{"id":"W4416704893","doi":"10.26868/25222708.2025.1234","title":"Explainable domain adaptation without source data for activity recognition","year":2025,"lang":"","type":"article","venue":"Building Simulation Conference proceedings","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Process (computing); Activity recognition; Transfer of learning; Transparency (behavior); Domain (mathematical analysis); Adaptation (eye); Energy (signal processing); Domain adaptation","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003276616,0.0007959126,0.00096585,0.0009440835,0.001401022,0.003202722,0.002298052,0.0005756653,0.00005483511],"category_scores_gemma":[0.002757851,0.000975031,0.0002131042,0.001824019,0.0001904104,0.008896215,0.001284932,0.0005923891,0.00005272544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005326616,"about_ca_system_score_gemma":0.001111289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002500266,"about_ca_topic_score_gemma":0.00005184797,"domain_scores_codex":[0.9938902,0.0001836135,0.001259498,0.002718443,0.0009012349,0.00104698],"domain_scores_gemma":[0.9914087,0.001523576,0.001484578,0.001179668,0.004139771,0.0002636827],"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":[0.0007257998,0.0004385322,0.002518814,0.001442921,0.0002796596,0.000001200962,0.005469682,0.003750207,0.008997865,0.008270225,0.000692613,0.9674125],"study_design_scores_gemma":[0.002486946,0.0001928888,0.000849103,0.001878092,0.0001817902,0.00000843281,0.001654619,0.9469352,0.002778992,0.02141189,0.02068538,0.0009367126],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1860073,0.00009795941,0.8060455,0.001745375,0.001247548,0.003101794,0.0001688216,0.0005027096,0.001083027],"genre_scores_gemma":[0.9518367,0.00002632532,0.04529415,0.000270082,0.0004232672,0.0004213663,0.0001487394,0.00006276539,0.001516592],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9664758,"threshold_uncertainty_score":0.999899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1433214221211334,"score_gpt":0.3512055922935967,"score_spread":0.2078841701724633,"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."}}