{"id":"W4410714111","doi":"10.1016/j.robot.2025.105056","title":"Deep networks for few-shot manipulation learning from scratch","year":2025,"lang":"en","type":"article","venue":"Robotics and Autonomous Systems","topic":"Force Microscopy Techniques and Applications","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scratch; Shot (pellet); Artificial intelligence; One shot; Human–computer interaction; Programming language; Mechanical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.00008803447,0.0001320092,0.000199,0.00003645831,0.0003109684,0.0001821327,0.00008797362,0.00006563093,0.00001196692],"category_scores_gemma":[0.000001509159,0.0001320552,0.00005882275,0.00008946982,0.00002213264,0.00004450782,0.000041057,0.0001137862,0.000003046066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000282733,"about_ca_system_score_gemma":0.00002382126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006479988,"about_ca_topic_score_gemma":0.000006999139,"domain_scores_codex":[0.9992604,0.00001717837,0.0002518249,0.0002397836,0.00003760435,0.0001931566],"domain_scores_gemma":[0.9995811,0.00006444789,0.0001035173,0.0001596168,0.00005152521,0.00003982208],"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":[0.000005100087,0.00003855073,0.01070613,0.00002996377,0.00006526755,1.088041e-7,0.00006414116,0.6343864,0.0008148308,0.3477201,0.001086288,0.005083126],"study_design_scores_gemma":[0.0002326457,0.00002321559,0.0003844408,0.00006807876,0.0000476527,9.212376e-8,0.000220734,0.9817737,0.0001993285,0.007300453,0.009596265,0.0001533932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00425453,0.0004202231,0.9907624,0.0001705735,0.0001988196,0.0005560871,0.00001201985,0.00008001219,0.003545397],"genre_scores_gemma":[0.9918769,0.000008332236,0.004965952,0.00004025634,0.0002377006,0.0001584884,0.0002293112,0.00001805278,0.002465021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9876224,"threshold_uncertainty_score":0.5385056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01501641185618162,"score_gpt":0.2682335892473681,"score_spread":0.2532171773911864,"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."}}