{"id":"W4289670471","doi":"10.48550/arxiv.1809.01494","title":"Interpretation of Natural Language Rules in Conversational Machine\\n Reading","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Reading (process); Interpretation (philosophy); Question answering; Natural (archaeology); Artificial intelligence; Government (linguistics); Natural language processing; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005864868,0.0003494995,0.0004661343,0.0006429093,0.00008887032,0.00007536356,0.001613207,0.0002775409,0.0001277662],"category_scores_gemma":[0.0001301583,0.0004382717,0.0002182114,0.0005524068,0.0002486012,0.000726392,0.001497379,0.0006767315,0.00007851016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004361646,"about_ca_system_score_gemma":0.0002769827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001090947,"about_ca_topic_score_gemma":0.0002164134,"domain_scores_codex":[0.9973767,0.0002886567,0.0005217011,0.001270063,0.0001764008,0.0003665137],"domain_scores_gemma":[0.9978333,0.0002408641,0.0005830973,0.0009687212,0.0002700144,0.000104036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005058557,0.0003022176,0.05078483,0.0006963563,0.0003256869,0.0005183608,0.03342102,0.5974545,0.0008830656,0.2957979,0.00004684815,0.01926333],"study_design_scores_gemma":[0.0006555908,0.00004159452,0.004503615,0.0004512309,0.0000399997,0.000005425106,0.0004946426,0.9835273,0.0003211929,0.009582295,0.00001202935,0.0003651048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5515704,0.000115314,0.4459466,0.00003902337,0.0008460502,0.0001932686,0.00001664113,0.00003820546,0.001234498],"genre_scores_gemma":[0.9937772,0.00006388613,0.005295275,0.00005477034,0.00009558262,4.71863e-7,0.00004139435,0.00001519274,0.0006562389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4422068,"threshold_uncertainty_score":0.9998069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03690349792639731,"score_gpt":0.2000435815320063,"score_spread":0.163140083605609,"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."}}