{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YRDE4FMKFJTGFGCQC5L6QNYMRF","short_pith_number":"pith:YRDE4FMK","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"},"canonical_sha256":"c4464e158a2a666298501757e8370c8949e0e430327f4cae55dabfb098c361cc","source":{"kind":"arxiv","id":"2509.01772","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YRDE4FMKFJTGFGCQC5L6QNYMRF","target":"record","payload":{"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"},"canonical_sha256":"c4464e158a2a666298501757e8370c8949e0e430327f4cae55dabfb098c361cc","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"},"source_kind":"arxiv","source_id":"2509.01772","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CZrzMefKm/uuDMFOVyTFYk68irYiK1Esw0s8HVFOm1eIjGutik9KJvgRovN4HXGCcE4A+In6241ZZJN8g7H9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:46:59.188484Z"},"content_sha256":"3fcc5a25cb769d1600ed224380cb212232267e793487781372a13ccb842ea195","schema_version":"1.0","event_id":"sha256:3fcc5a25cb769d1600ed224380cb212232267e793487781372a13ccb842ea195"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YRDE4FMKFJTGFGCQC5L6QNYMRF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8xiobioeaR86vaRwquYseJ2PnPiQI97G9v4Sk2To+b7noqI5oGTDFWr+PNo+OvqisOk87sH3ceGONUdSuO3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:46:59.188985Z"},"content_sha256":"1d0b071f1b73346f4f7c114f347a9cce1318a300a9ccc872d99be5b734269d56","schema_version":"1.0","event_id":"sha256:1d0b071f1b73346f4f7c114f347a9cce1318a300a9ccc872d99be5b734269d56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/bundle.json","state_url":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T21:46:59Z","links":{"resolver":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF","bundle":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/bundle.json","state":"https://pith.science/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRDE4FMKFJTGFGCQC5L6QNYMRF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GtnPgNBILuEiHCTnwJVeY+mdzUWHt0GiK68Ul9a/PUWPgT517lZTh9Zi9IfYN7WGOZT0emXXF9fZeEDo/NuUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:46:59.192823Z","bundle_sha256":"b5c9fa098c494b368fc41197cc00b38fabe0ed90ca881a404e6fa2a59bcf7967"}}