{"id":"W3098396746","doi":"10.18653/v1/2020.emnlp-main.551","title":"Distilling Structured Knowledge for Text-Based Relational Reasoning","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Canadian Institute for Advanced Research; Compute Canada; Microsoft Research","keywords":"Computer science; Artificial intelligence; Natural language processing; Benchmark (surveying); Task (project management); Statistical relational learning; Machine learning; Relational database; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000091584,0.0000747908,0.00008344871,0.00002318037,0.00009931439,0.00006074502,0.0003149656,0.00003686558,0.0000259028],"category_scores_gemma":[0.0001602465,0.00006722024,0.00004925692,0.0001354966,0.000009132994,0.0001533552,0.00006620464,0.00006762332,0.0000148288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002096895,"about_ca_system_score_gemma":0.00008608014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002520292,"about_ca_topic_score_gemma":0.000002715369,"domain_scores_codex":[0.9992979,0.0000148717,0.0001457865,0.0002927174,0.0001050272,0.0001436918],"domain_scores_gemma":[0.999504,0.0001388522,0.00003744215,0.0001716432,0.00006211617,0.00008591593],"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":[0.000008400128,0.000009319096,0.0007405096,0.00002875064,0.000008054421,0.000001046222,0.0007239268,0.03281143,0.000487988,0.9227813,0.0007526246,0.04164669],"study_design_scores_gemma":[0.000267079,0.00001541067,0.0005422992,0.000008800495,0.000002368271,5.078564e-7,0.000006849721,0.9896308,0.0007444127,0.002640159,0.006049985,0.00009129148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002049081,0.00005641432,0.9924641,0.00251287,0.0001550421,0.0001208787,0.000002051348,0.0002030076,0.002436615],"genre_scores_gemma":[0.5403618,9.381434e-8,0.4590418,0.0003955803,0.0001054299,0.000005839798,0.000003282374,0.000003996937,0.00008216478],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9568194,"threshold_uncertainty_score":0.2741162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04633304072299972,"score_gpt":0.2667868192989307,"score_spread":0.220453778575931,"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."}}