{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:01:17Z","timestamp":1790269277323,"version":"4.1.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3728110","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T19:12:50Z","timestamp":1787944370000},"page":"136009-136022","source":"Crossref","is-referenced-by-count":0,"title":["Same Methods, Different Rankings: Trainable Depth as an Evaluation Variable in Continual Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0361-8302","authenticated-orcid":false,"given":"Paul-Tiberiu","family":"Iordache","sequence":"first","affiliation":[{"name":"Bitdefender","place":["Bucharest, Romania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena","family":"Burceanu","sequence":"additional","affiliation":[{"name":"Bitdefender","place":["Bucharest, Romania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4815-9227","authenticated-orcid":false,"given":"Mihai","family":"Dascalu","sequence":"additional","affiliation":[{"name":"National University of Science and Technology POLITEHNICA Bucharest","place":["Bucharest, Romania"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3057446"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref5","article-title":"Continual learning through synaptic intelligence","author":"Zenke","year":"2017","journal-title":"arXiv:1703.04200"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"ref7","article-title":"Gradient episodic memory for continual learning","author":"Lopez-Paz","year":"2017","journal-title":"arXiv:1706.08840"},{"key":"ref8","article-title":"Towards robust evaluations of continual learning","author":"Farquhar","year":"2018","journal-title":"arXiv:1805.09733"},{"key":"ref9","article-title":"Three scenarios for continual learning","author":"van de Ven","year":"2019","journal-title":"arXiv:1904.07734"},{"key":"ref10","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"Goodfellow","year":"2013","journal-title":"arXiv:1312.6211"},{"key":"ref11","article-title":"Progress & compress: A scalable framework for continual learning","author":"Schwarz","year":"2018","journal-title":"arXiv:1805.06370"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00303"},{"key":"ref13","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"Kumar","year":"2022","journal-title":"arXiv:2202.10054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.574"},{"key":"ref15","first-page":"17","article-title":"CORe50: A new dataset and benchmark for continuous object recognition","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Lomonaco"},{"key":"ref16","article-title":"Re-evaluating continual learning scenarios: A categorization and case for strong baselines","author":"Hsu","year":"2018","journal-title":"arXiv:1810.12488"},{"key":"ref17","article-title":"Continual world: A robotic benchmark for continual reinforcement learning","author":"Wo\u0142czyk","year":"2021","journal-title":"arXiv:2105.10919"},{"key":"ref18","first-page":"9440","article-title":"Continual learning in linear classification on separable data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Evron"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2135"},{"key":"ref20","article-title":"The effect of task ordering in continual learning","author":"Bell","year":"2022","journal-title":"arXiv:2205.13323"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"ref22","article-title":"Scalable and order-robust continual learning with additive parameter decomposition","author":"Yoon","year":"2019","journal-title":"arXiv:1902.09432"},{"key":"ref23","article-title":"Parameter-level soft-masking for continual learning","author":"Konishi","year":"2023","journal-title":"arXiv:2306.14775"},{"key":"ref24","first-page":"23638","article-title":"InfLoRA: Interference-free low-rank adaptation for continual learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Liang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.715"},{"key":"ref26","article-title":"Subspace geometry governs catastrophic forgetting in low-rank adaptation","author":"Steele","year":"2026","journal-title":"arXiv:2603.02224"},{"key":"ref27","article-title":"Transfusion: Understanding transfer learning for medical imaging","author":"Raghu","year":"2019","journal-title":"arXiv:1902.07208"},{"key":"ref28","article-title":"Critical learning periods in deep neural networks","author":"Achille","year":"2017","journal-title":"arXiv:1711.08856"},{"key":"ref29","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Yosinski"},{"key":"ref30","first-page":"15699","article-title":"Wide neural networks forget less catastrophically","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML)","author":"Mirzadeh"},{"key":"ref31","first-page":"40888","article-title":"Rethinking the stability-plasticity trade-off in continual learning from an architectural perspective","volume-title":"Proc. 42nd Int. Conf. Mach. Learn. (ICML)","author":"Lu"},{"key":"ref32","first-page":"15173","article-title":"Supermasks in superposition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wortsman"},{"key":"ref33","article-title":"Analyzing and reducing catastrophic forgetting in parameter efficient tuning","author":"Ren","year":"2024","journal-title":"arXiv:2402.18865"},{"key":"ref34","article-title":"Budgeted online continual learning by adaptive layer freezing and frequency-based sampling","author":"Seo","year":"2024","journal-title":"arXiv:2410.15143"},{"key":"ref35","article-title":"Hyperparameters in continual learning: A reality check","author":"Cha","year":"2024","journal-title":"Trans. Mach. Learn. Res. (TMLR)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"ref37","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","journal-title":"arXiv:1512.03385"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11670451.pdf?arnumber=11670451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:07:43Z","timestamp":1790266063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11670451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3728110","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}