{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EMUMHWJEMAX3CJC3BGUZ5SHS5L","short_pith_number":"pith:EMUMHWJE","schema_version":"1.0","canonical_sha256":"2328c3d924602fb1245b09a99ec8f2eaea10080af1ffaafc01e8ec83c8de55df","source":{"kind":"arxiv","id":"2605.28827","version":1},"attestation_state":"computed","paper":{"title":"RightNow-Arabic-0.5B-Turbo: An Open Sub-1B Arabic Language Model via Vocabulary Injection and Edge-First Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jaber Jaber, Osama Jaber","submitted_at":"2026-04-10T00:56:50Z","abstract_excerpt":"Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arabic as an afterthought (Qwen2.5-0.5B, Falcon-H1-0.5B), and 7B-70B Arabic-specialized models that require a server to run (Jais, AceGPT, ALLaM, SILMA). The one published attempt at a sub-2B Arabic-specialized model, Kuwain-1.5B, never released its weights. We present RightNow-Arabic-0.5B-Turbo, a 518M-parameter Arabic-specialized decoder LLM built on Qwen2.5-0.5B. The pipeline adds 27,032 Arabic tokens via mean-subtoken initialization, continues pretraining on 504M Arabic tokens on 8xH100 with FSD"},"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":"2605.28827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T00:56:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb12e28724573ac4945ad6926a10bc47b3f7e0c74c9334f00d313a31522e1a4e","abstract_canon_sha256":"d09bcf82a01d2c3fe1ef2dab593941fff728f84bce89d46aaf20bcb02c3ab8d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:13.108913Z","signature_b64":"X2rdzdwmt4gsqRBE5nYjGXxN+CApubjtAKn1f7vgimE2j+zmBNR4/uM3hPZtFnlwvcQjV/R4AB4usegdyfMsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2328c3d924602fb1245b09a99ec8f2eaea10080af1ffaafc01e8ec83c8de55df","last_reissued_at":"2026-05-29T00:04:13.107986Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:13.107986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RightNow-Arabic-0.5B-Turbo: An Open Sub-1B Arabic Language Model via Vocabulary Injection and Edge-First Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jaber Jaber, Osama Jaber","submitted_at":"2026-04-10T00:56:50Z","abstract_excerpt":"Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arabic as an afterthought (Qwen2.5-0.5B, Falcon-H1-0.5B), and 7B-70B Arabic-specialized models that require a server to run (Jais, AceGPT, ALLaM, SILMA). The one published attempt at a sub-2B Arabic-specialized model, Kuwain-1.5B, never released its weights. We present RightNow-Arabic-0.5B-Turbo, a 518M-parameter Arabic-specialized decoder LLM built on Qwen2.5-0.5B. The pipeline adds 27,032 Arabic tokens via mean-subtoken initialization, continues pretraining on 504M Arabic tokens on 8xH100 with FSD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28827","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/2605.28827/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":"2605.28827","created_at":"2026-05-29T00:04:13.108096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28827v1","created_at":"2026-05-29T00:04:13.108096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28827","created_at":"2026-05-29T00:04:13.108096+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMUMHWJEMAX3","created_at":"2026-05-29T00:04:13.108096+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMUMHWJEMAX3CJC3","created_at":"2026-05-29T00:04:13.108096+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMUMHWJE","created_at":"2026-05-29T00:04:13.108096+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/EMUMHWJEMAX3CJC3BGUZ5SHS5L","json":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L.json","graph_json":"https://pith.science/api/pith-number/EMUMHWJEMAX3CJC3BGUZ5SHS5L/graph.json","events_json":"https://pith.science/api/pith-number/EMUMHWJEMAX3CJC3BGUZ5SHS5L/events.json","paper":"https://pith.science/paper/EMUMHWJE"},"agent_actions":{"view_html":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L","download_json":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L.json","view_paper":"https://pith.science/paper/EMUMHWJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28827&json=true","fetch_graph":"https://pith.science/api/pith-number/EMUMHWJEMAX3CJC3BGUZ5SHS5L/graph.json","fetch_events":"https://pith.science/api/pith-number/EMUMHWJEMAX3CJC3BGUZ5SHS5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L/action/storage_attestation","attest_author":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L/action/author_attestation","sign_citation":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L/action/citation_signature","submit_replication":"https://pith.science/pith/EMUMHWJEMAX3CJC3BGUZ5SHS5L/action/replication_record"}},"created_at":"2026-05-29T00:04:13.108096+00:00","updated_at":"2026-05-29T00:04:13.108096+00:00"}