{"id":"W4416034840","doi":"10.18653/v1/2025.findings-emnlp.609","title":"How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study","year":2025,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Sampling (signal processing); Noise (video); Measure (data warehouse)","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":[],"consensus_categories":[],"category_scores_codex":[0.01184742,0.001484931,0.001177912,0.003492825,0.00132934,0.003492218,0.001200271,0.001455956,0.001571837],"category_scores_gemma":[0.09533055,0.0004789494,0.0009576392,0.002171429,0.001620944,0.00516503,0.002241851,0.002102979,0.002936926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007796223,"about_ca_system_score_gemma":0.0009930701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003029013,"about_ca_topic_score_gemma":0.004122584,"domain_scores_codex":[0.9885139,0.005393793,0.001014153,0.002442806,0.002227462,0.0004079383],"domain_scores_gemma":[0.888007,0.08563604,0.004446247,0.01298436,0.007698101,0.001228163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002560033,0.0007245722,0.2037222,0.002760239,0.0009263417,0.001338665,0.00427149,0.04320537,0.0449326,0.00415579,0.05044629,0.6409565],"study_design_scores_gemma":[0.0003384235,0.001761705,0.1647074,0.0007300131,0.0007155377,0.004987997,0.003430718,0.5740882,0.1680901,0.02862924,0.05197115,0.0005495445],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8751414,0.006164098,0.08705365,0.001232782,0.0005605273,0.0002867732,0.007707919,0.01419881,0.007653981],"genre_scores_gemma":[0.946061,0.0007274076,0.03256168,0.0003287312,0.0001935021,0.0001334306,0.01642009,0.001775049,0.001799122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01184742,"threshold_uncertainty_score":0.06265593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04284217487403143,"score_gpt":0.3160113045522304,"score_spread":0.273169129678199,"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."}}