{"id":"W4414813482","doi":"10.48550/arxiv.2509.23340","title":"CrediBench: Building Web-Scale Network Datasets for Information Integrity","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Institut de Valorisation des Données; Compute Canada; Canadian Institute for Advanced Research","keywords":"Misinformation; Hyperlink; Credibility; Leverage (statistics); Snapshot (computer storage); Pipeline (software); Graph; The Internet","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001862979,0.002595584,0.000920607,0.007128404,0.001471142,0.002043155,0.003757278,0.002962938,0.005654254],"category_scores_gemma":[0.01559872,0.0007422667,0.001794038,0.005276178,0.0009125277,0.004424763,0.002668871,0.003588781,0.007399942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001944867,"about_ca_system_score_gemma":0.001190422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02581755,"about_ca_topic_score_gemma":0.0423287,"domain_scores_codex":[0.9981897,0.0003865886,0.0001366657,0.0005813846,0.0005436029,0.0001620048],"domain_scores_gemma":[0.9951974,0.001712961,0.0005605944,0.001463686,0.0007944083,0.0002710057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006392349,0.001331863,0.03627246,0.002923031,0.000753183,0.001118171,0.0008313796,0.1488442,0.006519456,0.0118765,0.6188418,0.1700489],"study_design_scores_gemma":[0.0002816684,0.000311921,0.03163403,0.0005165848,0.0002037073,0.001008745,0.000806966,0.6952646,0.01056713,0.02602859,0.2331624,0.0002137091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.1102816,0.003418634,0.06459764,0.002597724,0.0006014181,0.001141869,0.742482,0.06195313,0.01292604],"genre_scores_gemma":[0.0887479,0.0007554953,0.06379415,0.0003487556,0.0001121603,0.0007543848,0.841928,0.0008953805,0.002663716],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02581755,"threshold_uncertainty_score":0.05133456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03683564190909822,"score_gpt":0.2847961864799374,"score_spread":0.2479605445708392,"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."}}