{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007929974,0.0004682671,0.0004405949,0.0003475894,0.0007093846,0.0007495817,0.003001907,0.0002704977,0.0005246707],"category_scores_gemma":[0.0009748532,0.0003331055,0.00009114215,0.001097407,0.0005591429,0.0003259364,0.001104671,0.0003074124,0.00008247009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000723058,"about_ca_system_score_gemma":0.0007707215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003288893,"about_ca_topic_score_gemma":0.0002359086,"domain_scores_codex":[0.9967135,0.00005335881,0.0004217911,0.001398827,0.0005854359,0.0008270981],"domain_scores_gemma":[0.99768,0.0002016267,0.000341948,0.00127397,0.0002668115,0.0002356253],"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":[0.00002735111,0.0002213765,0.0000325504,0.0004447125,0.00007402603,0.00009131523,0.001131151,0.0008693027,0.006876535,0.005232009,0.9671297,0.01786995],"study_design_scores_gemma":[0.0007975074,0.0001331466,0.00002006712,0.0005059826,0.0000410566,0.0000588076,0.001546933,0.309149,0.002532343,0.0002522377,0.684118,0.000844878],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0001160484,0.0007115135,0.4722961,0.006101944,0.001930973,0.002207178,0.006653206,0.001250232,0.5087328],"genre_scores_gemma":[0.01003041,0.00001512797,0.2552602,0.0007810627,0.000851135,0.00009789222,0.00236898,0.00005427422,0.7305409],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3082797,"threshold_uncertainty_score":0.9999121,"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."}}