{"id":"W2966091573","doi":"10.1145/3341702","title":"From high-level inference algorithms to efficient code","year":2019,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Defense Advanced Research Projects Agency; Lilly Endowment; Eli Lilly and Company; National Science Foundation","keywords":"Computer science; Probabilistic logic; Inference; Code (set theory); Theoretical computer science; Algorithm; Compiler; Programming language; Artificial intelligence","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":[0.0003327897,0.0002064891,0.0002445861,0.00009550452,0.00008530119,0.0002515684,0.004188361,0.00008275209,0.00001107812],"category_scores_gemma":[0.0007198129,0.0001435507,0.00008425776,0.0005136628,0.00004492169,0.0001492132,0.001591799,0.0002352942,0.000104586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003849489,"about_ca_system_score_gemma":0.00003901453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002662461,"about_ca_topic_score_gemma":0.000002870844,"domain_scores_codex":[0.9982812,0.00001004472,0.0002629141,0.000548008,0.0005247632,0.0003730849],"domain_scores_gemma":[0.998444,0.0001424417,0.0001827759,0.0008809248,0.0002373574,0.0001124675],"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":[0.00008108623,0.0006666022,0.01138802,0.0002161591,0.0001337193,0.000004759341,0.01812307,0.001846179,0.07152527,0.1527429,0.001763242,0.741509],"study_design_scores_gemma":[0.002336217,0.002065317,0.04147554,0.002877325,0.0001087824,0.00002172216,0.004573043,0.07658753,0.8046674,0.05857511,0.004189826,0.002522215],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9694955,0.00006705768,0.02603428,0.002861861,0.0003652665,0.0004414915,0.00001795245,0.000246655,0.0004699156],"genre_scores_gemma":[0.8140855,0.000001751877,0.185196,0.0003323484,0.00006493243,0.00002825057,0.000001087534,0.00001317023,0.0002769401],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7389868,"threshold_uncertainty_score":0.7783086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02762690857749259,"score_gpt":0.2898079864273575,"score_spread":0.2621810778498649,"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."}}