{"id":"W3166655837","doi":"10.1080/10986065.2021.1940427","title":"The double-edged sword of conjecturing","year":2021,"lang":"en","type":"article","venue":"Mathematical Thinking and Learning","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Israeli Centers for Research Excellence; Azrieli Foundation; Israel Science Foundation","keywords":"SWORD; Mathematics education; Computer science; Statistical model; Statistical analysis; Epistemology; Psychology; Artificial intelligence; Mathematics; Statistics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01864685,0.0006063435,0.000722077,0.001630406,0.002144542,0.008024464,0.002466121,0.002334717,0.004632826],"category_scores_gemma":[0.1057393,0.0005469613,0.0006924354,0.0008365968,0.01857251,0.01074412,0.00830657,0.005617847,0.001280242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519334,"about_ca_system_score_gemma":0.002110861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003098619,"about_ca_topic_score_gemma":0.0004139618,"domain_scores_codex":[0.9761055,0.01473415,0.001195098,0.002379212,0.004970862,0.0006151486],"domain_scores_gemma":[0.8807363,0.08156276,0.01008374,0.0167907,0.006721962,0.004104547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002523204,0.0002366861,0.02594453,0.0009346684,0.00009227794,0.001581415,0.09159306,0.004434553,0.00867624,0.7151098,0.00802697,0.1431175],"study_design_scores_gemma":[0.00004239506,0.0002928092,0.007280043,0.0004571398,0.00003399918,0.002247213,0.01221589,0.01085635,0.006177809,0.8957951,0.06448701,0.0001141808],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3747957,0.001642058,0.5271591,0.02783039,0.0004749139,0.0002048336,0.000176166,0.0008230449,0.06689381],"genre_scores_gemma":[0.9312786,0.0005240343,0.0612089,0.001185001,0.0001496607,0.0001024537,0.00007531488,0.0001851111,0.005290815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01864685,"threshold_uncertainty_score":0.09861517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1498832762163705,"score_gpt":0.4022001684055007,"score_spread":0.2523168921891301,"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."}}