{"id":"W2965349778","doi":"10.4230/lipics.icalp.2019.84","title":"Short Proofs Are Hard to Find","year":2019,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Mathematical proof; Computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007908118,0.00239558,0.002280646,0.003384494,0.004862883,0.009852098,0.003478761,0.003721629,0.1058762],"category_scores_gemma":[0.07252703,0.003371448,0.003079132,0.005214345,0.004115095,0.03215416,0.01072643,0.00840799,0.04418086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003154858,"about_ca_system_score_gemma":0.002799176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009880287,"about_ca_topic_score_gemma":0.001274164,"domain_scores_codex":[0.9876989,0.003022752,0.0009666437,0.003163146,0.00405216,0.001096425],"domain_scores_gemma":[0.8980374,0.07186642,0.005268546,0.01683725,0.006425498,0.001564787],"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":[0.0005989936,0.0001602222,0.001078329,0.002669357,0.0002969076,0.0008000177,0.0009641097,0.004924446,0.004819744,0.6179987,0.1519518,0.2137373],"study_design_scores_gemma":[0.00008547879,0.00004397906,0.0001891842,0.0002559344,0.00007640364,0.0006678557,0.0001933845,0.00479746,0.002518538,0.8557065,0.13541,0.00005532195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02287458,0.01464797,0.7316297,0.04832846,0.004971839,0.0009007578,0.006934154,0.01673841,0.1529741],"genre_scores_gemma":[0.3779912,0.01416835,0.4215367,0.01622346,0.004432944,0.001496531,0.01177309,0.01248577,0.139892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1058762,"threshold_uncertainty_score":0.3541913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04533790389707443,"score_gpt":0.3725974693966653,"score_spread":0.3272595654995908,"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."}}