{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001366415,0.0004249117,0.0003329512,0.0003139483,0.00051581,0.001722977,0.003091506,0.000243483,0.000009016392],"category_scores_gemma":[0.00005579306,0.0002716095,0.0001674946,0.0004959554,0.0006899634,0.0004630365,0.001207975,0.000732351,0.0001731702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002946996,"about_ca_system_score_gemma":0.0004062101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003651746,"about_ca_topic_score_gemma":0.0001536894,"domain_scores_codex":[0.9966511,0.00003153027,0.0005235415,0.001121878,0.001010929,0.0006610544],"domain_scores_gemma":[0.9978789,0.0004262802,0.0002341013,0.001119177,0.0002014177,0.0001401074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[6.143888e-7,0.000004473121,0.000007251712,0.00002540885,0.00000744399,0.00002346507,0.0004792526,0.0005245107,0.000003686429,0.556922,0.00007644493,0.4419254],"study_design_scores_gemma":[0.0001145085,0.0001416307,0.00001978383,0.00008251383,0.000009700726,0.00007887611,4.255446e-7,0.2530643,0.0001675316,0.6051277,0.1407303,0.0004627451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000004474336,0.003258874,0.9685253,0.0009569082,0.009160021,0.0004657205,0.000001432541,0.0001983327,0.01742894],"genre_scores_gemma":[0.9695244,0.0002580312,0.02096882,0.00103861,0.002295242,0.00005889034,0.00001679089,0.00005964325,0.005779533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.96952,"threshold_uncertainty_score":0.9999736,"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."}}