pith. sign in

Recoverable Identifier

arXiv:2605.01199 · detector doi_compliance · incontrovertible · 2026-05-19 17:30:16.971286+00:00

advisory doi_compliance recoverable_identifier

DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1162/tacla) was visible in the surrounding text but could not be confirmed against doi.org as printed.

Paper page Integrity report arXiv Try DOI

Evidence text

doi: 10.1162/tacl a 00708. URL https: //aclanthology.org/2024.tacl-1.74/. Chen, S., Sheen, H., Wang, T., and Yang, Z. Unveiling induction heads: Provable training dynamics and feature learning in transformers. In Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., and Zhang, C. (eds.),Advances in Neural Information Processing Sys- tems, volume 37, pp. 66479–66567. Curran Associates, Inc., 2024a. doi: 10.52202/079017-2127. URL https: //proceedings.neurips.cc/paper_files /paper/2024/file/7aae9e3ec211249e05b d07271a6b1441-Paper-Conference.pdf. Chen, Z.-A. and Luo, T. From condensation to rank col- lapse: A two-stage analysis of transformer training dy- namics. InThe Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025. URL https: //openreview.net/forum?id=gm5mkiTGOy. Chen, Z.-A., Li, Y ., Luo, T., Zhou, Z., and Xu, Z.-Q. J. Phase diagram of initial condensation for two-layer neural networks.CSIAM Transactions on Applied Mathematics, 5(3):448–514, 2024b. ISSN 2708-0579. doi: https: 9 Submission and Formatting Instructions for ICML 2026 //doi.org/10.4208/csiam-am.SO-2023-0016. URL https://global-sci.com/article/91025 /phase-diagram-of-initial-condensatio n-for-two-layer-neural-networks. Chen, Z.-A., Luo, T., and Wang, G. On multi-stage loss dynamics in neural networks: Mechanisms of plateau and descent stages.arXiv preprint arXiv:2410.20119, 2024c. Eldan, R. and Li, Y . Tinystories: How small can language models be and still speak co

Evidence payload

{
  "printed_excerpt": "doi: 10.1162/tacl a 00708. URL https: //aclanthology.org/2024.tacl-1.74/. Chen, S., Sheen, H., Wang, T., and Yang, Z. Unveiling induction heads: Provable training dynamics and feature learning in transformers. In Globerson, A., Mackey, L., ",
  "reconstructed_doi": "10.1162/tacla",
  "ref_index": 1,
  "resolved_title": null,
  "verdict_class": "incontrovertible"
}