{"id":"W1537398163","doi":"10.1007/978-3-642-31951-8_2","title":"Beyond Reward: The Problem of Knowledge and Data","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Computability, Logic, AI Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Commonsense knowledge; Meaning (existential); Knowledge base; Artificial intelligence; Reinforcement learning; Knowledge management; Cognitive science; Epistemology; 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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003248032,0.0005597124,0.0006783772,0.0004678541,0.0002815684,0.0003570592,0.01013296,0.000290211,0.00001516126],"category_scores_gemma":[0.00009223477,0.0003943646,0.00008968595,0.0007516249,0.001950019,0.0009238981,0.01324473,0.0008973255,0.00002103261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001441651,"about_ca_system_score_gemma":0.0006203231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003505995,"about_ca_topic_score_gemma":0.0001290755,"domain_scores_codex":[0.9955226,0.0001034951,0.0007086674,0.001989762,0.0009305977,0.0007449152],"domain_scores_gemma":[0.9932174,0.001379121,0.000406546,0.004464792,0.0003287643,0.0002033461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002253019,0.00005277108,0.0001742694,0.00008511612,0.00001351769,0.00000839286,0.001345279,0.0006969285,0.00002765624,0.02819806,0.0000758401,0.9693199],"study_design_scores_gemma":[0.0003205533,0.0002353328,0.001109557,0.0003175378,0.00003189235,0.0002037226,3.861406e-7,0.4447713,0.0003270834,0.5369332,0.01484384,0.0009056608],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005670009,0.006874046,0.9849129,0.001156899,0.001153623,0.0006652183,0.00002040407,0.0001089706,0.005051287],"genre_scores_gemma":[0.07931632,0.0002054301,0.9186835,0.0005574209,0.0009247498,0.00001054765,0.00001263313,0.00004414113,0.0002452871],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9684142,"threshold_uncertainty_score":0.9998508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03249919021536033,"score_gpt":0.2752775497751014,"score_spread":0.2427783595597411,"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."}}