{"id":"W7113897858","doi":"10.2196/preprints.88838","title":"Battling the bots: Defending against fraudulent responses while conducting an international community-engaged web-based survey with people living with Long COVID (Preprint)","year":2025,"lang":"","type":"article","venue":"","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Incentive; Survey data collection; General Social Survey; Survey methodology; Survey research; 2019-20 coronavirus outbreak","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01520246,0.0003046819,0.0004341957,0.000973681,0.002602534,0.002686251,0.001249881,0.001323856,0.003332405],"category_scores_gemma":[0.04266792,0.0004672744,0.0004959274,0.0007111263,0.00119697,0.002669183,0.003643324,0.001481595,0.001287821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00121833,"about_ca_system_score_gemma":0.003955319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01378265,"about_ca_topic_score_gemma":0.02056458,"domain_scores_codex":[0.9930832,0.004269273,0.0006432113,0.0004566043,0.0007163247,0.0008313635],"domain_scores_gemma":[0.9777451,0.006427919,0.003898189,0.002081134,0.00601896,0.0038287],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002740698,0.001423018,0.5610698,0.0007178214,0.00006216217,0.0008761487,0.274533,0.0001386056,0.002775433,0.0006546024,0.04068521,0.1167902],"study_design_scores_gemma":[0.0001187258,0.001919663,0.4450398,0.001474766,0.00008953029,0.0005842731,0.4951836,0.001381953,0.001788311,0.00103797,0.05116392,0.0002175176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9843555,0.0001707164,0.002170357,0.005778028,0.0001335912,0.001594967,0.0008432973,0.0001042838,0.004849302],"genre_scores_gemma":[0.9732666,0.0004156476,0.008566514,0.007702646,0.0001288141,0.006042172,0.0007061819,0.00005765692,0.003113845],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9847975,"threshold_uncertainty_score":0.08039927,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.210321701717328,"score_gpt":0.4070422304367478,"score_spread":0.1967205287194198,"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."}}