{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02426529,0.0002799863,0.0004565733,0.0003514839,0.002372462,0.003075267,0.005779377,0.0001129032,0.001369176],"category_scores_gemma":[0.0006103645,0.0001985312,0.0001857759,0.005397929,0.001864272,0.0003852139,0.004959181,0.001912703,0.000006717854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002042268,"about_ca_system_score_gemma":0.0009577749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009779987,"about_ca_topic_score_gemma":0.00002179257,"domain_scores_codex":[0.9923108,0.004220888,0.0004863333,0.0009325825,0.0008075394,0.001241831],"domain_scores_gemma":[0.9943531,0.003337382,0.0001479452,0.001474461,0.0004523014,0.000234843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006814585,0.0006184711,0.384873,0.000008650112,0.00005245132,0.000007176923,0.00003138567,0.01265144,0.002325444,0.2524936,0.02801651,0.3188537],"study_design_scores_gemma":[0.0008917226,0.0003403366,0.2217482,0.0004033303,0.0001618398,6.641136e-7,0.0003115435,0.5381534,0.02555373,0.1794208,0.03210142,0.0009130314],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2774996,0.0001754155,0.5865863,0.005322674,0.0004227705,0.004461389,0.00001608465,0.0003501598,0.1251656],"genre_scores_gemma":[0.9150012,0.000002910484,0.08237539,0.0006718652,0.0003241961,0.001202846,0.00002235934,0.000024693,0.0003745942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6375015,"threshold_uncertainty_score":0.9995998,"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."}}