{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JOMLXOGNO4B7XETGRFSQ4TDFRV","short_pith_number":"pith:JOMLXOGN","canonical_record":{"source":{"id":"2505.08004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T19:09:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"629c780950673e6ecd7a73e186185aa421abbbbbc67d3462e0cd12e2f28cf6d9","abstract_canon_sha256":"74f5ff1b7d29eb7302d7186d0c0dedccff5a91e506d5874c8f714ae8e09fc358"},"schema_version":"1.0"},"canonical_sha256":"4b98bbb8cd7703fb926689650e4c658d46c10e1f670697921ed1113a3156b50c","source":{"kind":"arxiv","id":"2505.08004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08004","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08004v1","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08004","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"pith_short_12","alias_value":"JOMLXOGNO4B7","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"pith_short_16","alias_value":"JOMLXOGNO4B7XETG","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"pith_short_8","alias_value":"JOMLXOGN","created_at":"2026-07-05T11:02:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JOMLXOGNO4B7XETGRFSQ4TDFRV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T19:09:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"629c780950673e6ecd7a73e186185aa421abbbbbc67d3462e0cd12e2f28cf6d9","abstract_canon_sha256":"74f5ff1b7d29eb7302d7186d0c0dedccff5a91e506d5874c8f714ae8e09fc358"},"schema_version":"1.0"},"canonical_sha256":"4b98bbb8cd7703fb926689650e4c658d46c10e1f670697921ed1113a3156b50c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:01.086897Z","signature_b64":"D/OGASQsJnjiPiWtUa9z6ue91d4NAgzPqjwVhJIWZxwLhrdLlWwGEDl17q2Elb/0Winj964aZ7aUPpaBCO9lBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b98bbb8cd7703fb926689650e4c658d46c10e1f670697921ed1113a3156b50c","last_reissued_at":"2026-07-05T11:02:01.086435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:01.086435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08004","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":"2026-07-05T11:02:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0O9uCG4ELekuoEPBTWpUjGy8Dm9AxrshTGvnVR6dEY64fUpe4N46hQjqt5wT2o43tQktvdphA+pYQKpCjNMrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:46:30.865756Z"},"content_sha256":"2b66e39b2a7a748eecaa70cca13cc1c07ed182d6c39487fd7986a6bb715f2f11","schema_version":"1.0","event_id":"sha256:2b66e39b2a7a748eecaa70cca13cc1c07ed182d6c39487fd7986a6bb715f2f11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JOMLXOGNO4B7XETGRFSQ4TDFRV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models and Arabic Content: A Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dmitri Roussinov, Haneh Rhel","submitted_at":"2025-05-12T19:09:12Z","abstract_excerpt":"Over the past three years, the rapid advancement of Large Language Models (LLMs) has had a profound impact on multiple areas of Artificial Intelligence (AI), particularly in Natural Language Processing (NLP) across diverse languages, including Arabic. Although Arabic is considered one of the most widely spoken languages across 27 countries in the Arabic world and used as a second language in some other non-Arabic countries as well, there is still a scarcity of Arabic resources, datasets, and tools. Arabic NLP tasks face various challenges due to the complexities of the Arabic language, includi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08004","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/2505.08004/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":"2026-07-05T11:02:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ItOcFyHGr/tlgSnsvAdakq+46QmmTKouh3lKwA1c2+czdHlFD1jvwquvhtV1uboX5YjXJPoInjFZDzlf+bUqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:46:30.866247Z"},"content_sha256":"cf2a42afb5831510e27434d6f0f9937cb19f9ad17be13be2323ab41546c9dac9","schema_version":"1.0","event_id":"sha256:cf2a42afb5831510e27434d6f0f9937cb19f9ad17be13be2323ab41546c9dac9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV/bundle.json","state_url":"https://pith.science/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV/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":"2026-08-07T19:46:30Z","links":{"resolver":"https://pith.science/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV","bundle":"https://pith.science/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV/bundle.json","state":"https://pith.science/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOMLXOGNO4B7XETGRFSQ4TDFRV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JOMLXOGNO4B7XETGRFSQ4TDFRV","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":"74f5ff1b7d29eb7302d7186d0c0dedccff5a91e506d5874c8f714ae8e09fc358","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T19:09:12Z","title_canon_sha256":"629c780950673e6ecd7a73e186185aa421abbbbbc67d3462e0cd12e2f28cf6d9"},"schema_version":"1.0","source":{"id":"2505.08004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08004","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08004v1","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08004","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"pith_short_12","alias_value":"JOMLXOGNO4B7","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"pith_short_16","alias_value":"JOMLXOGNO4B7XETG","created_at":"2026-07-05T11:02:01Z"},{"alias_kind":"pith_short_8","alias_value":"JOMLXOGN","created_at":"2026-07-05T11:02:01Z"}],"graph_snapshots":[{"event_id":"sha256:cf2a42afb5831510e27434d6f0f9937cb19f9ad17be13be2323ab41546c9dac9","target":"graph","created_at":"2026-07-05T11:02:01Z","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/2505.08004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Over the past three years, the rapid advancement of Large Language Models (LLMs) has had a profound impact on multiple areas of Artificial Intelligence (AI), particularly in Natural Language Processing (NLP) across diverse languages, including Arabic. Although Arabic is considered one of the most widely spoken languages across 27 countries in the Arabic world and used as a second language in some other non-Arabic countries as well, there is still a scarcity of Arabic resources, datasets, and tools. Arabic NLP tasks face various challenges due to the complexities of the Arabic language, includi","authors_text":"Dmitri Roussinov, Haneh Rhel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T19:09:12Z","title":"Large Language Models and Arabic Content: A Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08004","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":"sha256:2b66e39b2a7a748eecaa70cca13cc1c07ed182d6c39487fd7986a6bb715f2f11","target":"record","created_at":"2026-07-05T11:02:01Z","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":"74f5ff1b7d29eb7302d7186d0c0dedccff5a91e506d5874c8f714ae8e09fc358","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T19:09:12Z","title_canon_sha256":"629c780950673e6ecd7a73e186185aa421abbbbbc67d3462e0cd12e2f28cf6d9"},"schema_version":"1.0","source":{"id":"2505.08004","kind":"arxiv","version":1}},"canonical_sha256":"4b98bbb8cd7703fb926689650e4c658d46c10e1f670697921ed1113a3156b50c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b98bbb8cd7703fb926689650e4c658d46c10e1f670697921ed1113a3156b50c","first_computed_at":"2026-07-05T11:02:01.086435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:01.086435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D/OGASQsJnjiPiWtUa9z6ue91d4NAgzPqjwVhJIWZxwLhrdLlWwGEDl17q2Elb/0Winj964aZ7aUPpaBCO9lBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:01.086897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b66e39b2a7a748eecaa70cca13cc1c07ed182d6c39487fd7986a6bb715f2f11","sha256:cf2a42afb5831510e27434d6f0f9937cb19f9ad17be13be2323ab41546c9dac9"],"state_sha256":"240eb1d7248b86ccdafcc70abe6f9828adbdc628362725c326c000242f5d82c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuC8aosFfeonNAjhzl5Lp5x73c7Pi/eRrdrSUJQ+V1uyiXXwTM/j6licapf0jM2LEe7CUNhPB1mhUHQE/lWBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:46:30.870515Z","bundle_sha256":"5a93ab6ac7fa1342260786a04a0e42f4b1825a2e212728ca1809b08edbfa83a7"}}