{"id":"W2965031958","doi":"10.1016/j.knosys.2019.104874","title":"Logic-driven autoencoders","year":2019,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Deanship of Scientific Research, King Saud University; King Abdulaziz University","keywords":"Autoencoder; Decoding methods; Encoding (memory); Computer science; Generalization; Artificial intelligence; Fuzzy logic; Set (abstract data type); Representation (politics); Deep learning; Algorithm; Programming language; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000185532,0.0001559663,0.0002123329,0.00008263682,0.0001133885,0.0001884575,0.000926172,0.00007600669,0.00002550187],"category_scores_gemma":[0.000006276791,0.0001302286,0.00009420561,0.000503117,0.00002864161,0.0001679483,0.0001011481,0.0001292673,0.002945654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005901647,"about_ca_system_score_gemma":0.0001085479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000229181,"about_ca_topic_score_gemma":0.00001040605,"domain_scores_codex":[0.998714,0.00009606236,0.0002521266,0.0004497269,0.0001732116,0.0003148694],"domain_scores_gemma":[0.9986586,0.0001439223,0.0001000927,0.0008647934,0.0001098894,0.0001227035],"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":[0.000009022793,0.0004369021,0.006338389,0.0003101575,0.00004916823,0.00001626274,0.0005177082,0.1633496,0.005480962,0.750913,0.06368092,0.00889786],"study_design_scores_gemma":[0.0003309102,0.0000610079,0.0003211238,0.00006707679,0.000003562918,0.000005223021,0.00001796143,0.9014063,0.0002197586,0.0003529852,0.09700752,0.000206518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008855006,0.0008854493,0.9366837,0.00109437,0.002692818,0.0009443237,0.000005001342,0.0007022233,0.04813712],"genre_scores_gemma":[0.9923409,0.000002689186,0.003513241,0.000187506,0.000187794,0.00009904495,0.000005171434,0.00001333557,0.003650324],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9834859,"threshold_uncertainty_score":0.9978307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01981038340582278,"score_gpt":0.2540926165889562,"score_spread":0.2342822331831334,"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."}}