{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LI6WNUFMNYZUFNNEEGX5R2SDVQ","short_pith_number":"pith:LI6WNUFM","schema_version":"1.0","canonical_sha256":"5a3d66d0ac6e3342b5a421afd8ea43ac1fac35c877ea09e4c7737b2cd2d42014","source":{"kind":"arxiv","id":"2606.21460","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of Small Language Models for Arabic Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdulrahman Gharawi, Ahmad Shabana, Ahmed Alhusayni, Alshaymaa Allahim, Israa Hamdine, Jumana Alsubhi, Lamees Alhumaid, Rafik Madani","submitted_at":"2026-06-19T14:16:13Z","abstract_excerpt":"This paper evaluates the performance of twelve Small Language Models (SLMs) on Arabic natural language processing tasks. The study introduces a benchmark of 240 Arabic test items distributed across eight domains and ten language skills, covering both comprehension-oriented and generation-oriented tasks. All models were evaluated under a controlled zero-shot setting using a standardized Arabic-only prompt template. Model responses were assessed through a multi-model LLM-as-a-judge framework involving GPT-4.1 Mini, Claude Haiku 4.5, and DeepSeek-Chat, with scores aggregated across judges and ana"},"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":"2606.21460","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-19T14:16:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ad97acd6804a45b2bc32d3579f005e6fbd2cfd0c2906c127e1e0acc9c119ade","abstract_canon_sha256":"f6f95b4b86e40a5eaf1c9045ae710d64036be810f9ae8c7b7415fd371272202e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:11.093491Z","signature_b64":"t2fEqCrLj7OTV+7GxEso4LcUFLeucDP6xL/9QTyg1vQpVkgNqmj0Q0oQy45cU2g2q4gMOMajH7ZKYLjMWhebBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a3d66d0ac6e3342b5a421afd8ea43ac1fac35c877ea09e4c7737b2cd2d42014","last_reissued_at":"2026-06-23T01:13:11.093002Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:11.093002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Small Language Models for Arabic Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdulrahman Gharawi, Ahmad Shabana, Ahmed Alhusayni, Alshaymaa Allahim, Israa Hamdine, Jumana Alsubhi, Lamees Alhumaid, Rafik Madani","submitted_at":"2026-06-19T14:16:13Z","abstract_excerpt":"This paper evaluates the performance of twelve Small Language Models (SLMs) on Arabic natural language processing tasks. The study introduces a benchmark of 240 Arabic test items distributed across eight domains and ten language skills, covering both comprehension-oriented and generation-oriented tasks. All models were evaluated under a controlled zero-shot setting using a standardized Arabic-only prompt template. Model responses were assessed through a multi-model LLM-as-a-judge framework involving GPT-4.1 Mini, Claude Haiku 4.5, and DeepSeek-Chat, with scores aggregated across judges and ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21460","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/2606.21460/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":"2606.21460","created_at":"2026-06-23T01:13:11.093067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21460v1","created_at":"2026-06-23T01:13:11.093067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21460","created_at":"2026-06-23T01:13:11.093067+00:00"},{"alias_kind":"pith_short_12","alias_value":"LI6WNUFMNYZU","created_at":"2026-06-23T01:13:11.093067+00:00"},{"alias_kind":"pith_short_16","alias_value":"LI6WNUFMNYZUFNNE","created_at":"2026-06-23T01:13:11.093067+00:00"},{"alias_kind":"pith_short_8","alias_value":"LI6WNUFM","created_at":"2026-06-23T01:13:11.093067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ","json":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ.json","graph_json":"https://pith.science/api/pith-number/LI6WNUFMNYZUFNNEEGX5R2SDVQ/graph.json","events_json":"https://pith.science/api/pith-number/LI6WNUFMNYZUFNNEEGX5R2SDVQ/events.json","paper":"https://pith.science/paper/LI6WNUFM"},"agent_actions":{"view_html":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ","download_json":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ.json","view_paper":"https://pith.science/paper/LI6WNUFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21460&json=true","fetch_graph":"https://pith.science/api/pith-number/LI6WNUFMNYZUFNNEEGX5R2SDVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LI6WNUFMNYZUFNNEEGX5R2SDVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ/action/storage_attestation","attest_author":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ/action/author_attestation","sign_citation":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ/action/citation_signature","submit_replication":"https://pith.science/pith/LI6WNUFMNYZUFNNEEGX5R2SDVQ/action/replication_record"}},"created_at":"2026-06-23T01:13:11.093067+00:00","updated_at":"2026-06-23T01:13:11.093067+00:00"}