{"id":"W6892996724","doi":"10.5281/zenodo.13645317","title":"Improving gyrochronology: An expanded benchmark data set and enhanced age inference framework","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Stellar, planetary, and galactic studies","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Inference; Set (abstract data type); Data set; Cluster (spacecraft); Bayesian inference; Field (mathematics); Bayesian probability","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":[0.01549855,0.001454017,0.001482954,0.003313037,0.001011961,0.002931935,0.003928563,0.001987925,0.002147737],"category_scores_gemma":[0.03646104,0.0005740421,0.001671581,0.00234103,0.0009540147,0.003420525,0.003094644,0.002592925,0.001576424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001659017,"about_ca_system_score_gemma":0.002257532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0203403,"about_ca_topic_score_gemma":0.01896863,"domain_scores_codex":[0.9953265,0.001759005,0.0002772635,0.001239478,0.001150369,0.0002473428],"domain_scores_gemma":[0.9845797,0.004944671,0.0007295999,0.005138615,0.004152022,0.0004554995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008973813,0.0005938032,0.1064765,0.0006927871,0.0009240774,0.0002956138,0.0002877567,0.5238152,0.008293617,0.02556013,0.03916011,0.293003],"study_design_scores_gemma":[0.0001296462,0.0001533098,0.01853304,0.00008177711,0.0001101387,0.000230645,0.00005994454,0.9174531,0.009432732,0.02872354,0.02500351,0.00008868206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1708238,0.002717946,0.7708001,0.00151145,0.0004139666,0.0004060747,0.03321493,0.01392409,0.006187568],"genre_scores_gemma":[0.3809248,0.0005961377,0.5395761,0.0005426891,0.0003141161,0.0003194925,0.07402308,0.001259202,0.002444388],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0203403,"threshold_uncertainty_score":0.08196515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04713610414058526,"score_gpt":0.2901879867848389,"score_spread":0.2430518826442536,"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."}}