{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RB3XXN2SDFJU7Z6JG62KPWLNTO","short_pith_number":"pith:RB3XXN2S","canonical_record":{"source":{"id":"2501.09825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T20:24:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d795f8c7cfcc38259e6be85a1a574d9103f1bf72e9f998931186dfadf5c92876","abstract_canon_sha256":"6658b16f39c90d91ac726a4f1ec69bc98fa544e853085e2edb7fdd59fa80e0a6"},"schema_version":"1.0"},"canonical_sha256":"88777bb75219534fe7c937b4a7d96d9ba07a2447e7cd8ec13f527428af562b36","source":{"kind":"arxiv","id":"2501.09825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09825","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09825v1","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09825","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"RB3XXN2SDFJU","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"RB3XXN2SDFJU7Z6J","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"RB3XXN2S","created_at":"2026-07-05T10:02:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RB3XXN2SDFJU7Z6JG62KPWLNTO","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T20:24:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d795f8c7cfcc38259e6be85a1a574d9103f1bf72e9f998931186dfadf5c92876","abstract_canon_sha256":"6658b16f39c90d91ac726a4f1ec69bc98fa544e853085e2edb7fdd59fa80e0a6"},"schema_version":"1.0"},"canonical_sha256":"88777bb75219534fe7c937b4a7d96d9ba07a2447e7cd8ec13f527428af562b36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:11.987215Z","signature_b64":"gKGjExPEiE7AZ8fKPcA+wadulDK+WGpmS8bg73Y3GVq7o928hIxZCx7hIKGXEX8jQvmuTVV9cKgNZh/Ub/nvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88777bb75219534fe7c937b4a7d96d9ba07a2447e7cd8ec13f527428af562b36","last_reissued_at":"2026-07-05T10:02:11.986839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:11.986839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09825","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibm24iHBVOjHqJiGaqiPX5jFSB+8lZJE+lI/KbR08Z4v5jWJ+B8nSFtJ2sL+k3eOWQjC6sOwhJvgCB38GiMmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:17:29.574966Z"},"content_sha256":"4f53ff706541d9228e62ead4db289ec022ebcf9b209fdc8dca9b61b1555e5d1f","schema_version":"1.0","event_id":"sha256:4f53ff706541d9228e62ead4db289ec022ebcf9b209fdc8dca9b61b1555e5d1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RB3XXN2SDFJU7Z6JG62KPWLNTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging Language Barriers in Healthcare: A Study on Arabic LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Nada Saadi, Praveen K Kanithi, Ronnie Rajan, Tathagata Raha","submitted_at":"2025-01-16T20:24:56Z","abstract_excerpt":"This paper investigates the challenges of developing large language models (LLMs) proficient in both multilingual understanding and medical knowledge. We demonstrate that simply translating medical data does not guarantee strong performance on clinical tasks in the target language. Our experiments reveal that the optimal language mix in training data varies significantly across different medical tasks. We find that larger models with carefully calibrated language ratios achieve superior performance on native-language clinical tasks. Furthermore, our results suggest that relying solely on fine-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09825","kind":"arxiv","version":1},"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/2501.09825/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":"2026-07-05T10:02:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngGIDFKgWEBxpirMN02ea2oYNNBmyVfmQ68foEAgaeVzQpaHJ/n2bRfz315lrDrTx7vQ9xKxifN52xFbULYACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:17:29.575375Z"},"content_sha256":"c3440f8b687f551bf13b46aa6d858e877bdb23a3a47b223ba56510c257137473","schema_version":"1.0","event_id":"sha256:c3440f8b687f551bf13b46aa6d858e877bdb23a3a47b223ba56510c257137473"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO/bundle.json","state_url":"https://pith.science/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO/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":"2026-07-07T12:17:29Z","links":{"resolver":"https://pith.science/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO","bundle":"https://pith.science/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO/bundle.json","state":"https://pith.science/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RB3XXN2SDFJU7Z6JG62KPWLNTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RB3XXN2SDFJU7Z6JG62KPWLNTO","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":"6658b16f39c90d91ac726a4f1ec69bc98fa544e853085e2edb7fdd59fa80e0a6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T20:24:56Z","title_canon_sha256":"d795f8c7cfcc38259e6be85a1a574d9103f1bf72e9f998931186dfadf5c92876"},"schema_version":"1.0","source":{"id":"2501.09825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09825","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09825v1","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09825","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"RB3XXN2SDFJU","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"RB3XXN2SDFJU7Z6J","created_at":"2026-07-05T10:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"RB3XXN2S","created_at":"2026-07-05T10:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:c3440f8b687f551bf13b46aa6d858e877bdb23a3a47b223ba56510c257137473","target":"graph","created_at":"2026-07-05T10:02:11Z","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/2501.09825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the challenges of developing large language models (LLMs) proficient in both multilingual understanding and medical knowledge. We demonstrate that simply translating medical data does not guarantee strong performance on clinical tasks in the target language. Our experiments reveal that the optimal language mix in training data varies significantly across different medical tasks. We find that larger models with carefully calibrated language ratios achieve superior performance on native-language clinical tasks. Furthermore, our results suggest that relying solely on fine-","authors_text":"Cl\\'ement Christophe, Marco AF Pimentel, Nada Saadi, Praveen K Kanithi, Ronnie Rajan, Tathagata Raha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T20:24:56Z","title":"Bridging Language Barriers in Healthcare: A Study on Arabic LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09825","kind":"arxiv","version":1},"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":"sha256:4f53ff706541d9228e62ead4db289ec022ebcf9b209fdc8dca9b61b1555e5d1f","target":"record","created_at":"2026-07-05T10:02:11Z","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":"6658b16f39c90d91ac726a4f1ec69bc98fa544e853085e2edb7fdd59fa80e0a6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T20:24:56Z","title_canon_sha256":"d795f8c7cfcc38259e6be85a1a574d9103f1bf72e9f998931186dfadf5c92876"},"schema_version":"1.0","source":{"id":"2501.09825","kind":"arxiv","version":1}},"canonical_sha256":"88777bb75219534fe7c937b4a7d96d9ba07a2447e7cd8ec13f527428af562b36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88777bb75219534fe7c937b4a7d96d9ba07a2447e7cd8ec13f527428af562b36","first_computed_at":"2026-07-05T10:02:11.986839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:11.986839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gKGjExPEiE7AZ8fKPcA+wadulDK+WGpmS8bg73Y3GVq7o928hIxZCx7hIKGXEX8jQvmuTVV9cKgNZh/Ub/nvCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:11.987215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f53ff706541d9228e62ead4db289ec022ebcf9b209fdc8dca9b61b1555e5d1f","sha256:c3440f8b687f551bf13b46aa6d858e877bdb23a3a47b223ba56510c257137473"],"state_sha256":"996f9b78f5d6756e734f5f8a546419c1d9ccbec963b708dc0349b901a0382c21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WzKOsrCSF1elrUxEjVXlx4zwa43jBfNau5aEq0QDEaMotOBIl5UOvIARDIQ+RXu5rD7qIQqNNWyLBFB5nCvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:17:29.577537Z","bundle_sha256":"cd098fb286954fb65d9983c57cfe4d4ffb34c729025b2d33ec05422151f64213"}}