{"id":"W4410701749","doi":"10.3847/1538-4357/adcabf","title":"Learning to See: Applying Inverse Recurrent Inference Machines to See through Refractive Scattering","year":2025,"lang":"en","type":"article","venue":"The Astrophysical Journal","topic":"Optical measurement and interference techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Perimeter Institute; University of Waterloo","funders":"","keywords":"Physics; Inference; Inverse scattering problem; Scattering; Inverse problem; Inverse; Optics; Theoretical physics; Artificial intelligence; Mathematical analysis; Geometry; Computer science","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":[0.0003516673,0.0001964463,0.0002273939,0.0001079462,0.0004080469,0.0005026226,0.00128295,0.00003337792,0.00001880042],"category_scores_gemma":[0.0002636566,0.0001322217,0.0001005028,0.0005713249,0.00005479806,0.0005939805,0.0007732362,0.0009234911,0.0001765307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001405322,"about_ca_system_score_gemma":0.00007035487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002129584,"about_ca_topic_score_gemma":0.000003070893,"domain_scores_codex":[0.9984168,0.000180576,0.0002823758,0.0003007755,0.0004210405,0.0003983811],"domain_scores_gemma":[0.9990631,0.0001470483,0.00009577518,0.0003353742,0.0002009776,0.0001577168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001684248,0.0001907833,0.0007151098,0.00001839768,0.00009213757,0.00001578007,0.004051011,0.002170913,0.3721355,0.03501427,0.00311005,0.5823177],"study_design_scores_gemma":[0.003242101,0.01723105,0.08354203,0.009183812,0.0003513387,0.0001902827,0.004456531,0.2249109,0.3366713,0.2670524,0.04858473,0.004583579],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1994369,0.000009136453,0.7919697,0.00563872,0.0003530016,0.0002430322,4.825332e-7,0.0001241929,0.002224799],"genre_scores_gemma":[0.9168451,0.000008302084,0.08165214,0.001059007,0.0002186109,0.00004223395,2.30817e-7,0.000007671711,0.0001666777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7174082,"threshold_uncertainty_score":0.5391843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03283996858878922,"score_gpt":0.317383135273618,"score_spread":0.2845431666848288,"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."}}