{"id":"W4404781665","doi":"10.18653/v1/2024.findings-emnlp.192","title":"HoneyComb: A Flexible LLM-Based Agent System for Materials Science","year":2024,"lang":"en","type":"article","venue":"","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Honeycomb; Computer science; Materials science; Composite material","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":[],"consensus_categories":[],"category_scores_codex":[0.0003110711,0.00008466688,0.00009441538,0.0001354703,0.00008931741,0.0003317722,0.0001116868,0.00002614243,0.00004641954],"category_scores_gemma":[0.000009765479,0.0000671943,0.00002585997,0.0002609339,0.00002478124,0.000121761,0.00001154066,0.00002992286,0.00008476656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001001519,"about_ca_system_score_gemma":0.00004656074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009386007,"about_ca_topic_score_gemma":6.654091e-7,"domain_scores_codex":[0.9993812,0.000002784953,0.0001272056,0.0001538487,0.0001110534,0.0002238398],"domain_scores_gemma":[0.9997962,0.00002465179,0.000005935676,0.00009934437,0.00002052214,0.0000533464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004927399,0.000007996393,0.00000406806,0.004134954,0.00001314348,0.000006610287,0.0001198812,0.02542466,0.9503905,0.01158777,0.005574927,0.002730544],"study_design_scores_gemma":[0.00009931519,0.00001964148,0.000007259651,0.0003422277,0.000008733274,0.000004482887,0.00004584548,0.2494357,0.7447755,0.0000614551,0.005075052,0.0001247351],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7572203,0.0008483093,0.2059139,0.0001595416,0.005469189,0.0004158697,0.00004177071,0.005132401,0.0247987],"genre_scores_gemma":[0.9954941,9.465994e-7,0.003001838,0.00001839327,0.0001343854,0.00004350491,0.000003750506,0.00002170611,0.001281381],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2382738,"threshold_uncertainty_score":0.3199287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0217652522255466,"score_gpt":0.2610658024384261,"score_spread":0.2393005502128795,"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."}}