{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S2SGQZ2BZG6B4MYXYCQ37LNKNX","short_pith_number":"pith:S2SGQZ2B","canonical_record":{"source":{"id":"2309.12053","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T13:20:13Z","cross_cats_sorted":[],"title_canon_sha256":"0ca4b80dc9778df5893889ff3fd94fe40955d8dbb0ed832c3583c977b5a36a4c","abstract_canon_sha256":"67c12e0a8ea6259fd687f3dec57216f5af4bb934df3d0cd8c40e54ac694fbec9"},"schema_version":"1.0"},"canonical_sha256":"96a4686741c9bc1e3317c0a1bfadaa6dfb202ae9e6b397d5d46e502268c01779","source":{"kind":"arxiv","id":"2309.12053","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12053","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12053v5","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12053","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"S2SGQZ2BZG6B","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"S2SGQZ2BZG6B4MYX","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"S2SGQZ2B","created_at":"2026-07-05T08:03:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S2SGQZ2BZG6B4MYXYCQ37LNKNX","target":"record","payload":{"canonical_record":{"source":{"id":"2309.12053","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T13:20:13Z","cross_cats_sorted":[],"title_canon_sha256":"0ca4b80dc9778df5893889ff3fd94fe40955d8dbb0ed832c3583c977b5a36a4c","abstract_canon_sha256":"67c12e0a8ea6259fd687f3dec57216f5af4bb934df3d0cd8c40e54ac694fbec9"},"schema_version":"1.0"},"canonical_sha256":"96a4686741c9bc1e3317c0a1bfadaa6dfb202ae9e6b397d5d46e502268c01779","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:07.133126Z","signature_b64":"ZfUGQ+ns2o1b2h9xR8KIZDMl/Iykp0TiLgc4SfVCZfchfSbJSdCYmmSqxk7FHJS5oxXEqJo1ap3AJmerQC7oBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96a4686741c9bc1e3317c0a1bfadaa6dfb202ae9e6b397d5d46e502268c01779","last_reissued_at":"2026-07-05T08:03:07.132626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:07.132626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.12053","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bs9QpluC5AQRit1T6euHFD21G7n+k25qRdOsR+j2JMF3W7Y3MnDKk4HUlaL804iRHM0+TrzqMGo9qEPWvIQSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:59:38.182833Z"},"content_sha256":"f17674dcce348fe509813bf66ae2e978dd03a0ad56fe9f06d2b738938ee226f2","schema_version":"1.0","event_id":"sha256:f17674dcce348fe509813bf66ae2e978dd03a0ad56fe9f06d2b738938ee226f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S2SGQZ2BZG6B4MYXYCQ37LNKNX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AceGPT, Localizing Large Language Models in Arabic","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdulmohsen Alharthi, Bang An, Benyou Wang, Dingjie Song, Fei Yu, Haizhou Li, Hao Cheng, Huang Huang, Jianqing Zhu, Jianquan Li, Jinchao Xu, Juncai He, Junying Chen, Lian Zhang, Ruoyu Sun, Xiang Wan, Xuening Sun, Zhihong Chen, Zhiyi Zhang, Ziche Liu","submitted_at":"2023-09-21T13:20:13Z","abstract_excerpt":"This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when addressing cultural sensitivity and local values. To address this, the paper proposes a comprehensive solution that includes further pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic, alongside Reinforcement Learning with AI Feedback (RLAIF) employing a reward model attun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12053","kind":"arxiv","version":5},"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/2309.12053/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":"2026-07-05T08:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIdc8+bfR6pzmTb4ePajBda8keK47I2Dj2QFw0r8/MjfGRoZI8q56X5KztACgQdXx9jAj5SmzUOtKgcU3fgEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:59:38.183519Z"},"content_sha256":"7c4c643c6c3e8747c6423ca8f962c9476f825155378e6ecbbf93d734430cb16b","schema_version":"1.0","event_id":"sha256:7c4c643c6c3e8747c6423ca8f962c9476f825155378e6ecbbf93d734430cb16b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX/bundle.json","state_url":"https://pith.science/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX/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