{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZOUPCO4RC5CLK2JIY5N26JSPSH","short_pith_number":"pith:ZOUPCO4R","schema_version":"1.0","canonical_sha256":"cba8f13b911744b56928c75baf264f91f2800a27aae42c2066d4f93a33ce9911","source":{"kind":"arxiv","id":"2505.17894","version":2},"attestation_state":"computed","paper":{"title":"Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Muhammad Hreden, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","submitted_at":"2025-05-23T13:42:21Z","abstract_excerpt":"We introduce Mutarjim, a compact yet powerful language model for bidirectional Arabic-English translation. While large-scale LLMs have shown impressive progress in natural language processing tasks, including machine translation, smaller models. Leveraging this insight, we developed Mutarjim based on Kuwain-1.5B , a language model tailored for both Arabic and English. Despite its modest size, Mutarjim outperforms much larger models on several established benchmarks, achieved through an optimized two-phase training approach and a carefully curated, high-quality training corpus.. Experimental re"},"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":"2505.17894","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T13:42:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac99b14c65c1545a2f7aef47dcc170cfb1b609c2828f8b399f0ad98468316dab","abstract_canon_sha256":"7e316d252387a06e36e0964796a17eb0a65089f65f3fd7146ec7aa3dccc97525"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:57.409329Z","signature_b64":"kq+YpJOA9bxWpo4K4e7uCemAW8B664hv74kYBnbejxbg3AioLDiSA7gFANBJbYAanlB9lVhO5VHkPtDIzE7xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cba8f13b911744b56928c75baf264f91f2800a27aae42c2066d4f93a33ce9911","last_reissued_at":"2026-07-05T11:56:57.408839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:57.408839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Khalil Hennara, Mohamed Motaism Hamed, Muhammad Hreden, Safwan AlModhayan, Sara Chrouf, Zeina Aldallal","submitted_at":"2025-05-23T13:42:21Z","abstract_excerpt":"We introduce Mutarjim, a compact yet powerful language model for bidirectional Arabic-English translation. While large-scale LLMs have shown impressive progress in natural language processing tasks, including machine translation, smaller models. Leveraging this insight, we developed Mutarjim based on Kuwain-1.5B , a language model tailored for both Arabic and English. Despite its modest size, Mutarjim outperforms much larger models on several established benchmarks, achieved through an optimized two-phase training approach and a carefully curated, high-quality training corpus.. Experimental re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17894","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/2505.17894/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":"2505.17894","created_at":"2026-07-05T11:56:57.408897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17894v2","created_at":"2026-07-05T11:56:57.408897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17894","created_at":"2026-07-05T11:56:57.408897+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOUPCO4RC5CL","created_at":"2026-07-05T11:56:57.408897+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOUPCO4RC5CLK2JI","created_at":"2026-07-05T11:56:57.408897+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOUPCO4R","created_at":"2026-07-05T11:56:57.408897+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/ZOUPCO4RC5CLK2JIY5N26JSPSH","json":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH.json","graph_json":"https://pith.science/api/pith-number/ZOUPCO4RC5CLK2JIY5N26JSPSH/graph.json","events_json":"https://pith.science/api/pith-number/ZOUPCO4RC5CLK2JIY5N26JSPSH/events.json","paper":"https://pith.science/paper/ZOUPCO4R"},"agent_actions":{"view_html":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH","download_json":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH.json","view_paper":"https://pith.science/paper/ZOUPCO4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17894&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOUPCO4RC5CLK2JIY5N26JSPSH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOUPCO4RC5CLK2JIY5N26JSPSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH/action/storage_attestation","attest_author":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH/action/author_attestation","sign_citation":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH/action/citation_signature","submit_replication":"https://pith.science/pith/ZOUPCO4RC5CLK2JIY5N26JSPSH/action/replication_record"}},"created_at":"2026-07-05T11:56:57.408897+00:00","updated_at":"2026-07-05T11:56:57.408897+00:00"}