{"id":"W4414265080","doi":"10.1117/12.3063619","title":"MCMC-LIME: enhancing stability of LIME using Markov chain Monte Carlo approach","year":2025,"lang":"en","type":"article","venue":"","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Markov chain Monte Carlo; Robustness (evolution); Segmentation; Monte Carlo method; Merge (version control); Markov chain; Stability (learning theory); Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002820753,0.0002752888,0.0006872762,0.0001739171,0.0001061023,0.00002883473,0.0002778286,0.0001871331,0.00006542522],"category_scores_gemma":[0.001016119,0.0002373946,0.0002516512,0.0004409762,0.000102783,0.00009467286,0.0002576008,0.0002372671,4.578989e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001548197,"about_ca_system_score_gemma":0.0001602803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004343553,"about_ca_topic_score_gemma":0.0001926322,"domain_scores_codex":[0.9976731,0.0004068254,0.0007669406,0.0004625584,0.0002878475,0.0004027067],"domain_scores_gemma":[0.9978028,0.0007857414,0.0002090685,0.0008811661,0.0002262972,0.00009492791],"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":[0.0007905554,0.003506502,0.01437745,0.01499088,0.001512636,0.00002150365,0.01169247,0.0003304075,0.5789277,0.3171801,0.004988802,0.05168106],"study_design_scores_gemma":[0.003877545,0.0002940923,0.0005488316,0.001112877,0.0009528597,0.00002457582,0.02449341,0.273964,0.6760934,0.01318323,0.003459425,0.001995688],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5690018,0.0002589793,0.3396685,0.00007718429,0.0001954547,0.0005895416,0.00001326382,0.0001086961,0.09008665],"genre_scores_gemma":[0.6264986,0.000010397,0.3698682,0.00007524488,0.00004616658,0.00002003576,0.000001358729,0.00002531227,0.003454759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3039968,"threshold_uncertainty_score":0.9680673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08257068759877423,"score_gpt":0.3580593006875617,"score_spread":0.2754886130887875,"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."}}