{"id":"W4414359725","doi":"10.24963/ijcai.2025/1271","title":"SandboxSocial: A Sandbox for Social Media Using Multimodal AI Agents","year":2025,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Impact; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Social media; Sandbox (software development); Bridge (graph theory); Key (lock); Grounded theory; Upload; Social dynamics","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":[0.001133009,0.0009303954,0.0005335758,0.0006522708,0.0009186587,0.001572252,0.002227268,0.001470481,0.01261772],"category_scores_gemma":[0.005843018,0.000522487,0.0008657529,0.0003631219,0.0008354392,0.002403645,0.002683828,0.001395555,0.001809714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007764546,"about_ca_system_score_gemma":0.001277001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005470779,"about_ca_topic_score_gemma":0.007209372,"domain_scores_codex":[0.9995283,0.0001860859,0.00003670583,0.00008987448,0.0001096947,0.00004932673],"domain_scores_gemma":[0.9979119,0.001086401,0.0001028804,0.0004432822,0.0002013378,0.0002542043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001797847,0.001225295,0.02079761,0.001158268,0.0006037563,0.00108911,0.002250032,0.6545821,0.01983153,0.1104018,0.06518477,0.1210779],"study_design_scores_gemma":[0.0001287025,0.00009471322,0.0005616074,0.00003277409,0.00002936119,0.00006097321,0.00009141542,0.9550608,0.003142869,0.01688517,0.02387892,0.00003266809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1852863,0.0006085577,0.6736946,0.001902566,0.0006909034,0.001936718,0.006410763,0.08841166,0.04105787],"genre_scores_gemma":[0.6982268,0.0004994326,0.2747531,0.0006170805,0.00008361908,0.002036889,0.004879487,0.004295657,0.01460793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01261772,"threshold_uncertainty_score":0.04221046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06472675789559049,"score_gpt":0.3660112146209306,"score_spread":0.3012844567253401,"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."}}