{"id":"W4393583881","doi":"10.5281/zenodo.3674790","title":"CoPhy: Counterfactual Learning of Physical Dynamics (Benchmark Dataset)","year":2019,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Counterfactual thinking; Benchmark (surveying); Dynamics (music); Computer science; Artificial intelligence; Machine learning; Econometrics; Mathematics; Psychology; Geography; Cartography; Social psychology","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":[0.003825697,0.004793579,0.001708483,0.002409928,0.001321457,0.003617106,0.008606893,0.006517968,0.02550454],"category_scores_gemma":[0.01915748,0.001265921,0.003055399,0.001745522,0.001598138,0.002735209,0.005073551,0.004483944,0.0208371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002573974,"about_ca_system_score_gemma":0.002117749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01932703,"about_ca_topic_score_gemma":0.02908058,"domain_scores_codex":[0.9974921,0.0007912241,0.000175657,0.0007036565,0.000646964,0.0001904939],"domain_scores_gemma":[0.9940529,0.002423651,0.0003212442,0.002271533,0.0006039418,0.0003266546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006210889,0.0005917145,0.005773932,0.00231806,0.0005010624,0.0003947955,0.0001041764,0.03026716,0.0008652398,0.005903941,0.9113633,0.04129553],"study_design_scores_gemma":[0.002515978,0.0007133153,0.01865618,0.001045891,0.000335648,0.001605137,0.0003360628,0.3639312,0.008114721,0.05460685,0.5478093,0.0003297338],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02849235,0.006138992,0.03962233,0.002537387,0.001314884,0.00102242,0.8609712,0.0433181,0.01658243],"genre_scores_gemma":[0.04341275,0.0006723484,0.035686,0.0006368654,0.0001368835,0.001164262,0.9132579,0.001247031,0.003785993],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02550454,"threshold_uncertainty_score":0.08532113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02314614858594055,"score_gpt":0.2646380888688546,"score_spread":0.2414919402829141,"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."}}