{"id":"W4412046214","doi":"10.1145/3719160.3737632","title":"Fitting the Message to the Moment: Designing Calendar-Aware Stress Messaging with Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Innovative Human-Technology Interaction","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Institute of Mental Health; Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Stress (linguistics); Moment (physics); Programming language; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0006837723,0.0001674033,0.0001319579,0.000191383,0.0006854716,0.0001769171,0.001337715,0.00005241617,0.00002424999],"category_scores_gemma":[0.00003030884,0.00008749939,0.00003119261,0.001030115,0.00005094401,0.0005288361,0.0006237496,0.0004204816,0.00001686364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000924561,"about_ca_system_score_gemma":0.00005650103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007275197,"about_ca_topic_score_gemma":0.0002157769,"domain_scores_codex":[0.9986465,0.0001173988,0.0002082168,0.0003856836,0.0002507599,0.000391439],"domain_scores_gemma":[0.9987635,0.0001917732,0.000090958,0.0007830327,0.0001504416,0.0000202966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001653428,0.0000725629,0.0006687519,0.00003109123,0.0001527782,0.0000471929,0.01719955,0.006840594,0.001863147,0.9510373,0.007289739,0.01478079],"study_design_scores_gemma":[0.001129507,0.0001633164,0.001075632,0.0008264106,0.00005625892,0.00004245225,0.04027621,0.7189153,0.2170285,0.007753155,0.0119728,0.0007604913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01516118,0.00006144297,0.9593041,0.01228315,0.0001471824,0.0003510001,0.000008578188,0.0003384739,0.01234491],"genre_scores_gemma":[0.9842181,0.000001178565,0.008757311,0.002877285,0.00002357596,0.00009066079,0.000001979579,0.00001009859,0.004019864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9690568,"threshold_uncertainty_score":0.5272163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01141865590492042,"score_gpt":0.2731965893455054,"score_spread":0.261777933440585,"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."}}