{"id":"W4400519874","doi":"10.1145/3641525.3663617","title":"Computational Experiment Comprehension using Provenance Summarization","year":2024,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Provenance; Natural language processing; Comprehension; Artificial intelligence; Information retrieval; Programming language; Geology; Paleontology","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001462708,0.00007958707,0.00009456713,0.0002490325,0.0001626783,0.001110211,0.0003217356,0.00001908396,0.0004585124],"category_scores_gemma":[0.0001654426,0.00005565921,0.00004993284,0.0009031353,0.00004371688,0.0003419747,0.0002841206,0.00004429196,0.000528713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000478926,"about_ca_system_score_gemma":0.00005230897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002675365,"about_ca_topic_score_gemma":0.000001288326,"domain_scores_codex":[0.9977001,0.0000660179,0.0003725682,0.0006067606,0.001114796,0.0001397334],"domain_scores_gemma":[0.9990031,0.0003745193,0.00004653105,0.0003928415,0.0001341383,0.00004882867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001055828,0.00009586873,0.0005803442,0.00001811681,0.00002105171,0.00002250129,0.0006862845,0.4262361,0.002371835,0.150199,0.1465778,0.2731805],"study_design_scores_gemma":[0.00005547605,0.000009842587,0.0003958779,0.00002802808,0.000002879622,0.000003703168,0.0001799036,0.9264116,0.0002582513,0.01889476,0.05368541,0.00007432282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05644916,0.0002336095,0.9331189,0.0005324765,0.002114468,0.0001549108,0.000007121066,0.0001789772,0.007210344],"genre_scores_gemma":[0.9676362,8.473599e-7,0.02814363,0.0001484436,0.00006232703,0.000002227626,0.00002420696,0.000005714866,0.003976422],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.911187,"threshold_uncertainty_score":0.9999267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2222819554899719,"score_gpt":0.4449581537560797,"score_spread":0.2226761982661078,"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."}}