{"id":"W4308498506","doi":"10.1016/j.conbuildmat.2022.129534","title":"Compressive strength prediction of one-part alkali activated material enabled by interpretable machine learning","year":2022,"lang":"en","type":"article","venue":"Construction and Building Materials","topic":"Concrete and Cement Materials Research","field":"Engineering","cited_by":83,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"National Natural Science Foundation of China","keywords":"Compressive strength; Durability; Computer science; Machine learning; Process engineering; Geopolymer; Artificial intelligence; Materials science; Composite material; Engineering; Database","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000301977,0.0001623103,0.0003281659,0.0001360006,0.0002373191,0.0001242417,0.0001111025,0.00005829818,0.006433682],"category_scores_gemma":[0.00002125625,0.0001782905,0.00002652015,0.0001214997,0.00007632164,0.0001873213,0.000175765,0.0001360836,0.000001812749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006360055,"about_ca_system_score_gemma":0.00001494863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000959907,"about_ca_topic_score_gemma":4.028425e-7,"domain_scores_codex":[0.9987152,0.0001942083,0.0004082581,0.0002127145,0.0002247808,0.0002448802],"domain_scores_gemma":[0.9996231,0.00003285237,0.0001225941,0.0001233994,0.00003921952,0.00005886334],"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":[0.0001786874,0.00001359544,0.0002214799,0.0001471422,0.00008667933,9.157538e-7,0.00008123897,0.000357099,0.9966065,0.0001427218,0.0005486566,0.001615259],"study_design_scores_gemma":[0.0006258023,0.000101749,0.00003286811,0.00005055256,0.00002786872,0.00002355653,0.0001836493,0.0009674708,0.9848549,0.00004921957,0.01294374,0.000138606],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961619,0.00009690749,0.0002199959,0.00001674002,0.001633993,0.0002265474,0.001175495,0.0002183025,0.0002501373],"genre_scores_gemma":[0.9987754,0.0002316469,0.0002941516,0.000005888962,0.000109514,0.00006737116,0.0004192854,0.00003025719,0.00006653739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01239509,"threshold_uncertainty_score":0.9944746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01044498149682488,"score_gpt":0.2146196378997796,"score_spread":0.2041746564029548,"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."}}