{"id":"W6949012962","doi":"10.5281/zenodo.10667878","title":"Artifacts for the paper \"Concretization of Abstract Traffic Scene Specifications Using Metaheuristic Search\"","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"History of Medicine and Tropical Health","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Overlay; Segmentation; Ground truth; Image segmentation; Semantics (computer science); Image (mathematics)","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":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006697365,0.0001864058,0.0002633506,0.0002614134,0.002402395,0.0004626901,0.0007465929,0.00008201221,0.03895576],"category_scores_gemma":[0.0004875571,0.0001444705,0.0001138573,0.0001501196,0.0005877907,0.0001315622,0.0001971944,0.0004686113,0.007123938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001576188,"about_ca_system_score_gemma":0.00003306796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001400046,"about_ca_topic_score_gemma":0.00002366938,"domain_scores_codex":[0.9982622,0.0001581135,0.0004695658,0.0003588598,0.0004455535,0.0003056969],"domain_scores_gemma":[0.9983378,0.0001685108,0.0001824376,0.0005305852,0.0006471243,0.0001335252],"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":[0.0000444226,0.00007383213,7.887158e-9,0.0006633461,0.00008476511,0.000003642283,0.001383002,0.00008726671,0.0000407817,0.002703055,0.9806238,0.01429204],"study_design_scores_gemma":[0.0001989259,0.0001711171,0.000009499942,0.0001406794,0.0001922139,0.00001068221,0.0006152079,0.0005477318,0.000005827112,0.00006192515,0.997908,0.0001381835],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0002870572,0.001175577,0.0003729493,0.001727137,0.0007536997,0.00129695,0.9855874,0.0002455928,0.008553598],"genre_scores_gemma":[0.01652787,0.0006537898,0.00006839312,0.0002392523,0.001741742,3.063195e-7,0.9786311,0.0008824308,0.001255076],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03183182,"threshold_uncertainty_score":0.9988964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1726080378476471,"score_gpt":0.294815852949452,"score_spread":0.1222078151018049,"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."}}