{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004473238,0.002796678,0.001295869,0.008696754,0.002110081,0.002123778,0.002953367,0.002679536,0.004101353],"category_scores_gemma":[0.03155835,0.0008197028,0.002352061,0.003447598,0.001615833,0.005551907,0.004983794,0.002849394,0.002916004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002053105,"about_ca_system_score_gemma":0.0037702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02632981,"about_ca_topic_score_gemma":0.05241246,"domain_scores_codex":[0.9931105,0.00145704,0.0004349757,0.002185591,0.002425434,0.0003864954],"domain_scores_gemma":[0.9862316,0.007161349,0.00119213,0.002803186,0.002125774,0.0004859848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001563999,0.0007611581,0.02792386,0.002811779,0.0004816199,0.003040181,0.005110279,0.05347438,0.04961157,0.01426974,0.08702515,0.7539263],"study_design_scores_gemma":[0.0002922559,0.0002604919,0.01573789,0.0004450931,0.0002902934,0.001008568,0.001974946,0.76394,0.05160142,0.05887957,0.1051063,0.0004632127],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08997626,0.00166789,0.80845,0.002548062,0.0008141303,0.001620858,0.02002621,0.06303087,0.01186573],"genre_scores_gemma":[0.3315767,0.0007257829,0.6144601,0.001685774,0.0004139683,0.001519361,0.03289322,0.004389375,0.01233584],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02632981,"threshold_uncertainty_score":0.05235314,"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."}}