{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006314956,0.0003557684,0.0004529473,0.0006109139,0.0006361753,0.0003804497,0.001051332,0.0002516472,0.003862278],"category_scores_gemma":[0.0004452083,0.000402572,0.00009557249,0.0005182164,0.0001603239,0.0002285203,0.0004325963,0.0002460449,0.001424008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002229924,"about_ca_system_score_gemma":0.00001372192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001514829,"about_ca_topic_score_gemma":0.000002897474,"domain_scores_codex":[0.9975085,0.0001850807,0.0007105767,0.0006166829,0.0004987152,0.0004804585],"domain_scores_gemma":[0.9981235,0.00007316739,0.0003340227,0.0008692252,0.0004269427,0.0001731415],"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":[0.00004461764,0.0003034711,0.00003267832,0.000950872,0.0004443257,0.000001554389,0.001083976,0.0003594044,0.01186441,0.01311434,0.8885548,0.08324561],"study_design_scores_gemma":[0.0007235921,0.00006781411,0.0002515022,0.0002606229,0.0001056357,0.000002871771,0.0006481435,0.02247077,0.002340976,0.000149437,0.9725804,0.0003981806],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.001127362,0.002368569,0.1593664,0.0006903896,0.0007098849,0.002818408,0.002310723,0.007592683,0.8230156],"genre_scores_gemma":[0.8384115,0.001309046,0.008572373,0.0001390018,0.0008704267,0.000005928133,0.00676892,0.02088553,0.1230373],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8372841,"threshold_uncertainty_score":0.9998426,"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."}}