{"id":"W4379511143","doi":"10.21428/594757db.5ed119cc","title":"Learning to Recognize Reachable States from Visual Domains","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Computer science; Noise (video); Hidden Markov model; Viterbi algorithm; Artificial intelligence; State (computer science); Algorithm; Space (punctuation); Property (philosophy); Machine learning; Image (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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003982448,0.0001110563,0.0001305779,0.0001371312,0.0001926537,0.0002147611,0.0004400938,0.00003526883,0.0001606864],"category_scores_gemma":[0.0001425374,0.00009578375,0.00004051228,0.0008006255,0.000009443497,0.0001764607,0.0003771128,0.0002177986,0.003855079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001625334,"about_ca_system_score_gemma":0.00002206907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001087842,"about_ca_topic_score_gemma":0.000025923,"domain_scores_codex":[0.9987638,0.00009838472,0.0001439216,0.0004114941,0.0002337604,0.0003486431],"domain_scores_gemma":[0.9992884,0.0002588551,0.00003297917,0.0002357452,0.00003532853,0.0001486539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001143773,0.000066151,0.008456467,0.000009239175,0.00004898102,0.0001098346,0.00872678,0.0205134,0.002671133,0.002652359,0.03767049,0.9190637],"study_design_scores_gemma":[0.0002578656,0.0002410814,0.005567133,0.00001911679,0.000002667812,0.000002406323,0.0004301944,0.8952301,0.001044377,0.00406716,0.09286886,0.0002690891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5421394,0.00001466791,0.4407629,0.004686024,0.0005251743,0.000108887,0.00000253805,0.00254784,0.009212652],"genre_scores_gemma":[0.6644824,0.00004753412,0.2421422,0.002039255,0.0005537447,0.00003909504,0.00009852114,0.00005080788,0.09054642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9187946,"threshold_uncertainty_score":0.9969205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101772433736837,"score_gpt":0.2760604000459559,"score_spread":0.2658831566722722,"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."}}