{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002702191,0.00007735755,0.00009188519,0.00009506028,0.00007218138,0.0002516666,0.0003017184,0.00002761938,0.000003293145],"category_scores_gemma":[0.0001315008,0.00006521989,0.0000489318,0.0002426927,0.00002192765,0.0005729772,0.00009025499,0.00007727063,0.00001548282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003585805,"about_ca_system_score_gemma":0.00008248025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004807974,"about_ca_topic_score_gemma":0.00001028605,"domain_scores_codex":[0.9990833,0.00001531001,0.000238792,0.0003611676,0.0001530836,0.0001483483],"domain_scores_gemma":[0.9993147,0.0001892289,0.00004886497,0.0003064012,0.0001068116,0.00003400362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005725426,0.0001157532,0.000009889511,0.0008553464,0.0000481367,0.00001587629,0.007171559,0.004826249,0.03440909,0.6162156,0.005349539,0.3309257],"study_design_scores_gemma":[0.0001994386,0.00004389866,0.00006915694,0.000289162,0.000005144921,0.000001683512,0.00003920234,0.9386089,0.03413382,0.02585026,0.0006689124,0.00009042292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003667576,0.00007504684,0.9888331,0.001472724,0.0001921379,0.0001960757,0.00001119198,0.0002321403,0.005319969],"genre_scores_gemma":[0.6689115,0.000003670927,0.3295671,0.0000643884,0.00005108931,0.00002169343,0.000001415484,0.00000705692,0.001372077],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9337826,"threshold_uncertainty_score":0.265959,"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."}}