{"id":"W3176158018","doi":"10.48550/arxiv.2104.01940","title":"What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Competence (human resources); sort; Natural language processing; Benchmark (surveying); Language model; Set (abstract data type); Task (project management); Deep learning; Machine learning; Cognitive science; Information retrieval; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001265023,0.0005278846,0.0003784317,0.000720554,0.002989718,0.004326282,0.0007806073,0.001473897,0.0477391],"category_scores_gemma":[0.00775159,0.0002440596,0.0003206469,0.001376439,0.0009195958,0.00342597,0.0008984606,0.002031688,0.01043873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00356364,"about_ca_system_score_gemma":0.003739989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1743674,"about_ca_topic_score_gemma":0.4002381,"domain_scores_codex":[0.9993818,0.000213152,0.00002908128,0.0001542334,0.0001246453,0.00009718076],"domain_scores_gemma":[0.9976567,0.000667933,0.0001263178,0.0002032938,0.0007211544,0.0006245983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005182133,0.0001723944,0.01747566,0.0006898544,0.00008706671,0.0006906069,0.003144484,0.005383907,0.003727727,0.02866125,0.6271911,0.3122578],"study_design_scores_gemma":[0.00006470043,0.00009269969,0.03167001,0.0004790359,0.00005406393,0.0004226626,0.008216365,0.01467197,0.004436414,0.03168665,0.9080727,0.0001327568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.206852,0.008965326,0.02801329,0.08861245,0.005276849,0.0004065612,0.02229467,0.006677674,0.6329013],"genre_scores_gemma":[0.7257574,0.004599927,0.04084597,0.004600808,0.0007135834,0.0002017198,0.02480541,0.00114533,0.1973298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1743674,"threshold_uncertainty_score":0.3467049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1900392553308146,"score_gpt":0.2508452537321296,"score_spread":0.06080599840131493,"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."}}