{"id":"W4416018108","doi":"10.1145/3746252.3761636","title":"CSMD: Curated Multimodal Dataset for Chinese Stock Analysis","year":2025,"lang":"","type":"preprint","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Stock market; Stock (firearms); Data quality; Affinity analysis; Quality (philosophy); Stock exchange","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":[0.0009157172,0.002123406,0.0008098315,0.005167805,0.0009909648,0.001123368,0.002417393,0.001463667,0.01305822],"category_scores_gemma":[0.003735887,0.0003045767,0.001180401,0.004492211,0.0004526484,0.001321188,0.002051875,0.001057993,0.008614916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001614636,"about_ca_system_score_gemma":0.003068957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.060624,"about_ca_topic_score_gemma":0.08917932,"domain_scores_codex":[0.999199,0.00008296694,0.0001063782,0.0002268866,0.0002455912,0.0001392005],"domain_scores_gemma":[0.9989415,0.0001332,0.00008914031,0.0003588109,0.0003564634,0.0001208519],"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":[0.0004678851,0.0003671583,0.01448982,0.001269906,0.0002453658,0.0007869848,0.0002626433,0.004800769,0.008673237,0.002679694,0.8493263,0.1166302],"study_design_scores_gemma":[0.0004398849,0.0003126014,0.1248381,0.0004837364,0.0003652475,0.001349512,0.001189614,0.08684704,0.02685826,0.007280088,0.7495727,0.0004632095],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.04360681,0.001369689,0.01142382,0.0007558827,0.0004870512,0.0005930743,0.921293,0.01266064,0.007810061],"genre_scores_gemma":[0.03944153,0.0003662806,0.01460578,0.0001818691,0.000090336,0.0005492771,0.9412865,0.0003078264,0.003170596],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.060624,"threshold_uncertainty_score":0.1205423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1428235587777985,"score_gpt":0.494960302798904,"score_spread":0.3521367440211056,"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."}}