{"id":"W3203911409","doi":"10.1145/3465403","title":"CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Programming language; Semantics (computer science); Information retrieval; Natural language processing","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":[0.000974135,0.0001504024,0.00033362,0.0001966804,0.00008455741,0.00003254388,0.000318374,0.000107159,0.00002480728],"category_scores_gemma":[0.0009481684,0.0001510317,0.0001158291,0.0004236758,0.00003593657,0.00008687891,0.00002868154,0.000319147,0.000002242853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002007638,"about_ca_system_score_gemma":0.00008877402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003765302,"about_ca_topic_score_gemma":0.00001431011,"domain_scores_codex":[0.9986451,0.0002875068,0.0002834687,0.0003753559,0.0001778073,0.0002307199],"domain_scores_gemma":[0.9970193,0.002028733,0.00006268761,0.000744144,0.00005162985,0.00009350573],"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":[0.00005660092,0.0003156487,0.001639192,0.0003383831,0.0004429267,0.0002455332,0.001580957,0.8283153,0.02255533,0.001822114,0.00009979725,0.1425882],"study_design_scores_gemma":[0.00118778,0.0004315677,0.002174575,0.0003798483,0.0002894972,0.0002105312,0.000197863,0.8641158,0.1267686,0.0009961968,0.00248377,0.0007638988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02684014,0.00007188562,0.972142,0.0004359035,0.0002754653,0.00003149114,0.00003562636,0.0001624911,0.00000496435],"genre_scores_gemma":[0.2273965,0.00006392599,0.7723173,0.000123132,0.00001837701,0.000006135713,0.000008211489,0.00001338254,0.00005304265],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2005563,"threshold_uncertainty_score":0.6158893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08444068339043621,"score_gpt":0.3254469426044706,"score_spread":0.2410062592140344,"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."}}