{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:20:05Z","timestamp":1787941205120,"version":"build-2784847793"},"reference-count":61,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"35","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32441102"],"award-info":[{"award-number":["32441102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206316"],"award-info":[{"award-number":["62206316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003395","name":"Shanghai Municipal Education Commission","doi-asserted-by":"publisher","award":["2024AIZD014"],"award-info":[{"award-number":["2024AIZD014"]}],"id":[{"id":"10.13039\/501100003395","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Natural Science Foundation","award":["L247010"],"award-info":[{"award-number":["L247010"]}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Adv."],"published-print":{"date-parts":[[2026,8,28]]},"abstract":"<jats:p>How agents acquire abstract concepts from sparse, diverse examples\u2014often without explicit supervision\u2014remains a central problem in cognitive science and artificial intelligence. Human studies suggest that this ability depends on mental bootstrapping, the gradual construction of complex concepts from simpler partial structures. Building on this idea, we develop a self-supervised framework that trains models on systematically simplified versions of abstract reasoning tasks containing incomplete but structured concept cues. This algorithm enables models to form internal abstractions under limited resources and later apply them to more complex problems. We evaluate the framework across 12 abstract visual reasoning datasets testing in-distribution concept induction, out-of-distribution generalization, and few-shot learning. To contextualize performance, we also measure human accuracy on the same tasks. Models trained on simplified problems generalize robustly, reaching or even surpassing human-level performance. These findings show that abstract reasoning can emerge from structured simplification and minimal data, offering a computational account of concept learning in humans and machines.<\/jats:p>","DOI":"10.1126\/sciadv.aea7202","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:58:31Z","timestamp":1787939911000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Mental bootstrapping enables human-level concept learning in self-supervised deep models"],"prefix":"10.1126","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8642-9614","authenticated-orcid":true,"given":"Lingxiao","family":"Yang","sequence":"first","affiliation":[{"name":"School of Systems Science and Engineering, Sun Yat-sen University, Guangzhou 510006, Guangdong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5138-3155","authenticated-orcid":true,"given":"Muyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing 100871, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5703-1724","authenticated-orcid":true,"given":"Ying-Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Brain Health Institute, National Center for Mental Disorders, Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine and School of Psychology, Shanghai 200030, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-4679","authenticated-orcid":true,"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, Guangdong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6748-6434","authenticated-orcid":true,"given":"Zonglei","family":"Zhen","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Applied Experimental Psychology, Faculty of Psychology, Beijing Normal University, Beijing 100875, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Huang","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, Guangdong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0654-715X","authenticated-orcid":true,"given":"Ru-Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Psychological and Cognitive Sciences, Peking University, Beijing 100871, People\u2019s Republic of China."},{"name":"IDG\/McGovern Institute for Brain Research, Peking University, Beijing 100871, People\u2019s Republic of China."},{"name":"Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing 100871, People\u2019s Republic of China."},{"name":"Beijing Key Laboratory of Brain-Computer Interface and Mental Health Modulation, Peking University, Beijing 100871, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-024-01991-9"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"e_1_3_2_4_2","unstructured":"J. Devlin M.-W. Chang K. Lee K. Toutanova \u201cBERT: Pre-training of deep bidirectional transformers for language understanding \u201d in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Association for Computational Linguistics 2019)."},{"key":"e_1_3_2_5_2","unstructured":"A. Dosovitskiy L. Beyer A. Kolesnikov D. Weissenborn X. Zhai T. Unterthiner M. Dehghani M. Minderer G. Heigold S. Gelly J. Uszkoreit N. Houlsby \u201cAn image is worth 16x16 words: Transformers for image recognition at scale \u201d in International Conference on Learning Representations (ICLR 2021)."},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","unstructured":"K. He X. Zhang S. Ren J. Sun \u201cDeep residual learning for image recognition \u201d in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2016) pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_7_2","unstructured":"K. Simonyan A. Zisserman Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs.CV] (2014)."