":"2026-08-10T09:59:38Z","links":{"resolver":"https://pith.science/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX","bundle":"https://pith.science/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX/bundle.json","state":"https://pith.science/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S2SGQZ2BZG6B4MYXYCQ37LNKNX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S2SGQZ2BZG6B4MYXYCQ37LNKNX","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":"67c12e0a8ea6259fd687f3dec57216f5af4bb934df3d0cd8c40e54ac694fbec9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T13:20:13Z","title_canon_sha256":"0ca4b80dc9778df5893889ff3fd94fe40955d8dbb0ed832c3583c977b5a36a4c"},"schema_version":"1.0","source":{"id":"2309.12053","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12053","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12053v5","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12053","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"S2SGQZ2BZG6B","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"S2SGQZ2BZG6B4MYX","created_at":"2026-07-05T08:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"S2SGQZ2B","created_at":"2026-07-05T08:03:07Z"}],"graph_snapshots":[{"event_id":"sha256:7c4c643c6c3e8747c6423ca8f962c9476f825155378e6ecbbf93d734430cb16b","target":"graph","created_at":"2026-07-05T08:03:07Z","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/2309.12053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper is devoted to the development of a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. Significant concerns emerge when addressing cultural sensitivity and local values. To address this, the paper proposes a comprehensive solution that includes further pre-training with Arabic texts, Supervised Fine-Tuning (SFT) utilizing native Arabic instructions, and GPT-4 responses in Arabic, alongside Reinforcement Learning with AI Feedback (RLAIF) employing a reward model attun","authors_text":"Abdulmohsen Alharthi, Bang An, Benyou Wang, Dingjie Song, Fei Yu, Haizhou Li, Hao Cheng, Huang Huang, Jianqing Zhu, Jianquan Li, Jinchao Xu, Juncai He, Junying Chen, Lian Zhang, Ruoyu Sun, Xiang Wan, Xuening Sun, Zhihong Chen, Zhiyi Zhang, Ziche Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T13:20:13Z","title":"AceGPT, Localizing Large Language Models in Arabic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12053","kind":"arxiv","version":5},"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:f17674dcce348fe509813bf66ae2e978dd03a0ad56fe9f06d2b738938ee226f2","target":"record","created_at":"2026-07-05T08:03:07Z","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":"67c12e0a8ea6259fd687f3dec57216f5af4bb934df3d0cd8c40e54ac694fbec9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T13:20:13Z","title_canon_sha256":"0ca4b80dc9778df5893889ff3fd94fe40955d8dbb0ed832c3583c977b5a36a4c"},"schema_version":"1.0","source":{"id":"2309.12053","kind":"arxiv","version":5}},"canonical_sha256":"96a4686741c9bc1e3317c0a1bfadaa6dfb202ae9e6b397d5d46e502268c01779","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96a4686741c9bc1e3317c0a1bfadaa6dfb202ae9e6b397d5d46e502268c01779","first_computed_at":"2026-07-05T08:03:07.132626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:07.132626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZfUGQ+ns2o1b2h9xR8KIZDMl/Iykp0TiLgc4SfVCZfchfSbJSdCYmmSqxk7FHJS5oxXEqJo1ap3AJmerQC7oBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:07.133126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12053","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f17674dcce348fe509813bf66ae2e978dd03a0ad56fe9f06d2b738938ee226f2","sha256:7c4c643c6c3e8747c6423ca8f962c9476f825155378e6ecbbf93d734430cb16b"],"state_sha256":"39734ce1756be31d8ca89ba0f6f67507801d8086fec0d5d602e146f40066cc12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ii9Q85nWc/9MZ1aJPSash6YKTvHQQGTWaN5lNeBI+9W344swII1nqkoq+D6rwWrha3uNvb4Wym0qDQnsrKz2BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:59:38.189667Z","bundle_sha256":"f0ef12f4d78d0a54d8b781f3de183d7345701718f37f268378e9515cc2877753"}}