{"id":"W4401042714","doi":"10.18653/v1/2024.naacl-srw.5","title":"SMARTR: A Framework for Early Detection using Survival Analysis of Longitudinal Texts","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Natural language processing","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":[0.01023269,0.001900391,0.001973925,0.007542103,0.001007075,0.002758329,0.003238474,0.00227302,0.007456577],"category_scores_gemma":[0.02352783,0.001387943,0.002601745,0.003746282,0.000858366,0.003467676,0.003167087,0.002854112,0.007968909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000696762,"about_ca_system_score_gemma":0.001829091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006090907,"about_ca_topic_score_gemma":0.009381713,"domain_scores_codex":[0.9971033,0.001309374,0.0001719962,0.0006969029,0.0005471415,0.0001713134],"domain_scores_gemma":[0.9862518,0.009476854,0.0008916318,0.001577499,0.001406067,0.0003961663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008122687,0.0004098644,0.0159255,0.0006282664,0.0007351247,0.0005044757,0.0008787789,0.05770053,0.007399223,0.03068467,0.05429739,0.8300239],"study_design_scores_gemma":[0.00009996605,0.0001470397,0.002682472,0.00009246953,0.0001301525,0.0002385811,0.0001292817,0.9041005,0.003208888,0.07082269,0.01825959,0.00008832883],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002442556,0.0005407324,0.9843828,0.000226931,0.0000734357,0.00008568514,0.001200504,0.01072153,0.0003257787],"genre_scores_gemma":[0.08734042,0.0009645717,0.8965522,0.0002638676,0.0004340533,0.0008132967,0.007026307,0.001902073,0.004703193],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01023269,"threshold_uncertainty_score":0.05411625,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05735219695138245,"score_gpt":0.3218239795214972,"score_spread":0.2644717825701148,"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."}}