{"id":"W4412603234","doi":"10.2139/ssrn.5353923","title":"Generative AI for Data Scraping","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Generative grammar; Artificial intelligence; Computer science; Generative model; Natural language processing; Data science","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":["open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002046467,0.0002260457,0.0002634438,0.0001617589,0.0004368063,0.0006858223,0.005510321,0.0001398106,0.000001899422],"category_scores_gemma":[0.00008821001,0.000214103,0.0001095324,0.0002053499,0.00002865217,0.0004683383,0.003168026,0.002859239,0.000006677696],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004891773,"about_ca_system_score_gemma":0.008868091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005680173,"about_ca_topic_score_gemma":0.0001731444,"domain_scores_codex":[0.9970472,0.00005828072,0.0003602046,0.0007782248,0.0002174626,0.001538598],"domain_scores_gemma":[0.9975733,0.00008916198,0.0002662237,0.001795198,0.000205032,0.00007113175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002535527,0.00003871714,0.000005437807,0.00001719021,0.0002180059,6.271542e-7,0.00008563141,0.0001778838,0.00001440027,0.6051989,0.009052904,0.3851878],"study_design_scores_gemma":[0.0002172423,0.00004742179,0.00000430359,0.00007756599,0.00004033046,0.0000486482,0.00005389368,0.3936541,0.00003959694,0.5696675,0.0359295,0.0002198571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000357387,0.003214963,0.9848415,0.01026191,0.0006875667,0.0003118205,0.0002982832,0.00007572693,0.0002725282],"genre_scores_gemma":[0.00412892,0.009829408,0.9719799,0.002499563,0.002436428,0.0002589581,0.001324588,0.0000423891,0.007499854],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3934762,"threshold_uncertainty_score":0.9998704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04355453867628083,"score_gpt":0.3401694084707009,"score_spread":0.29661486979442,"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."}}