{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YRDE4FMKFJTGFGCQC5L6QNYMRF","short_pith_number":"pith:YRDE4FMK","schema_version":"1.0","canonical_sha256":"c4464e158a2a666298501757e8370c8949e0e430327f4cae55dabfb098c361cc","source":{"kind":"arxiv","id":"2509.01772","version":1},"attestation_state":"computed","paper":{"title":"chDzDT: Word-level morphology-aware language model for Algerian social media text","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdelkrime Aries","submitted_at":"2025-09-01T21:09:55Z","abstract_excerpt":"Pre-trained language models (PLMs) have substantially advanced natural language processing by providing context-sensitive text representations. However, the Algerian dialect remains under-represented, with few dedicated models available. Processing this dialect is challenging due to its complex morphology, frequent code-switching, multiple scripts, and strong lexical influences from other languages. These characteristics complicate tokenization and reduce the effectiveness of conventional word- or subword-level approaches.\n  To address this gap, we introduce chDzDT, a character-level pre-train"},"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":"2509.01772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T21:09:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3763caf3e66482e820086c44ec17c1428a183fffad16af7fdffeceef72112ac0","abstract_canon_sha256":"a6dd50890e8d4a9afdcc306dcd89b084a881c72fea3e716af2b074585f387ea3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:07.921271Z","signature_b64":"0slAZ9WDU0h9w4+8Wht9dYXlmec7m+bvoQNmKb87p1Ifuhd/zhS14X/E+8hgrHbgomydXDxE3yQ3T7/qJZsoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4464e158a2a666298501757e8370c8949e0e430327f4cae55dabfb098c361cc","last_reissued_at":"2026-07-05T12:03:07.920703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:07.920703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"chDzDT: Word-level morphology-aware language model for Algerian social media text","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdelkrime Aries","submitted_at":"2025-09-01T21:09:55Z","abstract_excerpt":"Pre-trained language models (PLMs) have substantially advanced natural language processing by providing context-sensitive text representations. However, the Algerian dialect remains under-represented, with few dedicated models available. Processing this dialect is challenging due to its complex morphology, frequent code-switching, multiple scripts, and strong lexical influences from other languages. These characteristics complicate tokenization and reduce the effectiveness of conventional word- or subword-level approaches.\n  To address this gap, we introduce chDzDT, a character-level pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01772","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/2509.01772/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":"2509.01772","created_at":"2026-07-05T12:03:07.920773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01772v1","created_at":"2026-07-05T12:03:07.920773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01772","created_at":"2026-07-05T12:03:07.920773+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRDE4FMKFJTG","created_at":"2026-07-05T12:03:07.920773+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRDE4FMKFJTGFGCQ","created_at":"2026-07-05T12:03:07.920773+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRDE4FMK","created_at":"2026-07-05T12:03:07.920773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26003","citing_title":"Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13411","citing_title":"An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26003","citing_title":"Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF","json":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF.json","graph_json":"https://pith.science/api/pith-number/YRDE4FMKFJTGFGCQC5L6QNYMRF/graph.json","events_json":"https://pith.science/api/pith-number/YRDE4FMKFJTGFGCQC5L6QNYMRF/events.json","paper":"https://pith.science/paper/YRDE4FMK"},"agent_actions":{"view_html":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF","download_json":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF.json","view_paper":"https://pith.science/paper/YRDE4FMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01772&json=true","fetch_graph":"https://pith.science/api/pith-number/YRDE4FMKFJTGFGCQC5L6QNYMRF/graph.json","fetch_events":"https://pith.science/api/pith-number/YRDE4FMKFJTGFGCQC5L6QNYMRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/action/storage_attestation","attest_author":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/action/author_attestation","sign_citation":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/action/citation_signature","submit_replication":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/action/replication_record"}},"created_at":"2026-07-05T12:03:07.920773+00:00","updated_at":"2026-07-05T12:03:07.920773+00:00"}