{"id":"W4286560902","doi":"10.3758/s13428-022-01912-6","title":"Concreteness ratings for 62,000 English multiword expressions","year":2022,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Concreteness; Computer science; Psychology; Word (group theory); Meaning (existential); Linguistics; Cognitive psychology; Natural language processing","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01102309,0.0001812697,0.000271992,0.0004292378,0.001536504,0.0003701731,0.00302652,0.00009620171,0.0001479405],"category_scores_gemma":[0.003434594,0.0001674459,0.0001300525,0.001264595,0.0001603748,0.0005056974,0.002829709,0.001195701,0.000001609761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002140146,"about_ca_system_score_gemma":0.000257207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001160137,"about_ca_topic_score_gemma":0.000001510026,"domain_scores_codex":[0.9942021,0.002815026,0.000336971,0.0007721513,0.001069,0.0008047048],"domain_scores_gemma":[0.9954814,0.002254825,0.0001109449,0.001042964,0.0009002182,0.0002096503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004884154,0.0001688522,0.0003022298,0.00004993294,0.000008523426,0.0000668795,0.004631413,0.000004198962,0.3903663,0.02014768,0.005569628,0.5786356],"study_design_scores_gemma":[0.001347615,0.0008986215,0.0003299443,0.00008411613,0.00002392003,0.00005700879,0.001703331,0.01045496,0.7873173,0.02648549,0.1703919,0.000905726],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01238763,0.001544909,0.9818898,0.0003890777,0.000635451,0.001752633,0.00005500813,0.001081798,0.0002636706],"genre_scores_gemma":[0.04782943,0.000005631445,0.944747,0.0001020944,0.0001210635,0.00599053,0.00001416215,0.00003678479,0.001153304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5777298,"threshold_uncertainty_score":0.9997634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2310475677753295,"score_gpt":0.5707877905792769,"score_spread":0.3397402228039473,"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."}}