{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YRDE4FMKFJTGFGCQC5L6QNYMRF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a6dd50890e8d4a9afdcc306dcd89b084a881c72fea3e716af2b074585f387ea3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T21:09:55Z","title_canon_sha256":"3763caf3e66482e820086c44ec17c1428a183fffad16af7fdffeceef72112ac0"},"schema_version":"1.0","source":{"id":"2509.01772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.01772","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2509.01772v1","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01772","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"YRDE4FMKFJTG","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"YRDE4FMKFJTGFGCQ","created_at":"2026-07-05T12:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"YRDE4FMK","created_at":"2026-07-05T12:03:07Z"}],"graph_snapshots":[{"event_id":"sha256:1d0b071f1b73346f4f7c114f347a9cce1318a300a9ccc872d99be5b734269d56","target":"graph","created_at":"2026-07-05T12:03:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.01772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdelkrime Aries","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T21:09:55Z","title":"chDzDT: Word-level morphology-aware language model for Algerian social media text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01772","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3fcc5a25cb769d1600ed224380cb212232267e793487781372a13ccb842ea195","target":"record","created_at":"2026-07-05T12:03:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a6dd50890e8d4a9afdcc306dcd89b084a881c72fea3e716af2b074585f387ea3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T21:09:55Z","title_canon_sha256":"3763caf3e66482e820086c44ec17c1428a183fffad16af7fdffeceef72112ac0"},"schema_version":"1.0","source":{"id":"2509.01772","kind":"arxiv","version":1}},"canonical_sha256":"c4464e158a2a666298501757e8370c8949e0e430327f4cae55dabfb098c361cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4464e158a2a666298501757e8370c8949e0e430327f4cae55dabfb098c361cc","first_computed_at":"2026-07-05T12:03:07.920703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:07.920703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0slAZ9WDU0h9w4+8Wht9dYXlmec7m+bvoQNmKb87p1Ifuhd/zhS14X/E+8hgrHbgomydXDxE3yQ3T7/qJZsoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:07.921271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.01772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fcc5a25cb769d1600ed224380cb212232267e793487781372a13ccb842ea195","sha256:1d0b071f1b73346f4f7c114f347a9cce1318a300a9ccc872d99be5b734269d56"],"state_sha256":"fb6e5b7d4313bf0dc3da432a724d0b6e0bc4555a299539ecc6890a2cf87b81c9"}