{"id":"W4414577602","doi":"10.1109/iccv51701.2025.01146","title":"FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems","year":2025,"lang":"en","type":"article","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Inverse problem; Sampling (signal processing); Context (archaeology); Inverse; Noise (video); Flow (mathematics); Posterior probability; Ode; Importance sampling","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":[0.00014701,0.0001195094,0.0001485317,0.000129181,0.0000440054,0.00004407037,0.0001124748,0.00007552681,0.00004184505],"category_scores_gemma":[0.00007162882,0.0001157113,0.00007197564,0.000179188,0.000007471885,0.00008551432,0.00002171111,0.00007919542,0.0000122334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004190281,"about_ca_system_score_gemma":0.00001206355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004569328,"about_ca_topic_score_gemma":0.00001153529,"domain_scores_codex":[0.9994065,0.000009776582,0.0001970277,0.0001287854,0.00005910783,0.0001988663],"domain_scores_gemma":[0.9995697,0.0001384519,0.000007475832,0.0001941261,0.00004340504,0.00004685607],"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":[0.000003809982,0.00000341992,0.00009972206,0.0002167144,0.00003086125,1.663735e-7,0.0000891191,0.9884796,0.00500796,0.0002692093,0.0007603615,0.005039046],"study_design_scores_gemma":[0.0004441538,0.00001020949,0.0001091085,0.00005423051,0.00001016015,4.477531e-7,0.00003539997,0.9674519,0.001686635,0.0003913237,0.02968217,0.0001242711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1158703,0.00008704127,0.8788621,0.00006354315,0.0005834656,0.0002849155,0.000007458575,0.0006135341,0.00362769],"genre_scores_gemma":[0.1480417,0.00002186363,0.8487635,0.0001015829,0.0001060365,0.0001220356,0.00002293667,0.00004393182,0.002776394],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03217145,"threshold_uncertainty_score":0.471857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0334455923671907,"score_gpt":0.2990229551568679,"score_spread":0.2655773627896773,"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."}}