{"id":"W3105950517","doi":"","title":"Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hessian matrix; Stochastic gradient descent; Eigenvalues and eigenvectors; Computer science; Context (archaeology); Artificial intelligence; Mathematical optimization; Gradient descent; Ridge; Machine learning; Artificial neural network; Algorithm; Mathematics; Applied mathematics; Geology","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":[],"consensus_categories":[],"category_scores_codex":[0.00005277683,0.0001099393,0.000118901,0.00003459716,0.0004283904,0.00001844529,0.001157488,0.00003963786,0.00001041354],"category_scores_gemma":[0.00002685048,0.0001040938,0.0001609758,0.001321876,0.00008254565,0.0004359496,0.0005890395,0.0001466882,0.00003690179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005648614,"about_ca_system_score_gemma":0.00003530571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002237756,"about_ca_topic_score_gemma":0.00001067315,"domain_scores_codex":[0.999112,0.00005738256,0.0001136813,0.000395619,0.00007299319,0.0002483666],"domain_scores_gemma":[0.9991728,0.0000860447,0.0001179849,0.0004749844,0.00002520576,0.000122959],"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":[0.00001720364,0.0001519257,0.04165068,0.00002524134,0.0001479258,0.00007483533,0.001523761,0.1965895,0.01616423,0.7289765,0.01288262,0.001795596],"study_design_scores_gemma":[0.001427817,0.0001162538,0.00972052,0.00006328787,0.0001650518,0.000005082516,0.0006289516,0.9417075,0.01330314,0.01757602,0.01440046,0.0008859397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3326411,0.00003728552,0.6650412,0.001119133,0.000157375,0.0001799211,0.00001499758,0.0001378292,0.0006711473],"genre_scores_gemma":[0.9987254,0.00001465525,0.0007855697,0.0002754147,0.00002249506,5.313851e-7,0.0000020896,0.000006762915,0.000167053],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.745118,"threshold_uncertainty_score":0.4244822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09298876824310644,"score_gpt":0.1914379755067182,"score_spread":0.0984492072636118,"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."}}