{"id":"W6966966793","doi":"10.48448/n4d3-w687","title":"Towards Reproducible Machine Learning Research in Natural Language Processing Part 2","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Natural language; Support vector machine; Feature (linguistics); Natural (archaeology); Training set","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007713657,0.0002504518,0.0002799206,0.002153379,0.0006995328,0.0006138487,0.003237608,0.0001057723,0.0006869892],"category_scores_gemma":[0.001048317,0.0002274527,0.00003534762,0.004931925,0.0004743501,0.0005460338,0.001799553,0.002341227,0.000120301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003665546,"about_ca_system_score_gemma":0.001125652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002359679,"about_ca_topic_score_gemma":0.0007453887,"domain_scores_codex":[0.994713,0.0004924891,0.000348821,0.001820975,0.001832639,0.0007920467],"domain_scores_gemma":[0.9978074,0.00008566359,0.0002651607,0.001592387,0.00012045,0.0001289822],"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":[0.00000596845,0.0001771922,0.002306398,0.0001610749,0.000006992007,0.00008588901,0.001974108,0.0003854009,0.0004851715,0.00795372,0.03139094,0.9550672],"study_design_scores_gemma":[0.0002026728,0.0000745763,0.0004440468,0.0001263326,0.000002445205,0.00002233734,0.0003739495,0.3247256,0.0000393246,0.0001866867,0.6735206,0.0002814572],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0004019407,0.02405809,0.01319613,0.009696236,0.002216256,0.001136629,0.00003510771,0.002288583,0.946971],"genre_scores_gemma":[0.2650188,0.0004212242,0.06175568,0.0004396313,0.001141404,0.000160288,0.0007193492,0.0003816646,0.669962],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9547857,"threshold_uncertainty_score":0.9999604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05891084852940384,"score_gpt":0.3753735924228179,"score_spread":0.3164627438934141,"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."}}