{"id":"W4393810658","doi":"10.5281/zenodo.5113560","title":"The Oberwolfach Steel-Profile benchmark revisited","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Metallurgy and Material Forming","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Computer science; Parallel computing; Geography; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000744075,0.000251157,0.0002496646,0.0001320145,0.002268547,0.001343052,0.001300464,0.0001783455,0.03912977],"category_scores_gemma":[0.0005143173,0.0002202826,0.00008695645,0.0004258145,0.00009322357,0.0001490822,0.001083439,0.0005524884,0.01317288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248562,"about_ca_system_score_gemma":0.000004110457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009070043,"about_ca_topic_score_gemma":6.901839e-7,"domain_scores_codex":[0.9981866,0.0002756502,0.0003782681,0.0003438758,0.0003698811,0.0004456806],"domain_scores_gemma":[0.9985338,0.00004016249,0.00009034008,0.0009080028,0.0002851014,0.00014262],"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":[0.00001098654,0.00001436441,6.184828e-9,0.0002773807,0.00008097432,0.00002258481,0.00003090423,0.00004143595,0.0006872301,0.0002285727,0.9859746,0.01263095],"study_design_scores_gemma":[0.0001364568,0.000036446,0.00000663649,0.00009291803,0.00003493723,0.00007242968,0.00004872979,0.000130595,0.0002791147,0.00002331833,0.9988963,0.0002420894],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001675304,0.0009742593,0.0001294298,0.00007106882,0.0008853939,0.0004554582,0.9556221,0.0008224332,0.04087237],"genre_scores_gemma":[0.0002047102,0.001900989,0.00004905344,0.00003953695,0.0003651869,9.478109e-8,0.9951427,0.001099526,0.001198188],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03967418,"threshold_uncertainty_score":0.9996936,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02156782652738092,"score_gpt":0.2217678611487497,"score_spread":0.2002000346213688,"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."}}