{"id":"W4407688685","doi":"10.3758/s13428-025-02610-9","title":"Open-access network science: Investigating phonological similarity networks based on the SUBTLEX-US lexicon","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Lexicon; Python (programming language); Artificial intelligence; Natural language processing; Clustering coefficient; Adjacency list; Similarity (geometry); Cluster analysis","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005268631,0.000366351,0.0002334059,0.002103143,0.0006357524,0.0009573162,0.0006762668,0.0004374557,0.008014821],"category_scores_gemma":[0.006970515,0.0002678638,0.0004085258,0.002062155,0.0005447953,0.001969856,0.001329803,0.0006921075,0.001441431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004648968,"about_ca_system_score_gemma":0.0004560104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005608143,"about_ca_topic_score_gemma":0.01147332,"domain_scores_codex":[0.999727,0.00007696683,0.00001696192,0.00009748104,0.00005557974,0.00002616323],"domain_scores_gemma":[0.9974644,0.001673308,0.0002567201,0.0003308193,0.0001812073,0.00009349501],"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":[0.001323571,0.0007232107,0.1598433,0.004606803,0.0006405764,0.001935015,0.01470202,0.07784975,0.05491213,0.2229394,0.1765396,0.2839847],"study_design_scores_gemma":[0.0002181346,0.0003011406,0.1288873,0.0003560028,0.0002110933,0.001373517,0.003994995,0.4355738,0.02010912,0.2104987,0.1983024,0.000173853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7089417,0.0008014012,0.1646582,0.0007039799,0.0001602911,0.0003742249,0.08983741,0.01009185,0.02443092],"genre_scores_gemma":[0.7855477,0.0004780355,0.1215255,0.0001581851,0.00006993784,0.0009333818,0.08387603,0.00169431,0.005716983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9993237,"threshold_uncertainty_score":0.02681226,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4133289132249728,"score_gpt":0.6305229576386698,"score_spread":0.2171940444136971,"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."}}