{"id":"W4390527993","doi":"10.48550/arxiv.2312.17682","title":"Latent Idiom Recognition for a Minimalist Functional Array Language using Equality Saturation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; ENCODE; Compiler; Set (abstract data type); Natural language processing; Artificial intelligence; Speedup; Programming language; Language model; Minimalist program; Parallel computing; Syntax","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004770063,0.0002213639,0.000229489,0.0002689229,0.000232303,0.0001722383,0.0005465811,0.0002465225,0.000007351869],"category_scores_gemma":[0.00007493654,0.0002667569,0.0002052287,0.000436441,0.00004183297,0.0002837156,0.0004359769,0.0002543138,0.00002435072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001900462,"about_ca_system_score_gemma":0.0001567118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001808526,"about_ca_topic_score_gemma":0.00002696012,"domain_scores_codex":[0.9984213,0.0001536124,0.0002395272,0.0008446333,0.00009929174,0.0002416167],"domain_scores_gemma":[0.9986378,0.0001390061,0.0003207125,0.0005385858,0.0002843546,0.00007952857],"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":[0.0001235134,0.0001415765,0.0006704028,0.0002503946,0.0001547363,0.00004707474,0.000815888,0.9685287,0.001624623,0.02455472,0.001706811,0.001381498],"study_design_scores_gemma":[0.000321736,0.00003638004,0.0006350108,0.0001156176,0.00004788151,0.000003225229,0.00004094007,0.9683074,0.001444712,0.02859855,0.00007269596,0.0003758982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06634238,0.00002042996,0.9313039,0.00009550183,0.0006726042,0.0003859323,0.00005656662,0.000915029,0.0002076577],"genre_scores_gemma":[0.9162337,0.00002914228,0.08223722,0.00008718972,0.0001797797,0.000004230985,0.0003531031,0.00002132101,0.0008542946],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8498914,"threshold_uncertainty_score":0.9999785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2516276083190059,"score_gpt":0.2523807478597557,"score_spread":0.0007531395407498476,"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."}}