{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","open_science"],"category_scores_codex":[0.02888922,0.002112914,0.005006352,0.006300397,0.001204002,0.002106532,0.007771348,0.00162091,0.01515465],"category_scores_gemma":[0.09123655,0.001581421,0.003605868,0.01735664,0.0005575253,0.0006515845,0.008578587,0.001785142,0.0002752618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000383598,"about_ca_system_score_gemma":0.001970498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002184109,"about_ca_topic_score_gemma":0.001638105,"domain_scores_codex":[0.9785314,0.003884338,0.005603872,0.006506559,0.00369145,0.00178237],"domain_scores_gemma":[0.9386652,0.04600212,0.002872922,0.008311432,0.003296958,0.0008513483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003128727,0.00112234,0.06911875,0.0004601628,0.0142697,0.00002662771,0.0009109375,0.08539842,0.0001019848,0.0003597794,0.2400274,0.5850751],"study_design_scores_gemma":[0.001772546,0.0001571551,0.03174889,0.0001163258,0.005058806,0.000005341769,0.0002265647,0.8988355,0.00007901451,0.01292357,0.04745136,0.001624936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01216676,0.0002183229,0.8567041,0.0008651341,0.005470239,0.004585127,0.1095741,0.0001875459,0.01022875],"genre_scores_gemma":[0.07328598,0.00006825003,0.8166077,0.0009377102,0.0006951371,0.001353609,0.03438865,0.0001009536,0.07256205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.813437,"threshold_uncertainty_score":0.9999629,"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."}}