{"id":"W4411081344","doi":"10.1101/2025.06.06.656993","title":"A Self-Supervised Foundation Model for Robust and Generalizable Representation Learning in STED Microscopy","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Artificial Intelligence in Medicine (Canada); Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"STED microscopy; Foundation (evidence); Representation (politics); Self representation; Artificial intelligence; Computer science; Machine learning; Art; Political science; Superresolution; Humanities; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001112661,0.0005634989,0.0007734933,0.0004867279,0.0003225481,0.0008161845,0.00135074,0.001158363,0.001634953],"category_scores_gemma":[0.003041689,0.0004681924,0.0008457179,0.0004191344,0.001063241,0.001458785,0.001618697,0.001786259,0.0004792246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009364442,"about_ca_system_score_gemma":0.0008942948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002945677,"about_ca_topic_score_gemma":0.004088141,"domain_scores_codex":[0.9996547,0.0001102337,0.00001527626,0.0001043066,0.0000669104,0.00004873488],"domain_scores_gemma":[0.9989958,0.0004613757,0.0001444716,0.0001655961,0.000172506,0.00006012394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001362484,0.00007861539,0.001148092,0.00009389507,0.00006423172,0.0001015465,0.0000914508,0.8895863,0.01017876,0.04823812,0.002463852,0.04781882],"study_design_scores_gemma":[0.000002795318,0.00000872669,0.00004422393,0.000002511377,0.000002119463,0.00000718403,0.000002086883,0.9945227,0.0003902585,0.00487479,0.0001402492,0.000002385831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04943713,0.0001992221,0.9478465,0.0003621262,0.00001986593,0.0000304399,0.0002011448,0.0006076145,0.001296046],"genre_scores_gemma":[0.8507243,0.0003022379,0.1426958,0.0002573317,0.00005050088,0.000189831,0.0008311139,0.0002060561,0.004742868],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002945677,"threshold_uncertainty_score":0.006794453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02102087619435132,"score_gpt":0.2567150338818125,"score_spread":0.2356941576874612,"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."}}