{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001284994,0.0009548827,0.0008369365,0.0004796693,0.000266684,0.001125621,0.001129764,0.001677162,0.003348122],"category_scores_gemma":[0.007095414,0.0002892668,0.0004685397,0.0006229087,0.001203511,0.005528059,0.0007341261,0.001737935,0.001736114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004014923,"about_ca_system_score_gemma":0.0006511279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002227711,"about_ca_topic_score_gemma":0.001958688,"domain_scores_codex":[0.9995111,0.0001166356,0.00002169901,0.0002307603,0.00006743926,0.00005237809],"domain_scores_gemma":[0.9983225,0.0008736465,0.0001737373,0.0002910854,0.0002391941,0.0000997307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002002713,0.000251453,0.007993526,0.0004159114,0.00009920033,0.00009711367,0.0001051232,0.0280448,0.004471949,0.01061912,0.01501275,0.9326888],"study_design_scores_gemma":[0.0001108173,0.000522555,0.01014675,0.0002979397,0.0001578963,0.0007799625,0.0005870433,0.7520443,0.01375255,0.202465,0.01903349,0.0001016836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08174087,0.009150746,0.8814728,0.01589338,0.0005570197,0.00010163,0.0008296047,0.002550533,0.007703475],"genre_scores_gemma":[0.8251157,0.003872568,0.1597106,0.002247704,0.0007393379,0.0001383487,0.001109611,0.0002427236,0.006823424],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003348122,"threshold_uncertainty_score":0.01120055,"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."}}