{"id":"W6966533420","doi":"10.48448/hqbd-as52","title":"Studying word order through iterative shuffling","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Shuffling; Phrase; Word (group theory); Language model; Inference; Suite; Sentence; Benchmark (surveying)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003016977,0.0007339246,0.0005688409,0.001176653,0.000740646,0.001415894,0.001217138,0.0007591492,0.005325507],"category_scores_gemma":[0.02364073,0.0005488759,0.0006595181,0.00112799,0.001727067,0.003640337,0.001659291,0.001860265,0.001788409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008467755,"about_ca_system_score_gemma":0.001488764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00278242,"about_ca_topic_score_gemma":0.005183247,"domain_scores_codex":[0.9984758,0.0007961221,0.00007549571,0.0003209467,0.0002299315,0.0001017021],"domain_scores_gemma":[0.9881346,0.008598585,0.0006916448,0.00174434,0.0006086364,0.0002220815],"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":[0.0005330179,0.0003333505,0.01380632,0.0003463997,0.0001437051,0.0005554647,0.001662443,0.2831936,0.02143728,0.315308,0.009908278,0.3527722],"study_design_scores_gemma":[0.00003799728,0.00005825523,0.000688544,0.00002167205,0.00001761556,0.00008535253,0.000131457,0.7054003,0.01051885,0.2792574,0.003752204,0.00003029968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08389017,0.0002159367,0.9092105,0.0004353057,0.00004679736,0.0000719497,0.0002660148,0.001448464,0.004414918],"genre_scores_gemma":[0.6149544,0.0002425545,0.3768356,0.0003595082,0.00007596148,0.0002503138,0.001325556,0.0009735716,0.00498254],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005325507,"threshold_uncertainty_score":0.01781553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06734167491659197,"score_gpt":0.3518259270461,"score_spread":0.284484252129508,"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."}}