{"id":"W7082257884","doi":"10.48448/ew67-7427","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Relevance (law); Cultural diversity; Multiculturalism; Southeast asia; Representation (politics); Crowdsourcing; Work (physics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001163298,0.0009031107,0.0003752953,0.002006843,0.0008772588,0.001167823,0.001382405,0.0007679167,0.003237023],"category_scores_gemma":[0.004381238,0.0002337192,0.0007915673,0.001920293,0.0006048806,0.00110215,0.002136274,0.000914367,0.003231921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008870211,"about_ca_system_score_gemma":0.001555295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02956589,"about_ca_topic_score_gemma":0.0754675,"domain_scores_codex":[0.9992495,0.0002165622,0.00006964437,0.0002292839,0.0001575375,0.00007729778],"domain_scores_gemma":[0.9982467,0.00040425,0.0001030998,0.0007178942,0.0003612826,0.0001668575],"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":[0.0005796165,0.0005449252,0.04522172,0.003014495,0.0003604289,0.001279588,0.005991369,0.01637226,0.01630176,0.009032611,0.6270186,0.2742826],"study_design_scores_gemma":[0.0002122242,0.0001974019,0.05025949,0.0005576092,0.0001263907,0.0008683951,0.00933716,0.1085433,0.0259291,0.01590277,0.7878951,0.0001709388],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2975569,0.002923064,0.0880335,0.003515321,0.001405459,0.0019719,0.5058812,0.03768288,0.06102981],"genre_scores_gemma":[0.24934,0.0007225164,0.1359564,0.0008574945,0.0001053319,0.001163789,0.5979858,0.001886879,0.01198172],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02956589,"threshold_uncertainty_score":0.05878764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01828195463426322,"score_gpt":0.3055686554744729,"score_spread":0.2872867008402096,"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."}}