{"id":"W4413572751","doi":"10.69631/ipj.v2i3nr75","title":"Enhancing Effective Thermal Conductivity Predictions in Digital Porous Media Using Transfer Learning","year":2025,"lang":"en","type":"article","venue":"InterPore journal.","topic":"Radiative Heat Transfer Studies","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Porous medium; Thermal conductivity; Materials science; Transfer of learning; Porosity; Heat transfer; Conductivity; Computer science; Composite material; Artificial intelligence; Mechanics; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002489289,0.0002087689,0.0003176541,0.0003636265,0.0001442413,0.00009944315,0.0001123532,0.00008628729,0.00003216166],"category_scores_gemma":[0.0001476795,0.0001971902,0.0001111568,0.0003301579,0.00006995744,0.0005898076,0.00001738786,0.001012218,0.000004718862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004022139,"about_ca_system_score_gemma":0.0000437234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001605076,"about_ca_topic_score_gemma":0.0001326156,"domain_scores_codex":[0.9989423,0.00006563358,0.000373266,0.0001582337,0.0001433487,0.0003171971],"domain_scores_gemma":[0.999459,0.0003081539,0.00001421281,0.00008272567,0.00007323125,0.00006267322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002234087,0.0003091598,0.2323828,0.0003865578,0.002198634,0.0006115643,0.04839933,0.4582035,0.1845795,0.0003273898,0.0003270901,0.07205097],"study_design_scores_gemma":[0.008365696,0.0006928302,0.6710618,0.006725304,0.0005119602,0.001164068,0.01636072,0.1284648,0.1581527,0.003065587,0.002950823,0.00248379],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8969697,0.0009945951,0.09669974,0.00004434506,0.001114864,0.0001774082,0.000009774487,0.0001364511,0.003853157],"genre_scores_gemma":[0.9995713,0.00009163032,0.00008599695,0.00001527347,0.0001486618,0.00002667593,0.000001543295,0.00003117466,0.00002779753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4386789,"threshold_uncertainty_score":0.8041182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009262962308075684,"score_gpt":0.2393214475497436,"score_spread":0.2300584852416679,"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."}}