{"id":"W4415820784","doi":"10.1109/tip.2025.3624614","title":"Multi-Energy Quasi-Symplectic Langevin Inference for Latent Disentangled Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"Agence Nationale de la Recherche","keywords":"Inference; Information bottleneck method; Bottleneck; Encoding (memory); Integrator; Code (set theory); Approximate inference; Source code","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":[],"consensus_categories":[],"category_scores_codex":[0.000159109,0.0001990147,0.0002113244,0.0001975609,0.0006930776,0.0004297527,0.0003522813,0.00006375128,0.00001118085],"category_scores_gemma":[0.00004076185,0.0001867302,0.0001245746,0.0005813027,0.00005512856,0.0006846884,0.000005766679,0.0001902098,0.000007537649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008288155,"about_ca_system_score_gemma":0.0001434355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004354379,"about_ca_topic_score_gemma":0.00008035783,"domain_scores_codex":[0.9987321,0.00009670039,0.0002464939,0.0004595413,0.0001388105,0.0003263039],"domain_scores_gemma":[0.9991961,0.0002246017,0.00008777779,0.0002290218,0.0001965677,0.00006592175],"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":[0.0000565513,0.0005290612,0.00004728678,0.0001400953,0.00008223657,0.000006159762,0.000613987,0.05068596,0.04092636,0.0003920067,0.0001678933,0.9063524],"study_design_scores_gemma":[0.0006100194,0.00009667002,0.00006495695,0.0001477446,0.00004205151,0.000001760404,0.00005853565,0.9403966,0.0572434,0.0004324414,0.000686759,0.0002190428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002099737,0.0001883915,0.9978896,0.000651289,0.0004292357,0.0001699819,0.000003612992,0.0002202662,0.0002376611],"genre_scores_gemma":[0.8488368,0.00003408186,0.1491041,0.0002665833,0.00003700857,0.0001230205,0.000001662751,0.00001456404,0.001582169],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9061334,"threshold_uncertainty_score":0.7614636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02163577135703434,"score_gpt":0.2862701222859848,"score_spread":0.2646343509289505,"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."}}