{"id":"W4399479580","doi":"10.1007/978-3-031-62697-5_9","title":"The Concurrent Calculi Formalisation Benchmark","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Benchmark (surveying); Programming language; Parallel computing; Geology","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":[0.003069527,0.0008193362,0.0007859426,0.001604995,0.001685849,0.003418031,0.002808114,0.001462465,0.01463585],"category_scores_gemma":[0.01719576,0.0004767592,0.0007684217,0.002407639,0.001588355,0.003829328,0.002234606,0.002435892,0.002263733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002122059,"about_ca_system_score_gemma":0.004427814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008353546,"about_ca_topic_score_gemma":0.01366401,"domain_scores_codex":[0.9955284,0.001121895,0.0002419555,0.0005806446,0.001997807,0.0005292765],"domain_scores_gemma":[0.9861993,0.00725593,0.0003373143,0.003188745,0.002634158,0.0003846822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001036151,0.001125652,0.001290752,0.0009842933,0.00008013906,0.0002975866,0.0005404975,0.07357802,0.008395634,0.6556717,0.05431781,0.2026818],"study_design_scores_gemma":[0.0006447893,0.0002617846,0.0006600001,0.0003042127,0.0000884181,0.0002835292,0.0003870559,0.2821804,0.03901418,0.5329343,0.14315,0.00009135049],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2822934,0.004274007,0.3429185,0.00529164,0.001775749,0.0008789279,0.008295936,0.02427837,0.3299936],"genre_scores_gemma":[0.742071,0.0008112263,0.2049366,0.0006498029,0.0003393722,0.0004796722,0.007109668,0.003276743,0.04032579],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01463585,"threshold_uncertainty_score":0.04896182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02151553304512763,"score_gpt":0.2556730972718895,"score_spread":0.2341575642267618,"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."}}