{"id":"W4393156629","doi":"10.1609/aaai.v38i11.29140","title":"Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Photoacoustic and Ultrasonic Imaging","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; Agency for Defense Development","keywords":"Inversion (geology); Perspective (graphical); Computer science; Quality (philosophy); Geology; Mathematical optimization; Artificial intelligence; Mathematics; Epistemology; Paleontology; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007200088,0.001300841,0.001219512,0.001106135,0.0005739229,0.002715369,0.001155585,0.001553655,0.00122621],"category_scores_gemma":[0.03708713,0.0004112024,0.0004907722,0.000988343,0.00235118,0.005187559,0.00267228,0.002240897,0.0003810443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001236826,"about_ca_system_score_gemma":0.001798896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001940217,"about_ca_topic_score_gemma":0.001283428,"domain_scores_codex":[0.995804,0.001795188,0.0002366357,0.0006049093,0.001090931,0.0004683426],"domain_scores_gemma":[0.986931,0.007339463,0.001420998,0.002562083,0.001349701,0.0003968215],"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":[0.0006019811,0.0001760658,0.01605148,0.0002026441,0.0002009889,0.0002515294,0.0002254217,0.7520944,0.008965349,0.04727695,0.003816599,0.1701366],"study_design_scores_gemma":[0.00001122995,0.0001274941,0.00119946,0.00002438353,0.00001592588,0.0001320507,0.00006115829,0.9682968,0.004621509,0.02492387,0.0005654543,0.00002064011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1104459,0.0009540166,0.8830153,0.001611895,0.00006236984,0.00007614447,0.0001208095,0.0007651671,0.002948434],"genre_scores_gemma":[0.9279503,0.0003128618,0.0702035,0.000174475,0.00004594338,0.00004736821,0.0001415244,0.0001180472,0.001006103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007200088,"threshold_uncertainty_score":0.03807819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06441169045379819,"score_gpt":0.3028419576948925,"score_spread":0.2384302672410943,"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."}}