},{"key":"e_1_3_2_8_2","unstructured":"A. Krizhevsky I. Sutskever G. Hinton \u201cImageNet classification with deep convolutional neural networks \u201d in Advances in Neural Information Processing Systems 25 (NIPS) F. Pereira C. J. C. Burges L. Bottou K. Q. Weinberger Eds. (Curran Associates 2012) pp. 1097\u20131105."},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"J. Deng W. Dong R. Socher L.-J. Li K. Li L. Fei-Fei \u201cImageNet: A large-scale hierarchical image database \u201d in 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2009) pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_10_2","unstructured":"S. Dieleman H. Zen K. Simonyan O. Vinyals A. Graves N. Kalchbrenner A. Senior K. Kavukcuoglu WaveNet: A generative model for raw audio. arXiv:1609.03499 [cs.SD] (2016)."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1002\/wcs.78"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.39.3.484"},{"key":"e_1_3_2_13_2","unstructured":"M. Ding Y. Xu Z. Chen D. D. Cox P. Luo J. B. Tenenbaum C. Gan \u201cEmbodied concept learner: Self-supervised learning of concepts and mapping through instruction following \u201d in Proceedings of the 6th Conference on Robot Learning (CoRL) K. Liu D. Kulic J. Ichnowski Eds. vol. 205 of Proceedings of Machine Learning Research (PMLR 2023) pp. 1743\u20131754."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3010918"},{"key":"e_1_3_2_15_2","doi-asserted-by":"crossref","unstructured":"G. Rajendran S. Buchholz B. Aragam B. Sch\u00f6lkopf P. Ravikumar \u201cFrom causal to concept-based representation learning \u201d in Advances in Neural Information Processing Systems 37 (NeurIPS) A. Globerson L. Mackey D. Belgrave A. Fan U. Paquet J. Tomczak C. Zhang Eds. (Curran Associates 2024) pp. 101250\u2013101296.","DOI":"10.52202\/079017-3211"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00963-y"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adg2488"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aab3050"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2205582119"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2023.09.004"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.3389\/fcogn.2024.1324678"},{"key":"e_1_3_2_22_2","first-page":"155","article-title":"Structure-mapping: A theoretical framework for analogy","volume":"7","author":"Gentner D.","year":"1983","unstructured":"D. Gentner, Structure-mapping: A theoretical framework for analogy. Cognit. Sci. 7, 155\u2013170 (1983).","journal-title":"Cognit. Sci."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1417056111"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-021-02652-7"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40359-024-01952-x"},{"key":"e_1_3_2_26_2","unstructured":"J. B. Tenenbaum \u201cBayesian modeling of human concept learning \u201d in Advances in Neural Information Processing Systems 11 (NIPS) M. S. Kearns S. A. Solla D. A. Cohn Eds. (MIT Press 1999) pp. 59\u201365."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2008.0146"},{"key":"e_1_3_2_28_2","unstructured":"J. Wang C. Zhang J. Li Y. Ma L. Niu J. Han Y. Peng Y. Zhu L. Fan Evaluating and modeling social intelligence: A comparative study of human and AI capabilities. arXiv:2405.11841 [cs.AI] (2024)."},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1006\/cogp.1999.0735"},{"key":"e_1_3_2_30_2","unstructured":"M. M. Bongard The Recognition Problem (Western Washington University 1968)."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00630-8"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2011.11.005"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-023-01719-1"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X98001769"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"C. Zhang F. Gao B. Jia Y. Zhu S.-C. Zhu \u201cRAVEN: A dataset for Relational and Analogical Visual REasoNing \u201d in 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2019) pp. 5317\u20135327.","DOI":"10.1109\/CVPR.2019.00546"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"S. Hu Y. Ma X. Liu Y. Wei S. Bai \u201cStratified rule-aware network for abstract visual reasoning \u201d in Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI) (AAAI 2021) pp. 1567\u20131574.","DOI":"10.1609\/aaai.v35i2.16248"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Y. Benny N. Pekar L. Wolf \u201cScale-localized abstract reasoning \u201d in 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2021) pp. 12557\u201312565.","DOI":"10.1109\/CVPR46437.2021.01237"},{"key":"e_1_3_2_38_2","unstructured":"D. Barrett F. Hill A. Santoro A. Morcos T. Lillicrap \u201cMeasuring abstract reasoning in neural networks \u201d in Proceedings of the 35th International Conference on Machine Learning (ICML) J. Dy A. Krause Eds. vol. 80 of Proceedings of Machine Learning Research (PMLR 2018) pp. 511\u2013520."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3114987"},{"key":"e_1_3_2_40_2","unstructured":"N. Q. W. Kiat D. Wang M. Jamnik Pairwise relations discriminator for unsupervised Raven\u2019s Progressive Matrices. arXiv:2011.01306 [cs.AI] (2020)."},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"R. R. Selvaraju M. Cogswell A. Das R. Vedantam D. Parikh D. Batra \u201cGrad-CAM: Visual explanations from deep networks via gradient-based localization \u201d in 2017 IEEE International Conference on Computer Vision (ICCV) (IEEE 2017) pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_42_2","unstructured":"N. Arcot P. Srivastava S. Jaarsveld \u201cDo constraints in APM solving affect APM-like puzzle creation? \u201d in Proceedings of the 45th Annual Conference of the Cognitive Science Society (Cognitive Science Society 2023)."