{"id":"W7138957623","doi":"10.1109/icaiccit68829.2025.11434468","title":"AI-Enhanced Web Crawler for Real-Time Discovery of Emerging Trends in Sustainable Finance","year":2025,"lang":"","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Web crawler; Crawling; Latent Dirichlet allocation; Relevance (law); Semantic Web; Field (mathematics); Hyperlink; Term (time); Baseline (sea)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009457662,0.0003422733,0.0008457799,0.001397947,0.0002184851,0.0003945849,0.001349644,0.0001437956,0.0001293107],"category_scores_gemma":[0.0001578644,0.0003363152,0.0003524068,0.005237509,0.000128666,0.002080682,0.0007689117,0.0001846555,0.00001025206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000141624,"about_ca_system_score_gemma":0.000663685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001009775,"about_ca_topic_score_gemma":0.0001798233,"domain_scores_codex":[0.9966039,0.0001065225,0.0009886733,0.001071802,0.0002834966,0.0009455716],"domain_scores_gemma":[0.9978099,0.0002602218,0.0002900838,0.001288408,0.0003007366,0.00005063992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000376143,0.001499795,0.002013418,0.001320363,0.0005578853,0.00005934295,0.003774667,0.01352934,0.03705627,0.440606,0.1166111,0.3825957],"study_design_scores_gemma":[0.001812248,0.0002341439,0.002053849,0.0005892091,0.0001391643,4.296237e-7,0.001071925,0.9525278,0.02634969,0.00267796,0.01192611,0.0006174461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08892556,0.0005300558,0.8405767,0.007528873,0.0004402432,0.0003506042,0.00008903238,0.00009623761,0.06146271],"genre_scores_gemma":[0.6561106,0.0002325449,0.006291432,0.0001666997,0.0000308832,0.00003485399,0.0000232898,0.00001002524,0.3370997],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9389985,"threshold_uncertainty_score":0.9999089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007792141997870805,"score_gpt":0.2766169907717067,"score_spread":0.2688248487738359,"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."}}