{"id":"W1547503210","doi":"10.21427/1hkq-vf87","title":"Back to the Future:Knowledge Light Case Base Cookery","year":2021,"lang":"en","type":"article","venue":"Arrow@dit (Dublin Institute of Technology)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science Foundation Ireland; Canada Millennium Scholarship Foundation","keywords":"Recipe; WordNet; Computer science; Adaptation (eye); Domain (mathematical analysis); Similarity (geometry); Artificial intelligence; Ingredient; Representation (politics); Knowledge base; Case-based reasoning; Natural language processing; Information retrieval; Mathematics; Food science","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":[0.004386781,0.0005417606,0.0004241635,0.00252662,0.001367386,0.00625905,0.002662913,0.002910892,0.02323448],"category_scores_gemma":[0.01646021,0.0004843283,0.0008450968,0.002168562,0.001754058,0.005729693,0.003101996,0.002079698,0.00344485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002468585,"about_ca_system_score_gemma":0.001617812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007842157,"about_ca_topic_score_gemma":0.01180528,"domain_scores_codex":[0.9965557,0.001702468,0.0001884629,0.0003561321,0.0009925445,0.0002047445],"domain_scores_gemma":[0.9908376,0.006522154,0.0002844277,0.001463594,0.0005944854,0.000297684],"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":[0.001017999,0.0009888038,0.004760847,0.0007035374,0.0001111533,0.01010176,0.002425108,0.06256968,0.002367757,0.2699212,0.09859601,0.5464362],"study_design_scores_gemma":[0.0003905869,0.0001632152,0.001483479,0.0009917208,0.000104012,0.004055697,0.002122154,0.2611066,0.009003039,0.2948211,0.4256085,0.0001499891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1036651,0.004631186,0.6424932,0.02686182,0.001111447,0.00153862,0.008086627,0.006763358,0.2048486],"genre_scores_gemma":[0.4322244,0.002063152,0.532887,0.001756107,0.0001524132,0.0003938061,0.005087486,0.0004419399,0.02499375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02323448,"threshold_uncertainty_score":0.07772708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01063067401975512,"score_gpt":0.2496688746371536,"score_spread":0.2390382006173985,"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."}}