{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RKFVE2CGZFW236Q7EI46FLYJRN","short_pith_number":"pith:RKFVE2CG","canonical_record":{"source":{"id":"2109.12346","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T11:51:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b571633c7ba11ccc597c04e2f5b38f7fb99105df2d8ff8968cd6ccab7880752b","abstract_canon_sha256":"48eb892b3ecff23d606131288775c68681fa80430613056ba6404370fa237367"},"schema_version":"1.0"},"canonical_sha256":"8a8b526846c96dadfa1f2239e2af098b7db6c75df2f7560b2fb304d342cb5bf3","source":{"kind":"arxiv","id":"2109.12346","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12346","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12346v3","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12346","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"RKFVE2CGZFW2","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"RKFVE2CGZFW236Q7","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"RKFVE2CG","created_at":"2026-07-05T05:24:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RKFVE2CGZFW236Q7EI46FLYJRN","target":"record","payload":{"canonical_record":{"source":{"id":"2109.12346","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T11:51:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b571633c7ba11ccc597c04e2f5b38f7fb99105df2d8ff8968cd6ccab7880752b","abstract_canon_sha256":"48eb892b3ecff23d606131288775c68681fa80430613056ba6404370fa237367"},"schema_version":"1.0"},"canonical_sha256":"8a8b526846c96dadfa1f2239e2af098b7db6c75df2f7560b2fb304d342cb5bf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:09.530729Z","signature_b64":"nW4k2P4NE7nqXb/baI2g3Jv9E2224ErFOaiQqjDbQBhXNIguGxKuSkZ8+2/T8zjN6XELKDQDaC+Bo0+vSW47CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a8b526846c96dadfa1f2239e2af098b7db6c75df2f7560b2fb304d342cb5bf3","last_reissued_at":"2026-07-05T05:24:09.530267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:09.530267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.12346","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uqnRJXe0/jbLxAwFtTdI4fYpvyxr4mo63coBUORrJ7bIgsXY++nuPTygPRFXFpibuCqSMfPX72WUhVw6DNKyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:43:09.156895Z"},"content_sha256":"f6fad31ba04ae0e742eed6f2270df9ae8d7d924a0c005436f93451c3efd7c0e5","schema_version":"1.0","event_id":"sha256:f6fad31ba04ae0e742eed6f2270df9ae8d7d924a0c005436f93451c3efd7c0e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RKFVE2CGZFW236Q7EI46FLYJRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DziriBERT: a Pre-trained Language Model for the Algerian Dialect","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdelouahab Moussaoui, Amine Abdaoui, Mohamed Berrimi, Mourad Oussalah","submitted_at":"2021-09-25T11:51:35Z","abstract_excerpt":"Pre-trained transformers are now the de facto models in Natural Language Processing given their state-of-the-art results in many tasks and languages. However, most of the current models have been trained on languages for which large text resources are already available (such as English, French, Arabic, etc.). Therefore, there are still a number of low-resource languages that need more attention from the community. In this paper, we study the Algerian dialect which has several specificities that make the use of Arabic or multilingual models inappropriate. To address this issue, we collected mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12346","kind":"arxiv","version":3},"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/2109.12346/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":"2026-07-05T05:24:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A9k31ox93Vkn0tXPslrX1LpcZqa0hcRdfl8la0DuDi4uLchYV+SanZ35XNv6mtujDnzJbkhB7BA4a8h7LsBgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:43:09.157667Z"},"content_sha256":"29aa4f13296d6f0851569da5b8141d211087096970e5a917754ae4e3100ae475","schema_version":"1.0","event_id":"sha256:29aa4f13296d6f0851569da5b8141d211087096970e5a917754ae4e3100ae475"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKFVE2CGZFW236Q7EI46FLYJRN/bundle.json","state_url":"https://pith.science/pith/RKFVE2CGZFW236Q7EI46FLYJRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKFVE2CGZFW236Q7EI46FLYJRN/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":"2026-08-03T21:43:09Z","links":{"resolver":"https://pith.science/pith/RKFVE2CGZFW236Q7EI46FLYJRN","bundle":"https://pith.science/pith/RKFVE2CGZFW236Q7EI46FLYJRN/bundle.json","state":"https://pith.science/pith/RKFVE2CGZFW236Q7EI46FLYJRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKFVE2CGZFW236Q7EI46FLYJRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RKFVE2CGZFW236Q7EI46FLYJRN","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":"48eb892b3ecff23d606131288775c68681fa80430613056ba6404370fa237367","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T11:51:35Z","title_canon_sha256":"b571633c7ba11ccc597c04e2f5b38f7fb99105df2d8ff8968cd6ccab7880752b"},"schema_version":"1.0","source":{"id":"2109.12346","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.12346","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"arxiv_version","alias_value":"2109.12346v3","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12346","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"pith_short_12","alias_value":"RKFVE2CGZFW2","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"pith_short_16","alias_value":"RKFVE2CGZFW236Q7","created_at":"2026-07-05T05:24:09Z"},{"alias_kind":"pith_short_8","alias_value":"RKFVE2CG","created_at":"2026-07-05T05:24:09Z"}],"graph_snapshots":[{"event_id":"sha256:29aa4f13296d6f0851569da5b8141d211087096970e5a917754ae4e3100ae475","target":"graph","created_at":"2026-07-05T05:24:09Z","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/2109.12346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained transformers are now the de facto models in Natural Language Processing given their state-of-the-art results in many tasks and languages. However, most of the current models have been trained on languages for which large text resources are already available (such as English, French, Arabic, etc.). Therefore, there are still a number of low-resource languages that need more attention from the community. In this paper, we study the Algerian dialect which has several specificities that make the use of Arabic or multilingual models inappropriate. To address this issue, we collected mor","authors_text":"Abdelouahab Moussaoui, Amine Abdaoui, Mohamed Berrimi, Mourad Oussalah","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T11:51:35Z","title":"DziriBERT: a Pre-trained Language Model for the Algerian Dialect"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12346","kind":"arxiv","version":3},"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:f6fad31ba04ae0e742eed6f2270df9ae8d7d924a0c005436f93451c3efd7c0e5","target":"record","created_at":"2026-07-05T05:24:09Z","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":"48eb892b3ecff23d606131288775c68681fa80430613056ba6404370fa237367","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-25T11:51:35Z","title_canon_sha256":"b571633c7ba11ccc597c04e2f5b38f7fb99105df2d8ff8968cd6ccab7880752b"},"schema_version":"1.0","source":{"id":"2109.12346","kind":"arxiv","version":3}},"canonical_sha256":"8a8b526846c96dadfa1f2239e2af098b7db6c75df2f7560b2fb304d342cb5bf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a8b526846c96dadfa1f2239e2af098b7db6c75df2f7560b2fb304d342cb5bf3","first_computed_at":"2026-07-05T05:24:09.530267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:09.530267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nW4k2P4NE7nqXb/baI2g3Jv9E2224ErFOaiQqjDbQBhXNIguGxKuSkZ8+2/T8zjN6XELKDQDaC+Bo0+vSW47CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:09.530729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.12346","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6fad31ba04ae0e742eed6f2270df9ae8d7d924a0c005436f93451c3efd7c0e5","sha256:29aa4f13296d6f0851569da5b8141d211087096970e5a917754ae4e3100ae475"],"state_sha256":"090283321fb2b5dd33278b71b5505dc0bd3091a8d756a600c44e814718db2db6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tHYRxl2onzsslaOkCaABorVqYzWh48pJOb8nSwx3NxWJOhAaFDKQHfUs/hbc7hMOr8SEPIl7e6fltkUcCJFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:43:09.163385Z","bundle_sha256":"0dc7643876b4d192b4a837ece5d392355d251e8e63f39e626c99a87b984ca32c"}}