{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DHNB4WR3Y6ZTQZLWVJJB5PGAHJ","short_pith_number":"pith:DHNB4WR3","canonical_record":{"source":{"id":"2402.15313","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T13:32:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fa0a352ad4b2caada4a1ddacdec974147b5c6a4f5e6dadc2b4c484d25d5a226e","abstract_canon_sha256":"b11ea2f819e29f3fddc7aa221f3da3e0ecb7e7a23dbd3424c2bfc59e4c23145a"},"schema_version":"1.0"},"canonical_sha256":"19da1e5a3bc7b3386576aa521ebcc03a56d25897523dd5f548ac2b8f845fc206","source":{"kind":"arxiv","id":"2402.15313","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15313","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15313v2","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15313","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"DHNB4WR3Y6ZT","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"DHNB4WR3Y6ZTQZLW","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"DHNB4WR3","created_at":"2026-07-05T07:49:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DHNB4WR3Y6ZTQZLWVJJB5PGAHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15313","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T13:32:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fa0a352ad4b2caada4a1ddacdec974147b5c6a4f5e6dadc2b4c484d25d5a226e","abstract_canon_sha256":"b11ea2f819e29f3fddc7aa221f3da3e0ecb7e7a23dbd3424c2bfc59e4c23145a"},"schema_version":"1.0"},"canonical_sha256":"19da1e5a3bc7b3386576aa521ebcc03a56d25897523dd5f548ac2b8f845fc206","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:18.770200Z","signature_b64":"m0zA05wyvLl6HeKpbqAoBFU3MHqRfkQxUjhsCbzg0RmWd3Bn3H/JIkXP3/q3lZSWvN8X04L+p/Xg5ArF+C3NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19da1e5a3bc7b3386576aa521ebcc03a56d25897523dd5f548ac2b8f845fc206","last_reissued_at":"2026-07-05T07:49:18.769682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:18.769682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15313","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":"2026-07-05T07:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"322LaWpmvrHXOUagD7LoONsNXYuRQ7pnJa/kk7/YzU1TOWoCGAVMn0dql36WwhtHIroeIGQfWKW4WlmT+viADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:48:23.791053Z"},"content_sha256":"0e2e86193a20201cd18c9ae41075d49ad5094b08ff1a9d594368145567b65a75","schema_version":"1.0","event_id":"sha256:0e2e86193a20201cd18c9ae41075d49ad5094b08ff1a9d594368145567b65a75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DHNB4WR3Y6ZTQZLWVJJB5PGAHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ArabianGPT: Native Arabic GPT-based Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adel Ammar, Anis Koubaa, Lahouari Ghouti, Omar Najar, Serry Sibaee","submitted_at":"2024-02-23T13:32:47Z","abstract_excerpt":"The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes ArabianGPT, a series of transformer-based models within the ArabianLLM suite designed explicitly for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15313","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/2402.15313/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":"2026-07-05T07:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odlFRaLD4mt63MNi7QddMzLHNzelIcgmPFirL+lMU9YOQamhuHm1r85+R9Hh6+XPHvTu+XrHF5YeuKyG1x19Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:48:23.791935Z"},"content_sha256":"a54bd97fa420a59eac567bf8ecfcae3e937a949589901fe2d171380f4a670e24","schema_version":"1.0","event_id":"sha256:a54bd97fa420a59eac567bf8ecfcae3e937a949589901fe2d171380f4a670e24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ/bundle.json","state_url":"https://pith.science/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ/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":"2026-08-22T00:48:23Z","links":{"resolver":"https://pith.science/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ","bundle":"https://pith.science/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ/bundle.json","state":"https://pith.science/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHNB4WR3Y6ZTQZLWVJJB5PGAHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DHNB4WR3Y6ZTQZLWVJJB5PGAHJ","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":"b11ea2f819e29f3fddc7aa221f3da3e0ecb7e7a23dbd3424c2bfc59e4c23145a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T13:32:47Z","title_canon_sha256":"fa0a352ad4b2caada4a1ddacdec974147b5c6a4f5e6dadc2b4c484d25d5a226e"},"schema_version":"1.0","source":{"id":"2402.15313","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15313","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15313v2","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15313","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"DHNB4WR3Y6ZT","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"DHNB4WR3Y6ZTQZLW","created_at":"2026-07-05T07:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"DHNB4WR3","created_at":"2026-07-05T07:49:18Z"}],"graph_snapshots":[{"event_id":"sha256:a54bd97fa420a59eac567bf8ecfcae3e937a949589901fe2d171380f4a670e24","target":"graph","created_at":"2026-07-05T07:49:18Z","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/2402.15313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The predominance of English and Latin-based large language models (LLMs) has led to a notable deficit in native Arabic LLMs. This discrepancy is accentuated by the prevalent inclusion of English tokens in existing Arabic models, detracting from their efficacy in processing native Arabic's intricate morphology and syntax. Consequently, there is a theoretical and practical imperative for developing LLMs predominantly focused on Arabic linguistic elements. To address this gap, this paper proposes ArabianGPT, a series of transformer-based models within the ArabianLLM suite designed explicitly for ","authors_text":"Adel Ammar, Anis Koubaa, Lahouari Ghouti, Omar Najar, Serry Sibaee","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T13:32:47Z","title":"ArabianGPT: Native Arabic GPT-based Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15313","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":"sha256:0e2e86193a20201cd18c9ae41075d49ad5094b08ff1a9d594368145567b65a75","target":"record","created_at":"2026-07-05T07:49:18Z","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":"b11ea2f819e29f3fddc7aa221f3da3e0ecb7e7a23dbd3424c2bfc59e4c23145a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T13:32:47Z","title_canon_sha256":"fa0a352ad4b2caada4a1ddacdec974147b5c6a4f5e6dadc2b4c484d25d5a226e"},"schema_version":"1.0","source":{"id":"2402.15313","kind":"arxiv","version":2}},"canonical_sha256":"19da1e5a3bc7b3386576aa521ebcc03a56d25897523dd5f548ac2b8f845fc206","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19da1e5a3bc7b3386576aa521ebcc03a56d25897523dd5f548ac2b8f845fc206","first_computed_at":"2026-07-05T07:49:18.769682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:18.769682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m0zA05wyvLl6HeKpbqAoBFU3MHqRfkQxUjhsCbzg0RmWd3Bn3H/JIkXP3/q3lZSWvN8X04L+p/Xg5ArF+C3NCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:18.770200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15313","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e2e86193a20201cd18c9ae41075d49ad5094b08ff1a9d594368145567b65a75","sha256:a54bd97fa420a59eac567bf8ecfcae3e937a949589901fe2d171380f4a670e24"],"state_sha256":"903e4d1c9a0aa5fb81409f5260e73bf367cf971ae89d648de08bb1364c6054f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"idp2GCXPXsG+Bk97wxYGdDjRqa2XC/TPbfFKs5V5BwS6LqozCQWWYiO/Gq1GcrBzOluXPLVDG5AjJ/+gOWheBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:48:23.799514Z","bundle_sha256":"432a54349090114cddc81ab87dd314f4dde3724998aca5aac1b285b154f0b157"}}