{"id":"W4411450091","doi":"10.1145/3715724","title":"CKTyper: Enhancing Type Inference for Java Code Snippets by Leveraging Crowdsourcing Knowledge in Stack Overflow","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on software engineering.","topic":"Software Engineering Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province","keywords":"Snippet; Computer science; Crowdsourcing; Context (archaeology); Code (set theory); Inference; Set (abstract data type); Information retrieval; Type inference; Java; Source code; World Wide Web; Artificial intelligence; Programming language","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007450132,0.00031295,0.0003756256,0.0004510444,0.0001048053,0.000156774,0.003480715,0.0001396196,0.000003492653],"category_scores_gemma":[0.02186193,0.0002850567,0.000110767,0.001610135,0.00003470236,0.0003799441,0.001463847,0.0005008294,0.000006777636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002965053,"about_ca_system_score_gemma":0.0001624267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001737667,"about_ca_topic_score_gemma":0.000003658268,"domain_scores_codex":[0.9979707,0.000007471716,0.0004330966,0.0005828876,0.0003720379,0.0006337888],"domain_scores_gemma":[0.9965248,0.00202112,0.0001067808,0.0008319468,0.0004259704,0.00008935059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003421704,0.0009615664,0.5372317,0.009145144,0.0005048105,0.000007985138,0.00859932,0.08701733,0.2032818,0.02815873,0.1020873,0.02266208],"study_design_scores_gemma":[0.00322919,0.0005368048,0.07127476,0.006846765,0.00005165596,0.0000140931,0.0001550731,0.1879383,0.6941187,0.002429142,0.03149749,0.001907993],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7036215,0.001018782,0.291643,0.0005169148,0.001585866,0.0007578067,0.0000174301,0.0007510412,0.0000876227],"genre_scores_gemma":[0.9539075,0.00002157916,0.04533779,0.00007974736,0.00006482063,0.00008047897,0.000001883672,0.00004766276,0.0004584809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4908369,"threshold_uncertainty_score":0.9999602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01723503358432096,"score_gpt":0.2818270580510308,"score_spread":0.2645920244667099,"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."}}