Metraipolis › archive › dc_ae2373532358
A Closed-Form Estimator and Diagnostic Battery for Anchor-Judge Error Correlation, Under a Single-Common-Factor Model — arXiv:2609.08826
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08826
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:58:23.525Z
- SHA-256 of the archived text
4c96c0bac571c6530bdc0e106739a792b1a01cc4cbe1b2ef6533bb16ab806ac9- Stable URL of this page
https://metraipolis.com/documento/dc_ae2373532358
How to cite
A Closed-Form Estimator and Diagnostic Battery for Anchor-Judge Error Correlation, Under a Single-Common-Factor Model — arXiv:2609.08826 — arXiv (en), https://arxiv.org/abs/2609.08826 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae2373532358 (Metraipolis archive dc_ae2373532358, sha256 4c96c0bac571c6530bdc0e106739a792b1a01cc4cbe1b2ef6533bb16ab806ac9)
BibTeX
@misc{dcae2373532358,
title = {A Closed-Form Estimator and Diagnostic Battery for Anchor-Judge Error Correlation, Under a Single-Common-Factor Model — arXiv:2609.08826},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08826},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae2373532358; sha256 4c96c0bac571c6530bdc0e106739a792b1a01cc4cbe1b2ef6533bb16ab806ac9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08826. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When an external reference set (an anchor) is used to decompose an LLM-judge panel's error into a quality signal and a shared common-mode error, standard practice assumes the anchor is uncontaminated: its error uncorrelated with the judges' shared error. We study when that assumption can be dropped and replaced by an estimate. Under a single-common-factor model, >=2 judges and >=2 anchors point-identify the quality variance, the common-mode variance, and each anchor's contamination correlation rho_k in closed form, with an exact per-anchor-pair failure boundary; a designated clean-anchor estimator, by contrast, reports a contaminated companion anchor as fully clean once its trusted anchor is itself contaminated. Because the single-common-factor assumption is itself untestable, the estimator ships gated behind a calibrated diagnostic battery (judge-covariance dispersion; over-identification; a family-block test from judge metadata, with a family-blocked estimator that removes family-level shared-residual bias exactly), bootstrap confidence intervals with measured coverage, and a weak-identification screen. A proposition maps which violations bias rho_k, in which direction, and which evade detection. For ordinal scores we show an identification hierarchy: with all variables ordinal, rho_k is not identified at any number of anchors; with ordinal judges and >=3 continuous anchors it is, and we give an estimator for that case. On real data the validation is asymmetric, and we say so plainly: the diagnostics are validated in the rejecting direction (both real panels we test are correctly rejected by the model-adequacy pre-test), while the estimator is validated in simulation and stress-tested semi-synthetically under oracle calibration; no real panel has yet passed the pre-test, and the pre-test exists precisely to say so. All results replay offline from shipped, checksummed artifacts. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Methodology (stat.ME) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.08826 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T12:30:25.368Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).