{"id":"W4409364181","doi":"10.1609/aaai.v39i16.33809","title":"Learning Regularization for Graph Inverse Problems","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council","keywords":"Regularization (linguistics); Inverse problem; Graph; Inverse; Mathematics; Computer science; Artificial intelligence; Applied mathematics; Theoretical computer science; Mathematical analysis","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":[0.0006109169,0.0001569972,0.0001828718,0.0001899118,0.0003392475,0.0002354414,0.001317366,0.00008303844,0.00001040854],"category_scores_gemma":[0.0007528104,0.0001223151,0.0001135788,0.0009009684,0.0001306466,0.0002664047,0.0002513945,0.000234731,0.00001554031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002573476,"about_ca_system_score_gemma":0.00008347478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000261866,"about_ca_topic_score_gemma":0.000007343788,"domain_scores_codex":[0.998696,0.00002076006,0.0003735661,0.0004061998,0.0002428454,0.0002605936],"domain_scores_gemma":[0.9988155,0.00009528346,0.0002700005,0.0002085755,0.0005685727,0.00004204509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002277801,0.00005790968,0.0003056596,0.0000788848,0.00001178862,3.375936e-8,0.000843081,0.001401625,0.009312159,0.8798775,0.0002914149,0.1077972],"study_design_scores_gemma":[0.00003994191,0.0001824754,0.0001174995,0.0002739439,0.0000117055,6.810311e-7,0.0002338146,0.3695499,0.1201924,0.5076239,0.001628311,0.0001454716],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05161908,0.00002770222,0.891397,0.01459158,0.0009209827,0.001100733,0.000001922781,0.0003547861,0.03998623],"genre_scores_gemma":[0.9891695,0.00001775716,0.006450541,0.0002522856,0.00003230325,0.00005390683,8.430878e-7,0.000008029318,0.004014871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9375504,"threshold_uncertainty_score":0.4987864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04268476056366192,"score_gpt":0.2866678817304282,"score_spread":0.2439831211667663,"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."}}