用少量权重片段验证模型来源并拆解合并关系，精准识别模型血缘。
modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints
- 通过少量网络读取生成模型指纹，实现快速溯源
- 在真实数据上达成100%准确率，零误报
- 无需下载完整模型即可推断合并权重比例，适合安全审计
开源大模型的血缘关系依赖自我报告：Hugging Face 的 base_model 字段可选且未经验证，超过60%的模型未记录父模型。现有溯源方法多为单信号、单实验的独立代码，一旦出现争议需手动重做。本文提出 modelDNA 工具，仅需约100-300MB的分段HTTP读取（而非7B模型全量15GB下载），即可从四类已发表信号中比对参考数据库，输出八类判定结果并给出校准置信度，优先选择诚实弃权而非错误确信。在包含15个真实模型、13个正样本和107个难负样本的基准测试中，系统达到AUROC 1.0，报告阈值下零假阳性，13/13正确识别顶级父模型。第二贡献为合并分解：主流权重合并方法近似线性，指纹采样位置由张量身份决定，故合并模型指纹即为父模型指纹的线性组合。通过带和为1约束的最小二乘法，可仅凭指纹恢复混合权重。在 mergekit 配置为真值的合并中，slerp 合并的层插值曲线还原精度达 r=0.999，dare_ties 合并权重误差小于0.011，全程无需下载完整权重。所有指纹、基准与55个模型的推断血缘图均公开可复现。
原文摘要 · Abstract (English)
The lineage graph of open-weight language models is self-reported: Hugging Face's base_model metadata field is optional and unverified, and over 60% of Hub models document no parentage at all. Methods for detecting lineage from weights exist in the research literature, but each ships as paper code tied to one signal and one experiment; when a provenance dispute breaks, the analysis is redone by hand. This report describes modelDNA, a tool that fingerprints a model from roughly 100-300 MB of ranged HTTP reads (instead of a full 15 GB download for a 7B model), compares the fingerprint against a reference database of foundation models across four published signal families, and returns one of eight verdict classes with a calibrated probability, preferring honest abstention to confident error. On a benchmark of 15 real Hub models with org-documented parentage, judged against 8 candidate bases (13 positives, 107 hard negatives), the system achieves AUROC 1.0, zero false positives at its reporting threshold, and 13/13 correct top-1 parent attribution. The report's second contribution is merge decomposition. Every mainstream weight-merging method is (near-)linear per tensor, and fingerprint sample positions are deterministic functions of tensor identity, so a merged model's fingerprint is the same linear combination of its parents' fingerprints. Mixture weights can therefore be recovered from fingerprints alone by sum-to-one constrained least squares. Against merges with published mergekit configurations as ground truth, the method recovers a slerp merge's layer-interpolation curves at r = 0.999 and a dare_ties merge's mixture weights to within 0.011 of the published values, without downloading any weights beyond the fingerprints. All fingerprints, benchmarks, and the inferred lineage graph of 55 models are public and reproducible offline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。