Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

arXiv:2608.14929 · cs.CL, cs.LG · Submitted 2026-08-14 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-08-14

Updated: 2026-09-22

Terminology

• AUROC — 37× in this paper · explained in 2 episodes
• Benchmark — 36× in this paper · explained in 2 episodes
• Trace — 34× in this paper · explained in 2 episodes
• Accuracy — 23× in this paper · explained in 1 episode
• Verification — 19× in this paper · explained in 2 episodes
• Pruning — 12× in this paper · explained in 4 episodes
• Alignment — 11× in this paper · explained in 1 episode
• Calibration — 10× in this paper · explained in 7 episodes
• Quantization — 9× in this paper · explained in 12 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• AUC — 6× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Distillation — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Provenance — 6× in this paper · explained in 4 episodes
• Sparsity — 6× in this paper · explained in 4 episodes
• Verifier — 6× in this paper · explained in 2 episodes
• Cosine Similarity — 5× in this paper · explained in 3 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• Fingerprinting — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• The Llama 3 Herd of Models
• InternLM2 Technical Report
• Gaussian Error Linear Units (GELUs)
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Mistral 7B
• TinyStories: How Small Can Language Models Be and Still Speak Coherent English?
• LLM360: Towards Fully Transparent Open-Source LLMs
• Baichuan 2: Open Large-scale Language Models
• Qwen2.5 Technical Report
• Yi: Open Foundation Models by 01.AI
• I Dropped a Neural Net
• Code Llama: Open Foundation Models for Code
• GLU Variants Improve Transformer
• LLaMA: Open and Efficient Foundation Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering