{"id":"W3121922233","doi":"10.7287/peerj.preprints.1597","title":"Multi-token code suggestions using statistical language models","year":2015,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Naturalness; Security token; Computer science; Surprise; Programmer; Code (set theory); Metric (unit); Programming language; Simple (philosophy); Natural language processing; Psychology; Operating system","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":[0.003447432,0.001174595,0.0007214476,0.001173448,0.0005878244,0.001519067,0.002172567,0.001004438,0.004583209],"category_scores_gemma":[0.02331807,0.0006096131,0.0008971594,0.0006933893,0.0006792027,0.003084518,0.001170115,0.002099502,0.002367064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007688602,"about_ca_system_score_gemma":0.00186555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00449204,"about_ca_topic_score_gemma":0.01273077,"domain_scores_codex":[0.9975722,0.001204328,0.0001120006,0.0004894623,0.0005206307,0.0001012801],"domain_scores_gemma":[0.9772379,0.01727384,0.001260081,0.001776489,0.002083175,0.0003684671],"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":[0.002487016,0.0005519444,0.0157221,0.001103788,0.0003074935,0.0013726,0.001900549,0.2608975,0.03667064,0.03217886,0.02998894,0.6168185],"study_design_scores_gemma":[0.00003788641,0.00006738034,0.000362945,0.00001300759,0.00001864656,0.00009180424,0.0000536505,0.9794728,0.006582526,0.01034676,0.002920289,0.00003227612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04116384,0.0001518698,0.9202168,0.0007077518,0.0001392836,0.00009880037,0.0005363196,0.03587763,0.001107677],"genre_scores_gemma":[0.3207584,0.00009259662,0.6728812,0.0002254675,0.00007382813,0.0001295872,0.0008558543,0.002229786,0.002753171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004583209,"threshold_uncertainty_score":0.01823199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135364606180074,"score_gpt":0.3599472469151834,"score_spread":0.246410786297176,"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."}}