{"id":"W4283696279","doi":"10.1109/msp.2022.3163870","title":"Reproducibility in Matrix and Tensor Decompositions: Focus on model match, interpretability, and uniqueness","year":2022,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Baycrest Hospital","funders":"National Institute on Aging; Norges Forskningsråd; National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; U.S. Department of Health and Human Services","keywords":"Interpretability; Uniqueness; Focus (optics); Computer science; Audit; Tensor (intrinsic definition); Matrix (chemical analysis); Point (geometry); Artificial intelligence; Algorithm; Theoretical computer science; Mathematics; Algebra over a field; Pure mathematics; Mathematical analysis; Physics; Accounting; Geometry","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06318138,0.002571346,0.002799279,0.004134785,0.002860914,0.01321104,0.005721326,0.005466233,0.004835331],"category_scores_gemma":[0.2444331,0.002051915,0.002843108,0.003555371,0.03082422,0.03340122,0.01315942,0.01033285,0.001806492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003808432,"about_ca_system_score_gemma":0.00481943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002434237,"about_ca_topic_score_gemma":0.001515456,"domain_scores_codex":[0.9488403,0.03042724,0.002784118,0.008500727,0.008360343,0.001087292],"domain_scores_gemma":[0.7720979,0.1295135,0.01204007,0.07457814,0.009826495,0.00194373],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007124023,0.00003371054,0.001006602,0.0002311862,0.00009376801,0.0001197148,0.001159392,0.008991605,0.0005888973,0.9536617,0.002707972,0.03133408],"study_design_scores_gemma":[0.00001186919,0.00002150561,0.0001898476,0.00009694777,0.00001450349,0.00007388929,0.0001131545,0.02040259,0.0008139465,0.9736892,0.004545069,0.00002744013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00707303,0.003127407,0.9711211,0.01001521,0.0004322999,0.00007352599,0.0002149793,0.000536564,0.007405873],"genre_scores_gemma":[0.3307149,0.00559829,0.6495953,0.00273532,0.002931341,0.0006753232,0.001046424,0.001804611,0.004898524],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9368186,"threshold_uncertainty_score":0.3341391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04122156571030822,"score_gpt":0.3400429608258426,"score_spread":0.2988213951155344,"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."}}