{"id":"W3193303189","doi":"10.48550/arxiv.2108.08145","title":"Active Observer Visual Problem-Solving Methods are Dynamically Hypothesized, Deployed and Tested","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Spatial Cognition and Navigation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Observer (physics); Computer science; Relevance (law); Variety (cybernetics); Cognition; Representation (politics); Artificial intelligence; Cognitive architecture; Machine learning; Human–computer interaction; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001855264,0.0003153332,0.0003726958,0.0001566566,0.00009068841,0.00009356879,0.0001833393,0.0003676825,0.00007479941],"category_scores_gemma":[0.0001089285,0.0003905237,0.0001337162,0.0003651639,0.00006087473,0.0002287628,0.0003107469,0.0006186984,0.00000816818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002231214,"about_ca_system_score_gemma":0.00005590152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008064403,"about_ca_topic_score_gemma":0.0001830852,"domain_scores_codex":[0.9986526,0.0002691188,0.0001940952,0.0005762082,0.00006640927,0.0002415749],"domain_scores_gemma":[0.9990063,0.0002592596,0.000130251,0.0002601695,0.000200543,0.0001434504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006563354,0.000691083,0.02571169,0.003816639,0.00319921,0.001746129,0.002995355,0.8051665,0.06463622,0.002547618,0.0002632684,0.08856994],"study_design_scores_gemma":[0.001297785,0.00004703449,0.0536284,0.0006620967,0.0003949112,0.00000925093,0.0009765556,0.9315169,0.006695213,0.003766703,0.00005908158,0.0009461001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8115869,0.00009642429,0.1865301,0.00001527286,0.000191632,0.0003201925,0.00002150333,0.0004487163,0.0007892846],"genre_scores_gemma":[0.9900721,0.0002460016,0.009323791,0.00004066852,0.00004264681,0.000002943425,0.00009418933,0.00006015794,0.0001174726],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1784852,"threshold_uncertainty_score":0.9998547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0615149002700407,"score_gpt":0.218520456050207,"score_spread":0.1570055557801663,"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."}}