{"id":"W6931827081","doi":"10.5281/zenodo.7790046","title":"UofT-EcoSystem/hotline: Final release for MLSys artifact evaluation","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Multidisciplinary Science and Engineering Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artifact (error); Feature (linguistics); Calibration; Process (computing)","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","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009491323,0.0002976947,0.000394396,0.001425157,0.001690052,0.001790224,0.00282943,0.0002278375,0.05024097],"category_scores_gemma":[0.01359887,0.0002607029,0.0001863965,0.001875117,0.0001510115,0.0003290506,0.001203865,0.0003854401,0.04906866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003101518,"about_ca_system_score_gemma":0.00003548108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003758553,"about_ca_topic_score_gemma":0.00001741793,"domain_scores_codex":[0.9938306,0.0005799172,0.0006572231,0.001164631,0.003048439,0.0007191741],"domain_scores_gemma":[0.9961657,0.0003796461,0.0003290493,0.001305247,0.001450235,0.0003701462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000388858,0.00004944701,0.000002630717,0.00005830857,0.00002663961,0.000008106345,0.0002039663,0.0009113544,0.000153493,0.0002715435,0.8389434,0.1593322],"study_design_scores_gemma":[0.0005389446,0.0002208233,0.00021232,0.0001313883,0.00001998517,0.00002326521,0.0002618637,0.04162779,0.00002973906,0.0005971437,0.9560512,0.000285521],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.003864363,0.0005918394,0.04186948,0.00296013,0.00273455,0.007190574,0.004770156,0.008090081,0.9279288],"genre_scores_gemma":[0.07893687,0.0003269826,0.001347315,0.00008353683,0.001904716,0.000003764784,0.004183641,0.02399329,0.8892199],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1590467,"threshold_uncertainty_score":0.9999845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2546263431628282,"score_gpt":0.4002384161352245,"score_spread":0.1456120729723963,"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."}}