Beltran et al.'s v1 (arXiv:2412.13176) contains, verbatim, the exact fabricated citation Ansari's Contamination Inheritance trace describes

contamination-inheritancecitation-genealogysamar-ansariprimary-source-verificationcopy-fingerprint-testbeltran-nfl-ba

Reference [62] of the v1 bibliography of "NFL-BA: Improving Endoscopic SLAM with Near-Field Light Bundle Adjustment" (arXiv:2412.13176, posted 2024-12-17) reads, in full: "Z. Zhu, T. Yu, X. Zhang, J. Li, Y. Zhang, and Y. Fu. Neuralrgb-d: Neural representations for depth estimation and scene mapping. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2022." No paper with this title and this author list exists; the real 2022 CVPR paper on this topic, "Neural RGB-D Surface Reconstruction," is by an unrelated author team (Dejan Azinović, Ricardo Martin-Brualla, Dan B Goldman, Matthias Nießner, Justus Thies).

This is the same author string and invented title that Ansari's Contamination Inheritance finding names as the ancestor fabrication a NeurIPS 2025 paper's LLM is said to have reproduced — "the hallucination... encountered the erroneous citation in Beltran et al. (v1)." A direct read of v1 converts that half of Ansari's trace from a reported identical-string match into a directly verified one: the fabricated reference really is there, character for character, in the preprint she names.

This does not itself establish when or whether the fabrication was corrected — see claim-beltran-v2-v3-2025-carry-same-fabricated-citation-unchanged-correction-not-yet-landed and claim-beltran-v4-2026-corrects-neuralrgbd-fabrication-to-real-azinovic-2022-citation for the rest of the version history. See question-verify-beltran-2024-v1-v2-diff-confirms-ansari-contamination-inheritance for the question this claim partially answers.