{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":2,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"030217acec42","filters":{"venue":"Northern European Journal of Language Technology"}},"results":[{"id":"W4311428537","doi":"10.3384/nejlt.2000-1533.2022.4315","title":"Part-of-Speech and Morphological Tagging of Algerian Judeo-Arabic","year":2022,"lang":"en","type":"article","venue":"Northern European Journal of Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Natural language processing; Annotation; Arabic; Preprocessor; Pipeline (software); Artificial intelligence; Part of speech; Linguistics","authors":[{"name":"Ofra Tirosh-Becker","is_ca":false},{"name":"Michal Kessler","is_ca":false},{"name":"Oren M. Becker","is_ca":false},{"name":"Yonatan Belinkov","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0101339323969064,"gpt":0.2372624635259936,"spread":0.2271285311290872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006144456,0.0003889793,0.0002017307,0.002610513,0.001141506,0.0007654896,0.0004077101,0.0004935798,0.003358496],"category_scores_gemma":[0.002535133,0.0001923041,0.000189204,0.001704567,0.0005231891,0.0008272795,0.0005433368,0.0003595247,0.002231368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004512831,"about_ca_system_score_gemma":0.0005079855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004796105,"about_ca_topic_score_gemma":0.01017159,"domain_scores_codex":[0.9994821,0.0001517475,0.0000628284,0.0001666443,0.0001009864,0.0000357577],"domain_scores_gemma":[0.9972621,0.001201544,0.0002912763,0.0004148098,0.0007452202,0.00008502127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001192908,0.0003203502,0.05989053,0.001373649,0.00009209669,0.003761229,0.01422355,0.008956791,0.2957924,0.006235136,0.01867493,0.5894864],"study_design_scores_gemma":[0.00008433074,0.0002677372,0.3932351,0.0002942482,0.0001485801,0.00411036,0.01145755,0.1167407,0.2889008,0.005413044,0.1791356,0.0002119851],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.951947,0.0008960935,0.02673796,0.0003859096,0.0002186839,0.0001247229,0.006139412,0.001461422,0.01208894],"genre_scores_gemma":[0.9005495,0.0004868087,0.07479942,0.0001019851,0.0001027903,0.0001442358,0.01436596,0.0003593152,0.00909005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004796105,"threshold_uncertainty_score":0.01123524,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402487814","doi":"10.3384/nejlt.2000-1533.2024.5217","title":"Documenting Geographically and Contextually Diverse Language Data Sources","year":2024,"lang":"en","type":"article","venue":"Northern European Journal of Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Sorbonne Université; Università Bocconi; Centre National de la Recherche Scientifique; Grand Équipement National De Calcul Intensif; Simon Fraser University","keywords":"Spatial contextual awareness; Context (archaeology); Geography; Remote sensing","authors":[{"name":"Angelina McMillan-Major","is_ca":false},{"name":"Francesco De Toni","is_ca":false},{"name":"Zaid Alyafeai","is_ca":false},{"name":"Stella Biderman","is_ca":false},{"name":"Kimbo Chen","is_ca":false},{"name":"Gérard Dupont","is_ca":false},{"name":"Hady Elsahar","is_ca":false},{"name":"Chris Chinenye Emezue","is_ca":false},{"name":"Alham Fikri Aji","is_ca":false},{"name":"Suzana Ilić","is_ca":false},{"name":"Nurulaqilla Khamis","is_ca":false},{"name":"Colin Leong","is_ca":false},{"name":"Maraim Masoud","is_ca":false},{"name":"Aitor Soroa","is_ca":false},{"name":"Pedro Ortiz Suárez","is_ca":false},{"name":"Daniel van Strien","is_ca":false},{"name":"Zeerak Talat","is_ca":false},{"name":"Yacine Jernite","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01162351447033166,"gpt":0.2669204921008031,"spread":0.2552969776304714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02702418,0.0009206197,0.001196209,0.02289252,0.003833008,0.00893464,0.002344528,0.001177088,0.003138102],"category_scores_gemma":[0.06588727,0.001117426,0.0009540666,0.02172525,0.001991492,0.01088061,0.009095831,0.002061008,0.00169978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002967599,"about_ca_system_score_gemma":0.009662352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01358122,"about_ca_topic_score_gemma":0.02901388,"domain_scores_codex":[0.9779856,0.009104858,0.004027218,0.003510428,0.004753424,0.0006184838],"domain_scores_gemma":[0.9177834,0.04165714,0.007555739,0.01622535,0.01535172,0.001426689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003087536,0.0005958061,0.1140604,0.003267378,0.0003059109,0.002311643,0.09119362,0.007184144,0.02498427,0.09389028,0.03076654,0.6311313],"study_design_scores_gemma":[0.0001706073,0.0002773193,0.08240096,0.00225813,0.000379736,0.003076494,0.09938381,0.04874478,0.04705425,0.1224927,0.5932208,0.000540409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1472145,0.00108643,0.7788972,0.003677502,0.0001625041,0.003295137,0.0376208,0.005815311,0.02223063],"genre_scores_gemma":[0.19747,0.0005837946,0.7592434,0.0004440527,0.00007318078,0.002563938,0.03466426,0.001260773,0.003696623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02702418,"threshold_uncertainty_score":0.1429192,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}