{"id":"W6891775876","doi":"10.48448/mcwj-g845","title":"DadmaTools: Natural Language Processing Toolkit for Persian Language","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Language identification; Natural language; Persian; Universal Networking Language; Natural (archaeology)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001004038,0.0005024649,0.0004581415,0.001166346,0.0006639576,0.001013128,0.005470627,0.000203245,0.0004823236],"category_scores_gemma":[0.0003733143,0.0004410761,0.00013669,0.001871939,0.0005286693,0.0009987128,0.001478844,0.0007416066,0.00002904235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004247566,"about_ca_system_score_gemma":0.0009879339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001688913,"about_ca_topic_score_gemma":0.0001355202,"domain_scores_codex":[0.9960397,0.00005570751,0.0003600717,0.001404998,0.001212604,0.0009269263],"domain_scores_gemma":[0.9978667,0.00008526369,0.0004618904,0.001252843,0.0001475147,0.0001857625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001350862,0.0001550013,0.00002007942,0.0006040698,0.00003924321,0.0001960132,0.007037011,0.000004458012,0.005916819,0.02786895,0.1673961,0.7907487],"study_design_scores_gemma":[0.002173012,0.0006768563,0.00001374212,0.001325107,0.0001656361,0.0006265928,0.01010981,0.2455282,0.01060817,0.00717198,0.7159796,0.005621293],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001289507,0.1519252,0.6223801,0.003401187,0.003639817,0.003937812,0.0003210393,0.01409096,0.2001749],"genre_scores_gemma":[0.02101139,0.00002021471,0.7931218,0.001412626,0.0005590382,0.0001722459,0.0001596792,0.000344259,0.1831988],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7851274,"threshold_uncertainty_score":0.9999102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01146059298631998,"score_gpt":0.3042653346532331,"score_spread":0.2928047416669132,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}