{"id":"W4393817026","doi":"10.5281/zenodo.10119842","title":"HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005480369,0.002132482,0.001113954,0.001797211,0.0007988277,0.003054096,0.005008711,0.002075961,0.005887783],"category_scores_gemma":[0.0296024,0.001318438,0.003529833,0.001039425,0.001715413,0.005803429,0.0046924,0.004783224,0.004862459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001834466,"about_ca_system_score_gemma":0.00492216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006573105,"about_ca_topic_score_gemma":0.01326247,"domain_scores_codex":[0.995949,0.001485655,0.0004379543,0.0009731348,0.0009963835,0.0001578751],"domain_scores_gemma":[0.9814802,0.01062421,0.0007956583,0.005050475,0.001667468,0.0003819977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009646445,0.0008705715,0.01147209,0.003130283,0.0005510239,0.0007363143,0.002435857,0.1724423,0.04634445,0.03455941,0.09425967,0.6322334],"study_design_scores_gemma":[0.0002104954,0.000242707,0.0008403066,0.0001584508,0.00009843428,0.000201524,0.0002419494,0.8534603,0.04410791,0.03185289,0.06847055,0.0001145116],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.03536032,0.001115261,0.759478,0.001570827,0.0003793204,0.0009284943,0.005875354,0.1909232,0.004369183],"genre_scores_gemma":[0.1139551,0.0004496207,0.8551943,0.0009554498,0.00007100466,0.001110044,0.01558693,0.009553391,0.00312416],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.006573105,"threshold_uncertainty_score":0.02898329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02773555981106834,"score_gpt":0.2982344168912174,"score_spread":0.2704988570801491,"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."}}