{"id":"W4412966421","doi":"10.1177/10711813251358264","title":"Less can be More: Effects of a Forgetting Function on an AI-based Policy Capturing Tool Performance","year":2025,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thales (Canada); Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Forgetting; Computer science; Artificial intelligence; Session (web analytics); Machine learning; Relevance (law); Function (biology); Mechanism (biology); Cognitive psychology; Psychology","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":[0.0004131978,0.0002014823,0.000250018,0.00009910775,0.0004318398,0.0001159636,0.0007436998,0.00009846258,8.457107e-8],"category_scores_gemma":[0.0001365781,0.000163264,0.0001266978,0.0002705955,0.000132581,0.0005608203,0.0004637729,0.0002265575,1.768551e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001163294,"about_ca_system_score_gemma":0.00007697208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003316419,"about_ca_topic_score_gemma":0.000005880146,"domain_scores_codex":[0.9989143,0.000009461412,0.0003120912,0.000346149,0.0001557456,0.0002622638],"domain_scores_gemma":[0.9991407,0.0001035923,0.0003534396,0.0002125607,0.0001490459,0.00004068032],"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":[0.0002151187,0.0005891505,0.5677419,0.007183661,0.0004221382,2.767648e-7,0.08186444,0.001025765,0.1833245,0.1102885,0.003788084,0.04355645],"study_design_scores_gemma":[0.0006950119,0.0005424176,0.1229384,0.001738441,0.00007001868,7.730988e-7,0.005275363,0.02372925,0.8430566,0.00133988,0.0001401718,0.0004736771],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985515,0.00001380961,0.0005253228,0.0003385638,0.0000876481,0.0002103077,0.00001476558,0.0001134172,0.0001446423],"genre_scores_gemma":[0.9944539,0.00000700388,0.004936452,0.0005091549,0.00004478033,0.00001258041,0.000003014443,0.00001300747,0.00002007734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6597321,"threshold_uncertainty_score":0.6657714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01106648177758162,"score_gpt":0.2438927538900075,"score_spread":0.2328262721124259,"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."}}