{"id":"W4403413296","doi":"10.1145/3674805.3686688","title":"Negative Results of Image Processing for Identifying Duplicate Questions on Stack Overflow","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Stack (abstract data type); Image processing; Image (mathematics); Artificial intelligence; Pattern recognition (psychology); Data mining; Information retrieval; Programming language","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":[0.01006278,0.001968706,0.001282048,0.003248289,0.001338347,0.002555455,0.001451002,0.002488619,0.002896315],"category_scores_gemma":[0.0942084,0.0004196277,0.001566241,0.001597501,0.001754831,0.005368393,0.002073682,0.002293613,0.001878521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001304973,"about_ca_system_score_gemma":0.001440734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005802032,"about_ca_topic_score_gemma":0.004600595,"domain_scores_codex":[0.9906666,0.003677283,0.000788133,0.001791247,0.002537922,0.0005388587],"domain_scores_gemma":[0.8900293,0.0843005,0.004397803,0.009365924,0.01064079,0.001265651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005555464,0.001226972,0.1272466,0.003884172,0.0007996926,0.003436627,0.008579237,0.04017678,0.08516488,0.0099951,0.0453744,0.66856],"study_design_scores_gemma":[0.0002002381,0.00161874,0.07479171,0.0006921315,0.0008095712,0.003986483,0.005382243,0.6286782,0.2104989,0.02754749,0.04534169,0.0004525524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7358519,0.003434344,0.2272927,0.003577664,0.001205973,0.0008106537,0.003037025,0.01187273,0.01291695],"genre_scores_gemma":[0.8880278,0.0005018114,0.1024264,0.0009593415,0.0002995345,0.0001960381,0.002738823,0.0008266177,0.004023581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01006278,"threshold_uncertainty_score":0.05321771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05917570804844958,"score_gpt":0.3451050293138652,"score_spread":0.2859293212654156,"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."}}