{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YLGXNTLO3BDPGKVWUUMO5NDO4B","short_pith_number":"pith:YLGXNTLO","schema_version":"1.0","canonical_sha256":"c2cd76cd6ed846f32ab6a518eeb46ee07172e4277d2617fff1c1e425839dfb4c","source":{"kind":"arxiv","id":"2505.23276","version":2},"attestation_state":"computed","paper":{"title":"The Arabic AI Fingerprint: Stylometric Analysis and Detection of Large Language Models Text","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maged S. Al-shaibani, Moataz Ahmed","submitted_at":"2025-05-29T09:24:00Z","abstract_excerpt":"Large Language Models (LLMs) have achieved unprecedented capabilities in generating human-like text, posing subtle yet significant challenges for information integrity across critical domains, including education, social media, and academia, enabling sophisticated misinformation campaigns, compromising healthcare guidance, and facilitating targeted propaganda. This challenge becomes severe, particularly in under-explored and low-resource languages like Arabic. This paper presents a comprehensive investigation of Arabic machine-generated text, examining multiple generation strategies (generatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.23276","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T09:24:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"60a5c1e49f4f6d70a117879f3d63cfb864faf65bac7c82e029d56bdd4d751d9a","abstract_canon_sha256":"11891110ec44c8b0a5e7a93a40ef6b56d5e998795198592a790f742a90214709"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:47.287056Z","signature_b64":"wf2jHlzGQWNNamqIsx63cWnmCqx3M5/al4LfmW/PzCFa11fVOE6W5eZ2i7lobkp3mg0YU1la1M49NmpSPUwjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2cd76cd6ed846f32ab6a518eeb46ee07172e4277d2617fff1c1e425839dfb4c","last_reissued_at":"2026-07-05T11:15:47.286455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:47.286455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Arabic AI Fingerprint: Stylometric Analysis and Detection of Large Language Models Text","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Maged S. Al-shaibani, Moataz Ahmed","submitted_at":"2025-05-29T09:24:00Z","abstract_excerpt":"Large Language Models (LLMs) have achieved unprecedented capabilities in generating human-like text, posing subtle yet significant challenges for information integrity across critical domains, including education, social media, and academia, enabling sophisticated misinformation campaigns, compromising healthcare guidance, and facilitating targeted propaganda. This challenge becomes severe, particularly in under-explored and low-resource languages like Arabic. This paper presents a comprehensive investigation of Arabic machine-generated text, examining multiple generation strategies (generatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23276","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/2505.23276/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.23276","created_at":"2026-07-05T11:15:47.286524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23276v2","created_at":"2026-07-05T11:15:47.286524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23276","created_at":"2026-07-05T11:15:47.286524+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLGXNTLO3BDP","created_at":"2026-07-05T11:15:47.286524+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLGXNTLO3BDPGKVW","created_at":"2026-07-05T11:15:47.286524+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLGXNTLO","created_at":"2026-07-05T11:15:47.286524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00838","citing_title":"Stylometry recognizes human and LLM-generated texts in short samples","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B","json":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B.json","graph_json":"https://pith.science/api/pith-number/YLGXNTLO3BDPGKVWUUMO5NDO4B/graph.json","events_json":"https://pith.science/api/pith-number/YLGXNTLO3BDPGKVWUUMO5NDO4B/events.json","paper":"https://pith.science/paper/YLGXNTLO"},"agent_actions":{"view_html":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B","download_json":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B.json","view_paper":"https://pith.science/paper/YLGXNTLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23276&json=true","fetch_graph":"https://pith.science/api/pith-number/YLGXNTLO3BDPGKVWUUMO5NDO4B/graph.json","fetch_events":"https://pith.science/api/pith-number/YLGXNTLO3BDPGKVWUUMO5NDO4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B/action/storage_attestation","attest_author":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B/action/author_attestation","sign_citation":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B/action/citation_signature","submit_replication":"https://pith.science/pith/YLGXNTLO3BDPGKVWUUMO5NDO4B/action/replication_record"}},"created_at":"2026-07-05T11:15:47.286524+00:00","updated_at":"2026-07-05T11:15:47.286524+00:00"}