{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FAXAAYZ3YDI4HDEPDR62ASV5EJ","short_pith_number":"pith:FAXAAYZ3","canonical_record":{"source":{"id":"2410.20238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T17:48:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33aa1a4b591aea92ff7ea8401a0bdff0768a00779082d00b864e1eb4c81974ec","abstract_canon_sha256":"4fda7f672078c73d5593a55d177e4cdd8da463b8708410b0890e9e0529d183b0"},"schema_version":"1.0"},"canonical_sha256":"282e00633bc0d1c38c8f1c7da04abd225e30724f76ec6ffd2146e1b680e87c4c","source":{"kind":"arxiv","id":"2410.20238","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20238","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20238v2","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20238","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"FAXAAYZ3YDI4","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"FAXAAYZ3YDI4HDEP","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"FAXAAYZ3","created_at":"2026-05-20T02:05:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FAXAAYZ3YDI4HDEPDR62ASV5EJ","target":"record","payload":{"canonical_record":{"source":{"id":"2410.20238","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T17:48:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"33aa1a4b591aea92ff7ea8401a0bdff0768a00779082d00b864e1eb4c81974ec","abstract_canon_sha256":"4fda7f672078c73d5593a55d177e4cdd8da463b8708410b0890e9e0529d183b0"},"schema_version":"1.0"},"canonical_sha256":"282e00633bc0d1c38c8f1c7da04abd225e30724f76ec6ffd2146e1b680e87c4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:32.335901Z","signature_b64":"0jdyd3xNfmE7z4NIzzsYySSGW26jgi74Lzoj7iXkcQt5PKFrW7aeGDsbEjdU4/KZ+Dx7GRX4pkd45OoIBzO0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282e00633bc0d1c38c8f1c7da04abd225e30724f76ec6ffd2146e1b680e87c4c","last_reissued_at":"2026-05-20T02:05:32.335115Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:32.335115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.20238","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":"2026-05-20T02:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVffq2BQ9QgBbaxXHVjGJv4/Jg7ZBL3y9ZpY8a01rgkrqAW66ilHZY3JRfJKo+mw6+V3DRFJX9VxyxDvcra5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:07:26.176449Z"},"content_sha256":"3533e0904fcb2879bf361077479f05837a86a860c397bc78b787e045b32d8c08","schema_version":"1.0","event_id":"sha256:3533e0904fcb2879bf361077479f05837a86a860c397bc78b787e045b32d8c08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FAXAAYZ3YDI4HDEPDR62ASV5EJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Large Language Models for Arabic Language and its Dialects","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hend Al-Khalifa, Malak Mashaabi, Shahad Al-Khalifa","submitted_at":"2024-10-26T17:48:20Z","abstract_excerpt":"This survey offers a comprehensive overview of Large Language Models (LLMs) designed for Arabic language and its dialects. It covers key architectures, including encoder-only, decoder-only, and encoder-decoder models, along with the datasets used for pre-training, spanning Classical Arabic, Modern Standard Arabic, and Dialectal Arabic. The study also explores monolingual, bilingual, and multilingual LLMs, analyzing their architectures and performance across downstream tasks, such as sentiment analysis, named entity recognition, and question answering. Furthermore, it assesses the openness of A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20238","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/2410.20238/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":"2026-05-20T02:05:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGGhz9afYlO9rqqArY4mAP3VnJLztD7yCYp4FmY/li8qx3MtkSbw2INTWUUiatllDRyhglVEXOEAP5D9x76RBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:07:26.177166Z"},"content_sha256":"b035327b7126aa5fe13d210bdf99f7504eaef006e25cfc2955e741d36e4fef9d","schema_version":"1.0","event_id":"sha256:b035327b7126aa5fe13d210bdf99f7504eaef006e25cfc2955e741d36e4fef9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ/bundle.json","state_url":"https://pith.science/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ/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":"2026-05-27T05:07:26Z","links":{"resolver":"https://pith.science/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ","bundle":"https://pith.science/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ/bundle.json","state":"https://pith.science/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAXAAYZ3YDI4HDEPDR62ASV5EJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FAXAAYZ3YDI4HDEPDR62ASV5EJ","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":"4fda7f672078c73d5593a55d177e4cdd8da463b8708410b0890e9e0529d183b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T17:48:20Z","title_canon_sha256":"33aa1a4b591aea92ff7ea8401a0bdff0768a00779082d00b864e1eb4c81974ec"},"schema_version":"1.0","source":{"id":"2410.20238","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20238","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20238v2","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20238","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"pith_short_12","alias_value":"FAXAAYZ3YDI4","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"pith_short_16","alias_value":"FAXAAYZ3YDI4HDEP","created_at":"2026-05-20T02:05:32Z"},{"alias_kind":"pith_short_8","alias_value":"FAXAAYZ3","created_at":"2026-05-20T02:05:32Z"}],"graph_snapshots":[{"event_id":"sha256:b035327b7126aa5fe13d210bdf99f7504eaef006e25cfc2955e741d36e4fef9d","target":"graph","created_at":"2026-05-20T02:05:32Z","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/2410.20238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This survey offers a comprehensive overview of Large Language Models (LLMs) designed for Arabic language and its dialects. It covers key architectures, including encoder-only, decoder-only, and encoder-decoder models, along with the datasets used for pre-training, spanning Classical Arabic, Modern Standard Arabic, and Dialectal Arabic. The study also explores monolingual, bilingual, and multilingual LLMs, analyzing their architectures and performance across downstream tasks, such as sentiment analysis, named entity recognition, and question answering. Furthermore, it assesses the openness of A","authors_text":"Hend Al-Khalifa, Malak Mashaabi, Shahad Al-Khalifa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T17:48:20Z","title":"A Survey of Large Language Models for Arabic Language and its Dialects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20238","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":"sha256:3533e0904fcb2879bf361077479f05837a86a860c397bc78b787e045b32d8c08","target":"record","created_at":"2026-05-20T02:05:32Z","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":"4fda7f672078c73d5593a55d177e4cdd8da463b8708410b0890e9e0529d183b0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-26T17:48:20Z","title_canon_sha256":"33aa1a4b591aea92ff7ea8401a0bdff0768a00779082d00b864e1eb4c81974ec"},"schema_version":"1.0","source":{"id":"2410.20238","kind":"arxiv","version":2}},"canonical_sha256":"282e00633bc0d1c38c8f1c7da04abd225e30724f76ec6ffd2146e1b680e87c4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"282e00633bc0d1c38c8f1c7da04abd225e30724f76ec6ffd2146e1b680e87c4c","first_computed_at":"2026-05-20T02:05:32.335115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:32.335115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0jdyd3xNfmE7z4NIzzsYySSGW26jgi74Lzoj7iXkcQt5PKFrW7aeGDsbEjdU4/KZ+Dx7GRX4pkd45OoIBzO0Dw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:32.335901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20238","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3533e0904fcb2879bf361077479f05837a86a860c397bc78b787e045b32d8c08","sha256:b035327b7126aa5fe13d210bdf99f7504eaef006e25cfc2955e741d36e4fef9d"],"state_sha256":"bfbb83c51cd70b88b009a3e1346e8f0ff73856153a58a9669718988d64b058e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKqm05TymGYTs2yI5Hm1KKNBJwYzJTvaPzsKrGXYrkeYzIfup/uPM2A0kTzjyJUul4uychgBE8bGFn8APADBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:07:26.180440Z","bundle_sha256":"04579da672f5621cf1be97119a074c621c003a91f69d62ad43a4a33b1dde83c0"}}