{"id":"W4391833299","doi":"10.1609/icaps.v34i1.31489","title":"Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings","year":2024,"lang":"en","type":"preprint","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Innovative Teaching and Learning Methods","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"Office of Naval Research","keywords":"Psychology; Epistemology; Computer science; Artificial intelligence; Philosophy","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":[0.002606574,0.0003030525,0.0003685885,0.0004984306,0.0002261192,0.000295852,0.0003425841,0.0003068039,0.00001150791],"category_scores_gemma":[0.0006993371,0.0002646058,0.00006634263,0.0001735772,0.00008544825,0.0001130094,0.0003845142,0.00192686,0.000002261728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008028268,"about_ca_system_score_gemma":0.00007832034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007453477,"about_ca_topic_score_gemma":3.736572e-7,"domain_scores_codex":[0.998175,0.00009106625,0.0005698905,0.0006268607,0.0002803213,0.0002568559],"domain_scores_gemma":[0.998553,0.0003487253,0.0006121481,0.00007947523,0.0003682372,0.0000384505],"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":[0.001737262,0.0002525142,0.1392202,0.005281205,0.001424767,0.00003259276,0.2106375,0.2815197,0.08973081,0.2504575,0.005150201,0.0145557],"study_design_scores_gemma":[0.0005906071,0.0001195668,0.01041865,0.008282417,0.00005125675,0.00002634379,0.009624201,0.946307,0.0008202725,0.02318517,0.0001990765,0.0003754163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9847118,0.0004937553,0.001980284,0.003128098,0.001123538,0.000396907,0.0000252414,0.0003330469,0.007807289],"genre_scores_gemma":[0.9800393,0.00001191983,0.0181102,0.0001486641,0.0001630271,0.0001415544,0.00007078444,0.00004594525,0.001268625],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6647873,"threshold_uncertainty_score":0.9999806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09167038274346535,"score_gpt":0.3999914533419298,"score_spread":0.3083210705984644,"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."}}