{"id":"W1989059628","doi":"10.1145/859670.859699","title":"Grammar-based compression of interpreted code","year":2003,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Grammar; Programming language; Code (set theory); Compression (physics); Natural language processing; Artificial intelligence; Linguistics","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0002665095,0.00006969865,0.0001277009,0.00004994549,0.0001553564,0.00001768049,0.03114397,0.00003606434,0.000007440908],"category_scores_gemma":[0.002311691,0.00004752602,0.00007667007,0.0003214072,0.0001877164,0.0001448519,0.01397529,0.0001286857,0.000003236254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001288042,"about_ca_system_score_gemma":0.00006617222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003297819,"about_ca_topic_score_gemma":0.00000744733,"domain_scores_codex":[0.9990739,0.0002981041,0.0002586685,0.000118619,0.0001621653,0.00008854867],"domain_scores_gemma":[0.9676471,0.0003840601,0.0002306054,0.03158198,0.0001278373,0.00002835665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006100759,0.002650859,0.0164091,0.0001882666,0.0001445914,7.680661e-7,0.002540975,0.003037428,0.134504,0.6711439,0.1072823,0.06203682],"study_design_scores_gemma":[0.001533177,0.0001497669,0.01121404,0.0009230374,0.00004389619,0.000008450505,0.0001179353,0.390558,0.2618478,0.2391415,0.09404222,0.0004201698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03609077,0.004243105,0.9117581,0.03117161,0.0009405437,0.0009755457,0.0001290088,0.0002551003,0.01443619],"genre_scores_gemma":[0.609017,0.00002528916,0.3908584,0.00006522793,0.000001398871,0.000005901084,0.000004908759,0.000003149117,0.00001879162],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5729262,"threshold_uncertainty_score":0.9939995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04484810471989512,"score_gpt":0.3007764249463846,"score_spread":0.2559283202264895,"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."}}