{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MKJKNQ6C4ZM4B3O7C46ZBMRB54","short_pith_number":"pith:MKJKNQ6C","canonical_record":{"source":{"id":"2504.15120","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T14:17:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1833bc56493fac931065203a918d446fe92c8b9b9820c00534bb0370552bcaf8","abstract_canon_sha256":"50d2afc7e22fbc6f524853f5c93e011db62da6921894835138d1f68d91b1d78f"},"schema_version":"1.0"},"canonical_sha256":"6292a6c3c2e659c0eddf173d90b221ef386065a08afdab6441e29708cfe40cd9","source":{"kind":"arxiv","id":"2504.15120","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15120","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15120v2","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15120","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_12","alias_value":"MKJKNQ6C4ZM4","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_16","alias_value":"MKJKNQ6C4ZM4B3O7","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_8","alias_value":"MKJKNQ6C","created_at":"2026-07-05T11:56:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MKJKNQ6C4ZM4B3O7C46ZBMRB54","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15120","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T14:17:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1833bc56493fac931065203a918d446fe92c8b9b9820c00534bb0370552bcaf8","abstract_canon_sha256":"50d2afc7e22fbc6f524853f5c93e011db62da6921894835138d1f68d91b1d78f"},"schema_version":"1.0"},"canonical_sha256":"6292a6c3c2e659c0eddf173d90b221ef386065a08afdab6441e29708cfe40cd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:56.219278Z","signature_b64":"xGSvf9880d33djPbAhWeI3vjvbW4tpnWah1Et5PsovzTqbI3OXVZ+G3XrtVDN8PNvlTmclmSwJnoQBRD0Lk1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6292a6c3c2e659c0eddf173d90b221ef386065a08afdab6441e29708cfe40cd9","last_reissued_at":"2026-07-05T11:56:56.218795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:56.218795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15120","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":"2026-07-05T11:56:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3zVyEC5OrM8IG2rq+B1Emf+9c1/0tJkmkx0T3LSmSv2GfOUu4QCDW044ptVUoTORfpsjrBUSksp/c5J/2b4IAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:49:16.673834Z"},"content_sha256":"9241902948f583671f0489916c1e1f82970dd4816b8837c2a1dff7462dcd7d27","schema_version":"1.0","event_id":"sha256:9241902948f583671f0489916c1e1f82970dd4816b8837c2a1dff7462dcd7d27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MKJKNQ6C4ZM4B3O7C46ZBMRB54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Kuwain 1.5B: An Arabic SLM via Language Injection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Omar Hadid, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","submitted_at":"2025-04-21T14:17:25Z","abstract_excerpt":"Enhancing existing models with new knowledge is a crucial aspect of AI development. This paper introduces a novel method for integrating a new language into a large language model (LLM). Our approach successfully incorporates a previously unseen target language into an existing LLM without compromising its prior knowledge. We trained a tiny model with 1.5 billion parameters named Kuwain by injecting the Arabic language into a small open-source model mainly trained in English. Our method demonstrates significant improvements in Arabic language performance, with an average 8% improvement across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15120","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/2504.15120/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":"2026-07-05T11:56:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RY3wm7+OJL91LEbnPhxCRvxaaT1jyEZTirUc7MvY6tGUp2i3qrtwpBB9inZ7waCNAv4FtI1R3cAgvrh/O4w8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:49:16.674374Z"},"content_sha256":"8254b1ae50f6f4719587e7c66a6e653c361abc885fb3b96f14b20b3c6ee059da","schema_version":"1.0","event_id":"sha256:8254b1ae50f6f4719587e7c66a6e653c361abc885fb3b96f14b20b3c6ee059da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54/bundle.json","state_url":"https://pith.science/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54/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":"2026-08-18T08:49:16Z","links":{"resolver":"https://pith.science/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54","bundle":"https://pith.science/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54/bundle.json","state":"https://pith.science/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKJKNQ6C4ZM4B3O7C46ZBMRB54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MKJKNQ6C4ZM4B3O7C46ZBMRB54","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":"50d2afc7e22fbc6f524853f5c93e011db62da6921894835138d1f68d91b1d78f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T14:17:25Z","title_canon_sha256":"1833bc56493fac931065203a918d446fe92c8b9b9820c00534bb0370552bcaf8"},"schema_version":"1.0","source":{"id":"2504.15120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15120","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15120v2","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15120","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_12","alias_value":"MKJKNQ6C4ZM4","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_16","alias_value":"MKJKNQ6C4ZM4B3O7","created_at":"2026-07-05T11:56:56Z"},{"alias_kind":"pith_short_8","alias_value":"MKJKNQ6C","created_at":"2026-07-05T11:56:56Z"}],"graph_snapshots":[{"event_id":"sha256:8254b1ae50f6f4719587e7c66a6e653c361abc885fb3b96f14b20b3c6ee059da","target":"graph","created_at":"2026-07-05T11:56:56Z","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/2504.15120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enhancing existing models with new knowledge is a crucial aspect of AI development. This paper introduces a novel method for integrating a new language into a large language model (LLM). Our approach successfully incorporates a previously unseen target language into an existing LLM without compromising its prior knowledge. We trained a tiny model with 1.5 billion parameters named Kuwain by injecting the Arabic language into a small open-source model mainly trained in English. Our method demonstrates significant improvements in Arabic language performance, with an average 8% improvement across ","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Omar Hadid, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T14:17:25Z","title":"Kuwain 1.5B: An Arabic SLM via Language Injection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15120","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":"sha256:9241902948f583671f0489916c1e1f82970dd4816b8837c2a1dff7462dcd7d27","target":"record","created_at":"2026-07-05T11:56:56Z","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":"50d2afc7e22fbc6f524853f5c93e011db62da6921894835138d1f68d91b1d78f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-21T14:17:25Z","title_canon_sha256":"1833bc56493fac931065203a918d446fe92c8b9b9820c00534bb0370552bcaf8"},"schema_version":"1.0","source":{"id":"2504.15120","kind":"arxiv","version":2}},"canonical_sha256":"6292a6c3c2e659c0eddf173d90b221ef386065a08afdab6441e29708cfe40cd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6292a6c3c2e659c0eddf173d90b221ef386065a08afdab6441e29708cfe40cd9","first_computed_at":"2026-07-05T11:56:56.218795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:56.218795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xGSvf9880d33djPbAhWeI3vjvbW4tpnWah1Et5PsovzTqbI3OXVZ+G3XrtVDN8PNvlTmclmSwJnoQBRD0Lk1Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:56.219278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9241902948f583671f0489916c1e1f82970dd4816b8837c2a1dff7462dcd7d27","sha256:8254b1ae50f6f4719587e7c66a6e653c361abc885fb3b96f14b20b3c6ee059da"],"state_sha256":"89e242284d733afa90c2ea07ea95b11706e60bb1e8356df3d917a90762d5b948"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tL+ZcOG4mHJXfo8LGnB5pAIPO/5DSL9mvqZbRejFc7FtyBHEgWFRXcJi8bt7HczXuTckDpSt+QYnqJop682jCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:49:16.681669Z","bundle_sha256":"685e334a425e65d1e86ae9f25f3dd437c2f0e55ab0b88133b8399a50c3586cfa"}}