{"id":"W4392266008","doi":"10.1109/cgo57630.2024.10444879","title":"Latent Idiom Recognition for a Minimalist Functional Array Language Using Equality Saturation","year":2024,"lang":"en","type":"article","venue":"","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; ENCODE; Compiler; Natural language processing; Set (abstract data type); Artificial intelligence; Speedup; Programming language; Language model; Minimalist program; Matching (statistics); Parallel computing; Syntax","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003682287,0.00008276865,0.00007561318,0.0001005388,0.0001084654,0.0003139806,0.000120883,0.00005018814,0.00002259765],"category_scores_gemma":[0.00003314247,0.00007298623,0.00006914778,0.0002378874,0.00001217304,0.0003701653,0.00003091526,0.0000568564,0.00001618233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004447403,"about_ca_system_score_gemma":0.00005606138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003362786,"about_ca_topic_score_gemma":0.00000442953,"domain_scores_codex":[0.9992369,0.00004439742,0.00018058,0.0002798467,0.0001326733,0.000125604],"domain_scores_gemma":[0.999601,0.00009125693,0.00003708844,0.0001442546,0.00009319591,0.00003319487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001575236,0.0004121534,0.0002569545,0.0007824046,0.0002728819,0.00002909582,0.008016629,0.02223122,0.2639231,0.2848446,0.05159041,0.367483],"study_design_scores_gemma":[0.000114067,0.00004256768,0.0001217243,0.00005411197,0.000008878127,0.0000170817,0.00001972284,0.9634191,0.02915817,0.005549549,0.001330033,0.0001650039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0053848,0.0001442493,0.991053,0.000450254,0.0004306274,0.0001722958,0.000007903822,0.0009583639,0.001398523],"genre_scores_gemma":[0.4421042,0.000004000427,0.5568812,0.0002470301,0.000172165,0.0000194256,0.00006468278,0.000007157839,0.0005001356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9411879,"threshold_uncertainty_score":0.3027722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08493101923587307,"score_gpt":0.3235527454138313,"score_spread":0.2386217261779583,"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."}}