{"id":"W6948047544","doi":"10.48660/23100032","title":"Correlations, representations and transformers in physics and in AI","year":2023,"lang":"en","type":"other","venue":"PIRSA","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transformer; Knowledge representation and reasoning","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":[0.00006146153,0.00008571281,0.0001248084,0.0001828845,0.00001542856,0.00003098508,0.00009297113,0.0000698822,0.000005234174],"category_scores_gemma":[0.00002507127,0.00008803729,0.00001269332,0.0003993605,0.00003715721,0.0002325174,0.0000434633,0.0001495272,0.00000616669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001705572,"about_ca_system_score_gemma":0.00001800169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002481958,"about_ca_topic_score_gemma":0.0009065049,"domain_scores_codex":[0.9994654,0.00001681097,0.0001089791,0.0002333904,0.00007229921,0.0001031271],"domain_scores_gemma":[0.9997395,0.00006195253,0.00003406425,0.0001348629,0.000006662774,0.0000229819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006753452,0.00006336776,0.02093619,0.0001149556,0.00001694591,0.00006768477,0.001652042,0.00002014999,0.00004390766,0.01502958,0.04165196,0.9203964],"study_design_scores_gemma":[0.003231332,0.000233555,0.08697847,0.002523646,0.00004420641,0.00003277736,0.0003377962,0.03112442,0.001505251,0.1631209,0.7086955,0.002172189],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00003420747,0.00101985,0.9402854,0.0005211688,0.00008582742,0.000345983,0.00001026737,0.0004659749,0.05723135],"genre_scores_gemma":[0.08750308,0.06399421,0.2396628,0.002366474,0.0009273102,0.0006867886,0.0001000003,0.002090298,0.6026691],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9182243,"threshold_uncertainty_score":0.3590057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01948132203325257,"score_gpt":0.314046789324504,"score_spread":0.2945654672912514,"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."}}