{"id":"W3203427563","doi":"10.1109/icdmw53433.2021.00085","title":"Determining Standard Occupational Classification Codes from Job Descriptions in Immigration Petitions","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Data Mining Workshops (ICDMW)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Becton Dickinson (Canada)","funders":"","keywords":"Computer science; Code (set theory); Task (project management); Variety (cybernetics); Quality (philosophy); Natural language processing; Machine learning; Artificial intelligence; Programming language; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003112716,0.0003911527,0.0003215791,0.00449339,0.0006983392,0.001479992,0.000930036,0.0006242665,0.002514808],"category_scores_gemma":[0.02141682,0.0002951253,0.0004788305,0.003437024,0.0005162767,0.001265074,0.001179323,0.0009500277,0.001868491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00161445,"about_ca_system_score_gemma":0.00244532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02910278,"about_ca_topic_score_gemma":0.03828266,"domain_scores_codex":[0.9977174,0.0007196084,0.0002796339,0.0003016465,0.0008128718,0.0001689851],"domain_scores_gemma":[0.9862684,0.006995881,0.001817096,0.001543822,0.003107352,0.0002675308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006577399,0.0007918044,0.5112777,0.0004526697,0.00007803163,0.0006922634,0.002372148,0.08212549,0.003625674,0.01610888,0.06096434,0.3208533],"study_design_scores_gemma":[0.00006690423,0.0001493304,0.1842228,0.0003775112,0.00003396914,0.000300782,0.003853553,0.7381531,0.009218329,0.01744028,0.04608159,0.0001017848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8267258,0.0002576148,0.1107918,0.0009144463,0.0002003224,0.000659088,0.03918632,0.002106682,0.0191579],"genre_scores_gemma":[0.8324961,0.000182379,0.09072665,0.0001360566,0.00003176897,0.0004808127,0.07179544,0.0001962411,0.003954604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02910278,"threshold_uncertainty_score":0.05786675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3150605083302441,"score_gpt":0.4360140101417311,"score_spread":0.1209535018114871,"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."}}