{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00199462,0.0003653291,0.0004029807,0.0009275051,0.0004148823,0.0005650772,0.0001991812,0.0006681752,0.007516975],"category_scores_gemma":[0.02251662,0.0001815569,0.0003149306,0.0005529844,0.00030392,0.0009066702,0.0006420516,0.0004802194,0.00167334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002375644,"about_ca_system_score_gemma":0.0001490174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001046426,"about_ca_topic_score_gemma":0.001883915,"domain_scores_codex":[0.9982119,0.0006510324,0.0003232713,0.0002960262,0.0004347491,0.00008313759],"domain_scores_gemma":[0.978625,0.01526602,0.001710367,0.0007969012,0.002962727,0.0006389787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.010555,0.00158076,0.550047,0.001937828,0.0005220422,0.00105454,0.01899488,0.001442276,0.1376357,0.002170925,0.0124263,0.2616328],"study_design_scores_gemma":[0.0001008877,0.001245564,0.9788103,0.000101307,0.0001303633,0.0007079106,0.00198236,0.001851638,0.007671286,0.0004290167,0.006917091,0.00005230227],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907775,0.0003076543,0.001042161,0.00005739168,0.00004491838,0.00008742112,0.000925883,0.00007254504,0.006684556],"genre_scores_gemma":[0.9831696,0.0003575771,0.004306909,0.0001348298,0.00005744991,0.0002235655,0.00313588,0.0001231833,0.008491064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007516975,"threshold_uncertainty_score":0.02514678,"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."}}