{"id":"W7117478457","doi":"10.1145/3714394.3756211","title":"LSTM vs. DistilBERT: A Comparative Study for 2025 SHL Recognition Challenge","year":2025,"lang":"","type":"article","venue":"","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Transport Canada; Concordia University","funders":"","keywords":"Generalization; Modality (human–computer interaction); Inference; Modalities; Task (project management); Activity recognition; Domain (mathematical analysis)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.004423747,0.002343989,0.001314054,0.001333163,0.000659608,0.001658141,0.00199708,0.002852872,0.003904647],"category_scores_gemma":[0.01383337,0.0004630969,0.0007746041,0.00102807,0.0007897324,0.003868502,0.002205034,0.002236681,0.002769398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001816794,"about_ca_system_score_gemma":0.001234681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01852044,"about_ca_topic_score_gemma":0.02719791,"domain_scores_codex":[0.9969982,0.001077264,0.000266284,0.0006618843,0.0006785471,0.0003179277],"domain_scores_gemma":[0.9946703,0.003395934,0.0002209855,0.000590408,0.0008899111,0.0002324015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006617414,0.001649749,0.01159035,0.003995406,0.00113107,0.0007637164,0.0008121954,0.1576541,0.02591838,0.00187629,0.05190377,0.7360875],"study_design_scores_gemma":[0.0002955672,0.003652621,0.01864565,0.0003601568,0.0003431832,0.0007373925,0.001386094,0.9221998,0.03446011,0.0032074,0.01451092,0.0002011555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8682707,0.01864059,0.04958909,0.003418332,0.001669409,0.0007453618,0.01264452,0.01153645,0.03348567],"genre_scores_gemma":[0.9389885,0.001820067,0.03021846,0.0007837525,0.0002024587,0.0003104541,0.0193208,0.0005741407,0.007781396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01852044,"threshold_uncertainty_score":0.0368253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1321837074961509,"score_gpt":0.3610271354708418,"score_spread":0.2288434279746909,"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."}}