{"id":"W7083694231","doi":"10.5281/zenodo.17224377","title":"LSPFuzz: Hunting Bugs in Language Servers (Experimental Data)","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Education, Psychology, and Social Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Server; Software; Code (set theory); Source code; Software bug","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":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00334506,0.0001835697,0.0002418026,0.000516349,0.003457758,0.001110141,0.003745299,0.0002851378,0.01787079],"category_scores_gemma":[0.003701537,0.0002247041,0.00005344356,0.001190015,0.0005135259,0.0003808696,0.002180992,0.000805271,0.001416472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005385856,"about_ca_system_score_gemma":0.00008098482,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006707163,"about_ca_topic_score_gemma":0.0004083242,"domain_scores_codex":[0.9959114,0.001623188,0.0003291962,0.0007204349,0.0007586167,0.0006571293],"domain_scores_gemma":[0.9981511,0.0001259512,0.000137888,0.001032207,0.0003482693,0.0002045977],"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":[0.0000188794,0.0002244814,0.000005682616,0.00006234535,0.0000263683,0.00001417347,0.006871553,7.985047e-7,0.00003189712,0.0006073893,0.9862814,0.005855047],"study_design_scores_gemma":[0.0002974641,0.00004410434,0.0001242218,0.00006688823,0.00001029665,0.000002116614,0.01967679,0.000004104562,0.000007826735,0.00003421472,0.9795393,0.0001926488],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002530419,0.0006190395,0.000007248875,0.002428775,0.0008661636,0.0009586517,0.8450642,0.0003691974,0.1471564],"genre_scores_gemma":[0.004065446,0.0009497514,0.00003516126,0.000238216,0.0007284415,1.589771e-7,0.9894909,0.0002999795,0.004191934],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1444268,"threshold_uncertainty_score":0.9999268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08919280807241241,"score_gpt":0.4212033362107007,"score_spread":0.3320105281382883,"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."}}