{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001946884,0.00009407403,0.000230422,0.00002371377,0.0004264341,0.00009109365,0.0001009094,0.00005318184,0.000153397],"category_scores_gemma":[0.01021349,0.00006237892,0.00004913919,0.00009746409,0.0001226096,0.00002156906,0.00009405547,0.0003456442,0.000007982127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009461586,"about_ca_system_score_gemma":0.0000404401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001536419,"about_ca_topic_score_gemma":0.000001124177,"domain_scores_codex":[0.9988821,0.0003187649,0.0002959083,0.0001379056,0.000194102,0.0001711772],"domain_scores_gemma":[0.9898877,0.009648443,0.0001339867,0.0001834448,0.0001038376,0.00004257594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001512307,0.00003219424,0.000127356,0.0002599504,0.00004041826,0.000004093627,0.006480168,0.000009145484,0.0003064667,0.980548,0.0002243139,0.01195283],"study_design_scores_gemma":[0.000316417,0.00001917631,0.0001751349,0.0001705914,0.00004184556,0.00004484319,0.006049567,0.0004698792,0.003097008,0.9843172,0.005201161,0.00009720878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5206817,0.001931425,0.402953,0.002144888,0.0007869905,0.0003289851,0.000002394326,0.0003464818,0.07082404],"genre_scores_gemma":[0.4931284,0.0001580391,0.4933701,0.00008886721,0.0001098843,0.00001998234,0.000002785614,0.00003702158,0.01308496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09041707,"threshold_uncertainty_score":0.9981239,"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."}}