{"id":"W1603107701","doi":"10.1007/978-3-540-70829-2_13","title":"Opposite Actions in Reinforced Image Segmentation","year":2008,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Obstacle; Artificial intelligence; Segmentation; Machine learning; Process (computing); Image segmentation; Computer vision","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":[0.0005173275,0.0003052715,0.0004058327,0.000476371,0.0004866112,0.001255068,0.0006995262,0.001010723,0.004634247],"category_scores_gemma":[0.002628486,0.0003318729,0.0003591866,0.0005693376,0.002356473,0.002405897,0.001075552,0.001362225,0.0005404014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005703695,"about_ca_system_score_gemma":0.0003311258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007989503,"about_ca_topic_score_gemma":0.0007791526,"domain_scores_codex":[0.9997427,0.00005841632,0.00001302766,0.00007724475,0.00008168504,0.00002699383],"domain_scores_gemma":[0.9989887,0.0006344428,0.0001001776,0.0001231636,0.00008733865,0.00006629203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006401561,0.00002254333,0.000352643,0.00006770585,0.00001074866,0.0001323672,0.0002612578,0.01214897,0.008280318,0.9141142,0.001575329,0.06296989],"study_design_scores_gemma":[0.000009192924,0.0000302143,0.0007536429,0.00002590928,0.00001227161,0.0002985685,0.0001056901,0.1160233,0.008364392,0.8675541,0.006804063,0.00001868753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.141037,0.003694561,0.7281725,0.002124198,0.000515652,0.00004889846,0.00008095918,0.0005096248,0.1238166],"genre_scores_gemma":[0.8024041,0.001899111,0.1561463,0.000224709,0.0002236986,0.00005617143,0.00008856596,0.0002074599,0.03874978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004634247,"threshold_uncertainty_score":0.01550317,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1493669577841351,"score_gpt":0.3897149674028239,"score_spread":0.2403480096186888,"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."}}