi. Our experiments encomp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09753","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/2504.09753/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":"2026-07-05T11:45:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmX9AdVDc0Rid6SPOuxPz18Fm/4hgJDfkRXYnelgRnJXjvSB38FEzO5JioZcjNdm8OHT+7lnCYVm88fwgJX1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:40:31.266872Z"},"content_sha256":"cdec88a4b3ab7f5feec86b7f0092b540fbfb31a5178b4610e3bc1399c8e2856c","schema_version":"1.0","event_id":"sha256:cdec88a4b3ab7f5feec86b7f0092b540fbfb31a5178b4610e3bc1399c8e2856c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQCA5572YI3T26C27PEUTHQJUT/bundle.json","state_url":"https://pith.science/pith/VQCA5572YI3T26C27PEUTHQJUT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQCA5572YI3T26C27PEUTHQJUT/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":"2026-07-07T04:40:31Z","links":{"resolver":"https://pith.science/pith/VQCA5572YI3T26C27PEUTHQJUT","bundle":"https://pith.science/pith/VQCA5572YI3T26C27PEUTHQJUT/bundle.json","state":"https://pith.science/pith/VQCA5572YI3T26C27PEUTHQJUT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQCA5572YI3T26C27PEUTHQJUT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VQCA5572YI3T26C27PEUTHQJUT","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":"b92b543d364c724a6715bfce8e0e7b6399752e68cebd1aafc552d5335a297122","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T23:10:13Z","title_canon_sha256":"bb5657e99adb29d2cb7e42f6093b9da100e4c090d7c18c298cd2e699234a670f"},"schema_version":"1.0","source":{"id":"2504.09753","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09753","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09753v3","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09753","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_12","alias_value":"VQCA5572YI3T","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_16","alias_value":"VQCA5572YI3T26C2","created_at":"2026-07-05T11:45:57Z"},{"alias_kind":"pith_short_8","alias_value":"VQCA5572","created_at":"2026-07-05T11:45:57Z"}],"graph_snapshots":[{"event_id":"sha256:cdec88a4b3ab7f5feec86b7f0092b540fbfb31a5178b4610e3bc1399c8e2856c","target":"graph","created_at":"2026-07-05T11:45:57Z","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/2504.09753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities, but their development has primarily focused on English and other high-resource languages, leaving many languages underserved. We present our latest Hindi-English bi-lingual LLM \\textbf{Mantra-14B} with ~3\\% average improvement in benchmark scores over both languages, outperforming models twice its size. Using a curated dataset composed of English and Hindi instruction data of 485K samples, we instruction tuned models such as Qwen-2.5-14B-Instruct and Phi-4 to improve performance over both English and Hindi. Our experiments encomp","authors_text":"Drishti Sharma, Hamza Farooq, Jebish Purbey, Kanwal Mehreen, Muhammad Arham, Ram Mohan Rao Kadiyala, Siddartha Pullakhandam, Siddhant Gupta, Suman Debnath","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T23:10:13Z","title":"Improving Multilingual Capabilities with Cultural and Local Knowledge in Large Language Models While Enhancing Native Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09753","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:a196c5e7087cf3eb81c36597de41c10d5c73de3986dd84d5c301887c4c803d0f","target":"record","created_at":"2026-07-05T11:45:57Z","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":"b92b543d364c724a6715bfce8e0e7b6399752e68cebd1aafc552d5335a297122","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T23:10:13Z","title_canon_sha256":"bb5657e99adb29d2cb7e42f6093b9da100e4c090d7c18c298cd2e699234a670f"},"schema_version":"1.0","source":{"id":"2504.09753","kind":"arxiv","version":3}},"canonical_sha256":"ac040ef7fac2373d785afbc9499e09a4c0a8d42a3c275f19c40a4df561e00228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac040ef7fac2373d785afbc9499e09a4c0a8d42a3c275f19c40a4df561e00228","first_computed_at":"2026-07-05T11:45:57.281203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:57.281203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yaFPSSEMEyLOvfQFd3mRj0pHaM8eeye7VpK4dKuwsJ4K/fYLnJDAOx1RbU/fMWlqTr6e3uot4TrBv51EsMYMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:57.281736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09753","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a196c5e7087cf3eb81c36597de41c10d5c73de3986dd84d5c301887c4c803d0f","sha256:cdec88a4b3ab7f5feec86b7f0092b540fbfb31a5178b4610e3bc1399c8e2856c"],"state_sha256":"a5665c8d29110526661ae6c5efc9a7b3efc9d1a4c4eac101e50d6ce88521e748"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dkX12supxZxmTrbPe0VJwNkmzsed14bmzWRwTPGxbwSuIixhztKeGCxv0Z/Tuv0PMW9ulg0fv0pD/i2wd0ByCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:40:31.271234Z","bundle_sha256":"737730de693cf4f050bdade438a580e67c496d446b8b6f2c8963ddcd9e44da34"}}