READER: Dynamic LLM Provenance from Query-Varying Interactions

Abstract

Existing black-box LLM provenance methods achieve comparability by querying every candidate model with the same diagnostic prompts. In deployment, auditors inherit a different evidence stream: heterogeneous prompt-response traces that arrive incrementally. We formalize dynamic black-box LLM provenance: after enrolling a fixed candidate ecosystem, attribute query-varying interactions at any available evidence budget. READER recovers comparability through a frozen proxy LLM. It projects proxy states aligned with response tokens onto length-normalized DC and first-AC modes, capturing response-wide activation location and coarse trajectory evolution. An enrollment-trained linear probe converts each fingerprint into source evidence, and Bayesian accumulation reuses this evidence unit from one observation to many. We introduce Agent500, containing 50,000 responses from 100 local and API sources to 500 heterogeneous agent prompts. On 100-way attribution, READER reaches $50.4\%$ accuracy from one response and $96.2\%$ from 100, compared with $33.0\%$ and $79.0\%$ for the strongest dynamic baselines. Four distinct proxy families all exceed $94.8\%$ at the latter budget. Controlled response-length and Math100 domain shifts expose the limits of zero-retraining transfer. Component analysis reveals a task-dependent spectral division of labor: DC dominates dynamic source identity, while first AC dominates static relationship evidence. Their joint fingerprint provides a shared measurement space for both tasks. READER audits observed text without target internals or audit-only queries. Code and data are available at https://github.com/LeoJeshua/READER.