{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004526831,0.0003028566,0.0004544824,0.0006724236,0.002641348,0.001563086,0.0032129,0.0001671088,0.008831959],"category_scores_gemma":[0.003195677,0.0003001073,0.00006413218,0.001062055,0.0008108161,0.0006726487,0.0029416,0.0002581135,0.005254989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001845302,"about_ca_system_score_gemma":0.00003791553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001459377,"about_ca_topic_score_gemma":0.000001141822,"domain_scores_codex":[0.996107,0.0004486534,0.0006357672,0.0009623301,0.001040718,0.0008055239],"domain_scores_gemma":[0.9969553,0.00006909057,0.0007712658,0.0009813592,0.001044856,0.000178067],"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":[0.00007482719,0.00006155071,3.44385e-8,0.00050846,0.000008423106,0.000008586417,0.0004047167,0.000472433,0.3262902,0.0005766389,0.6708659,0.0007282848],"study_design_scores_gemma":[0.0008935109,0.0004401881,0.00002339879,0.0003647402,0.00004916254,0.000103437,0.0004116113,0.0017124,0.08222074,0.0004199516,0.9128259,0.0005349402],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02332281,0.00004080148,0.001422777,0.00009107137,0.001181759,0.001138595,0.9716774,0.0007194968,0.0004052437],"genre_scores_gemma":[0.01385608,0.00004943735,0.002484414,0.00006014771,0.000491031,0.00000123169,0.9816297,0.001192587,0.0002353875],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2440694,"threshold_uncertainty_score":0.9999451,"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."}}