{"id":"W4381797942","doi":"10.48550/arxiv.2306.13040","title":"What to Learn: Features, Image Transformations, or Both?","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Feature (linguistics); Computer science; Transformation (genetics); Image (mathematics); Computer vision; Pattern recognition (psychology); Artificial neural network; Matching (statistics); Transfer of learning; Robotics; Invariant (physics); Term (time); Feature matching; Machine learning; Robot; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009530938,0.0002719985,0.000252078,0.0003246671,0.00009671126,0.000218452,0.000343691,0.0002845638,0.00008238911],"category_scores_gemma":[0.00001942353,0.0003026289,0.000130935,0.000530483,0.00002753454,0.0003697692,0.0001105345,0.000437792,0.0003902108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001980853,"about_ca_system_score_gemma":0.00005142565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006103883,"about_ca_topic_score_gemma":0.0002619298,"domain_scores_codex":[0.9990184,0.00003752309,0.0001807514,0.0003931165,0.00008032611,0.0002899279],"domain_scores_gemma":[0.999202,0.00004972795,0.00003596999,0.0004751948,0.00007093304,0.0001662089],"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":[0.0000260077,0.0000126711,0.00002127173,0.0001947335,0.0000597929,0.0001267881,0.0002875843,0.98848,0.00006789431,0.002725547,0.00770955,0.0002882029],"study_design_scores_gemma":[0.0004622192,0.00004566531,0.0005387247,0.0003635427,0.0001220557,0.000004122952,0.0008137114,0.9855229,0.0005311333,0.002496031,0.008359569,0.0007403597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05326777,0.000169823,0.9379064,0.0004921836,0.002916871,0.0008563966,0.0001137949,0.001603071,0.002673714],"genre_scores_gemma":[0.9837517,0.00320701,0.0009292267,0.0001255809,0.0001387023,0.000002434147,0.0003593279,0.0001138543,0.01137221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9369771,"threshold_uncertainty_score":0.9999426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05856718286475374,"score_gpt":0.1894379011021486,"score_spread":0.1308707182373949,"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."}}