{"id":"W4386622318","doi":"10.5281/zenodo.8335990","title":"Raw Data for benchmarking structure based domain annotation","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Benchmarking; Raw data; Annotation; Computer science; Domain (mathematical analysis); Information retrieval; Artificial intelligence; Business; Mathematics; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0007387255,0.00008673011,0.00007685483,0.000249791,0.001594197,0.0004995123,0.002367222,0.00005707908,0.0006965178],"category_scores_gemma":[0.0003205893,0.00009127863,0.00002123632,0.0009124555,0.00006508172,0.0004395272,0.001367069,0.0001423519,0.0005813215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006386881,"about_ca_system_score_gemma":0.00001245694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001736928,"about_ca_topic_score_gemma":2.465739e-7,"domain_scores_codex":[0.9987537,0.0001255494,0.0001551847,0.0004627944,0.0002459046,0.0002568827],"domain_scores_gemma":[0.9986491,0.0000677846,0.00007834097,0.0008718464,0.000269995,0.00006297982],"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":[0.00002046072,0.00009763363,0.00001608562,0.00007711945,0.0000388329,0.000007460545,0.000658085,0.0007065996,0.007214407,0.2094605,0.5371217,0.2445811],"study_design_scores_gemma":[0.0003573177,0.0001044253,0.001468739,0.00001774713,0.000004386181,0.00001379971,0.0001451702,0.06172808,0.0005215502,0.0114173,0.924085,0.000136474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0166646,0.00002907079,0.9604629,0.01342219,0.0004524707,0.0007188168,0.0005866576,0.002439985,0.005223351],"genre_scores_gemma":[0.9145432,0.00001490711,0.06627494,0.0004569582,0.0002874396,2.377399e-7,0.01758078,0.0005262785,0.0003153266],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8978785,"threshold_uncertainty_score":0.9997056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06301138541023635,"score_gpt":0.3067664919215459,"score_spread":0.2437551065113096,"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."}}