{"id":"W4384664207","doi":"10.3758/s13428-023-02170-w","title":"LaDEP: A large database of English pseudo-compounds","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Yorkville University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database; Programming language; Information retrieval; Natural language processing; World Wide Web","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":[],"consensus_categories":[],"category_scores_codex":[0.01368531,0.0001556982,0.000273978,0.0009190322,0.0002264812,0.0001951348,0.002574013,0.000130589,0.00003511561],"category_scores_gemma":[0.004510529,0.000138158,0.00009659411,0.003872741,0.0001747904,0.0006738082,0.002360175,0.0008397566,0.00003337279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007018904,"about_ca_system_score_gemma":0.0001996447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009146814,"about_ca_topic_score_gemma":0.000006548904,"domain_scores_codex":[0.9953614,0.001712518,0.0003399212,0.0005983076,0.001142562,0.0008453279],"domain_scores_gemma":[0.9960337,0.001035402,0.00008275975,0.001447003,0.001213914,0.0001872707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003130856,0.0006249592,0.002941793,0.0003211785,0.0000234387,0.0004909197,0.006010258,4.146817e-7,0.5467944,0.09850985,0.02774896,0.3165026],"study_design_scores_gemma":[0.0007529152,0.0003155223,0.002550152,0.0002499681,0.00001877974,0.00002395804,0.0005431329,0.004779736,0.9362215,0.02206536,0.0318995,0.0005794712],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04409974,0.002026357,0.9457165,0.0004279887,0.0009278443,0.001147552,0.0001044091,0.003610137,0.001939446],"genre_scores_gemma":[0.05192953,0.00005776456,0.9469455,0.00002550706,0.0001209943,0.0002364103,0.00002488527,0.00002698149,0.0006324043],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3894271,"threshold_uncertainty_score":0.563392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2067183506943114,"score_gpt":0.5583345911829365,"score_spread":0.3516162404886251,"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."}}