{"id":"W6912673711","doi":"10.5281/zenodo.8335989","title":"Raw Data for benchmarking structure based domain annotation","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Raw data; Domain (mathematical analysis); Benchmarking; Annotation; Scripting language; Data structure","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00513202,0.003888662,0.001874113,0.005879993,0.002198624,0.004004553,0.002949903,0.001788494,0.080457],"category_scores_gemma":[0.02573276,0.001305344,0.001988037,0.006489231,0.0008159466,0.003048746,0.004413456,0.003627663,0.1235564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555562,"about_ca_system_score_gemma":0.003373451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005768538,"about_ca_topic_score_gemma":0.006192814,"domain_scores_codex":[0.9940392,0.001188393,0.0008316956,0.001539283,0.001949365,0.0004519559],"domain_scores_gemma":[0.9877659,0.003358627,0.0005293469,0.00474931,0.002928479,0.0006683493],"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":[0.0007931932,0.0003141036,0.003304728,0.002202308,0.0001719733,0.0002934832,0.0003957011,0.003427381,0.008868136,0.003800877,0.9353008,0.04112731],"study_design_scores_gemma":[0.0004556049,0.0002465022,0.01322605,0.001038669,0.0002334568,0.0007419332,0.0007764911,0.02781747,0.0456244,0.021779,0.8877586,0.0003018107],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006682264,0.0004967492,0.03496022,0.0003131641,0.0005226741,0.0005520307,0.7165681,0.2242853,0.01561945],"genre_scores_gemma":[0.009332164,0.0002165422,0.02571975,0.0002072332,0.0000342677,0.0008370593,0.9370974,0.02318907,0.00336654],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.080457,"threshold_uncertainty_score":0.2691555,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04947144449278982,"score_gpt":0.2725789662523704,"score_spread":0.2231075217595806,"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."}}