{"id":"W3016194403","doi":"10.1007/978-3-030-45442-5_6","title":"Reproducibility is a Process, Not an Achievement: The Replicability of IR Reproducibility Experiments","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reproducibility; Replicate; Computer science; Process (computing); Set (abstract data type); Artificial intelligence; Data science; Mathematics; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06121498,0.0006162978,0.001054172,0.0004759089,0.0005793464,0.000866577,0.008984479,0.000206724,0.0002465476],"category_scores_gemma":[0.02017589,0.0003965481,0.0003119876,0.002143653,0.002871813,0.0006760036,0.004666566,0.0008728793,0.00005398156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002264771,"about_ca_system_score_gemma":0.0005981151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001362247,"about_ca_topic_score_gemma":0.00006782621,"domain_scores_codex":[0.9734653,0.0003931518,0.002542354,0.01746251,0.005459094,0.0006775919],"domain_scores_gemma":[0.9631228,0.001453734,0.00133646,0.03263018,0.001186156,0.0002706835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001748836,0.0005268793,0.007555669,0.0001293116,0.00003926787,0.0000127724,0.009104019,0.008795073,0.0008126025,0.001256658,0.0007187159,0.9708741],"study_design_scores_gemma":[0.0006899012,0.0008252684,0.02474503,0.000408294,0.00007685531,0.00001383625,0.00004036308,0.1991796,0.04798879,0.710035,0.01436557,0.001631534],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1509694,0.0008060772,0.7940971,0.03617447,0.007145898,0.005216294,0.0003837345,0.0004103668,0.004796674],"genre_scores_gemma":[0.9813382,0.000008176965,0.01435691,0.003167929,0.0004937861,0.00002987505,0.0000161816,0.00003086894,0.0005580699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9692426,"threshold_uncertainty_score":0.9998487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1470045001085528,"score_gpt":0.3877759823654807,"score_spread":0.2407714822569278,"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."}}