},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"T. Ito T. Klinger D. Schultz J. Murray M. Cole M. Rigotti \u201cCompositional generalization through abstract representations in human and artificial neural networks \u201d in Advances in Neural Information Processing Systems 35 (NeurIPS) S. Koyejo S. Mohamed A. Agarwal D. Belgrave K. Cho A. Oh Eds. (Curran Associates 2022) pp. 32225\u201332239.","DOI":"10.52202\/068431-2335"},{"key":"e_1_3_2_44_2","unstructured":"B. M. Lake T. Linzen M. Baroni Human few-shot learning of compositional instructions. arXiv:1901.04587 [cs.CL] (2019)."},{"key":"e_1_3_2_45_2","unstructured":"W. Nie Z. Yu L. Mao A. B. Patel Y. Zhu A. Anandkumar \u201cBongard-LOGO: A new benchmark for human-level concept learning and reasoning \u201d in Advances in Neural Information Processing Systems 33 (NeurIPS) H. Larochelle M. Ranzato R. Hadsell M. F. Balcan H. Lin Eds. (Curran Associates 2020) pp. 16468\u201316480."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-023-01659-w"},{"key":"e_1_3_2_47_2","unstructured":"J. Raven Handbook of Nonverbal Assessment (Springer 2003) pp. 223\u2013237."},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Y. Bengio J. Louradour R. Collobert J. Weston \u201cCurriculum learning \u201d in Proceedings of the 26th Annual International Conference on Machine Learning (ICML) A. P. Danyluk L. Bottou M. L. Littman Eds. vol. 382 of ACM International Conference Proceeding Series (Association for Computing Machinery 2009) pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1037\/h0048109"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-017-1338-1"},{"key":"e_1_3_2_51_2","unstructured":"M. P. Kumar B. Packer D. Koller \u201cSelf-paced learning for latent variable models \u201d in Advances in Neural Information Processing Systems 23 (NIPS) J. D. Lafferty C. K. I. Williams J. Shawe-Taylor R. S. Zemel A. Culotta Eds. (Curran Associates 2010) pp. 1189\u20131197."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_3_2_55_2","unstructured":"T. Chen S. Kornblith M. Norouzi G. Hinton \u201cA simple framework for contrastive learning of visual representations \u201d in Proceedings of the 37th International Conference on Machine Learning (ICML) H. Daum\u00e9 III A. Singh Eds. vol. 119 of Proceedings of Machine Learning Research (PMLR 2020) pp. 1597\u20131607."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5575"},{"key":"e_1_3_2_57_2","unstructured":"L. Yang H. You Z. Zhen D. Wang X. Wan X. Xie R.-Y. Zhang \u201cNeural prediction errors enable analogical visual reasoning in human standard intelligence tests \u201d in Proceedings of the 40th International Conference on Machine Learning (ICML) A. Krause E. Brunskill K. Cho B. Engelhardt S. Sabato J. Scarlett Eds. vol. 202 of Proceedings of Machine Learning Research (PMLR 2023) pp. 39572\u201339583."},{"key":"e_1_3_2_58_2","doi-asserted-by":"crossref","unstructured":"K. Zhao C. Xu B. Si \u201cLearning visual abstract reasoning through dual-stream networks \u201d in Proceedings of the AAAI Conference on Artificial Intelligence (Association for the Advancement of Artificial Intelligence 2024) pp. 16979\u201316988.","DOI":"10.1609\/aaai.v38i15.29641"},{"key":"e_1_3_2_59_2","unstructured":"S. S. Mondal J. D. Cohen T. W. Webb \u201cSlot abstractors: Toward scalable abstract visual reasoning \u201d in Proceedings of the 41st International Conference on Machine Learning (ICML) R. Salakhutdinov Z. Kolter K. Heller A. Weller N. Oliver J. Scarlett F. Berkenkamp Eds. vol. 235 of Proceedings of Machine Learning Research (PMLR 2024) pp. 36088\u201336105."},{"key":"e_1_3_2_60_2","doi-asserted-by":"crossref","unstructured":"S. Antol A. Agrawal J. Lu M. Mitchell D. Batra C. L. Zitnick D. Parikh \u201cVQA: Visual Question Answering \u201d in Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV) (IEEE 2015) pp. 2425\u20132433.","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_61_2","doi-asserted-by":"crossref","unstructured":"M. Xu G. Jiang W. Liang C. Zhang Y. Zhu \u201cActive reasoning in an open-world environment \u201d in Advances in Neural Information Processing Systems 36 (NeurIPS) A. Oh T. Naumann A. Globerson K. Saenko M. Hardt S. Levine Eds. (Curran Associates 2023) pp. 11716\u201311736.","DOI":"10.52202\/075280-0515"},{"key":"e_1_3_2_62_2","unstructured":"C. Zhang B. Jia F. Gao Y. Zhu H. Lu S.-C. Zhu \u201cLearning perceptual inference by contrasting \u201d in Advances in Neural Information Processing Systems 32 (NeurIPS) H. Wallach H. Larochelle A. Beygelzimer F. d\u2019Alch\u00e9-Buc E. Fox R. Garnett Eds. (Curran Associates 2019) pp. 1073\u20131085."}],"container-title":["Science Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/sciadv.aea7202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:59:05Z","timestamp":1787939945000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/sciadv.aea7202"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":61,"journal-issue":{"issue":"35","published-print":{"date-parts":[[2026,8,28]]}},"alternative-id":["10.1126\/sciadv.aea7202"],"URL":"https:\/\/doi.org\/10.1126\/sciadv.aea7202","relation":{},"ISSN":["2375-2548"],"issn-type":[{"value":"2375-2548","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"assertion":[{"value":"2025-07-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eaea7202"}}