{"id":"W7088574281","doi":"10.5281/zenodo.17318864","title":"aminzadenoori/A-Comparison-of-Small-and-Large-Language-Models-for-Requirements-Classification: slmvsllm requirements classification-v3","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Laser-Ablation Synthesis of Nanoparticles","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Replication (statistics); Task (project management); Computational model; Natural language; Modeling language; Software","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01544628,0.002017207,0.001149087,0.003822206,0.001097304,0.003172615,0.00302417,0.002269256,0.01851555],"category_scores_gemma":[0.05005964,0.0007237121,0.003469814,0.002360046,0.000603636,0.006317123,0.003268213,0.002930073,0.009655345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002240688,"about_ca_system_score_gemma":0.002753389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009575159,"about_ca_topic_score_gemma":0.01274924,"domain_scores_codex":[0.9899546,0.005434657,0.0008424252,0.001349663,0.002079718,0.0003389933],"domain_scores_gemma":[0.9506686,0.03525403,0.001067763,0.007841216,0.004370436,0.0007978842],"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":[0.004346281,0.002340764,0.03310344,0.003717674,0.001670992,0.0002452909,0.0009114253,0.04560708,0.006136828,0.009317921,0.2279943,0.6646079],"study_design_scores_gemma":[0.001943873,0.002248409,0.0388283,0.001739053,0.0009371965,0.0006853248,0.00309667,0.7902114,0.02329893,0.0259152,0.1106522,0.0004435823],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.3491268,0.01383068,0.4192525,0.01447136,0.002721812,0.004548659,0.0769333,0.07327341,0.04584154],"genre_scores_gemma":[0.5283152,0.00254731,0.3076294,0.001830259,0.0003075761,0.003088328,0.1411531,0.004426104,0.01070263],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01851555,"threshold_uncertainty_score":0.08168876,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08620065752806035,"score_gpt":0.3014053761877254,"score_spread":0.2152047186596651,"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."}}