Iryŏx II - Sharp Minimax Guarantees for Evaluating New Outcomes in Self-Modifying Systems

How can a self-modifying system certify that a rewrite improves its objective when the rewrite introduces outcomes its evaluator has never scored? Iryŏx II studies this problem under corrupted pairwise comparisons. New outcomes may have independent unknown utilities outside the old ontology’s convex hull. Each new group is grounded through a cycle of comparisons sharing one persistent operational reference. The main theorem constructs an online evaluator that keeps each score fixed once published and bounds the absolute error of every pairwise score difference by \(2\tau\) across arbitrarily many expansions. Per cycle, at most one initial comparison can be arbitrarily corrupted and the remaining initial comparisons are exact. Honest local follow-ups have absolute error at most \(\tau\), with up to \(b\) arbitrary replies per cycle. The evaluator uses at most \((2b+1)\lceil\log_2 m\rceil\) follow-ups for a cycle of \(m\) outcomes. Two cycles already force the \(2\tau\) bound in the worst case, even with unlimited local follow-ups. A reported improvement greater than \(2\tau\) therefore certifies a true improvement on the operational objective. The manuscript also determines the value of a partial audit. For a cycle with exact healthy initial readings, signed discrepancy \(S\), and \(h\) fault locations compatible with the audit transcript, the exact minimax error of one coherent score vector across all pairs is \(\lvert S\rvert(1-1/h)\). This quantifies what the evaluator can certify before identifying the faulty comparison. A linear-programming formulation extends the analysis to finite feature models with grouped measurement faults and identifies when incomplete observations leave the worst-case error for a new score difference unbounded. A reproducible experiment tests the evaluator on six modular exponentiation tasks. Across 33 proposal rounds, each with one corrupted initial comparison and one false follow-up, the evaluator accepts 32 strictly improving rewrites. The final plans use 49 modular multiplications, down from 430 for the initial plans and 15.5% below the 58 required by binary exponentiation. The proposal mechanism is fixed, the faults are simulated, and the reported gains are in operation count. The release includes the full proofs, executable benchmark, round-by-round trace, exact rational-arithmetic checkers, 19 finite symbolic SMT checks, and a linear-programming cross-check. For recursive self-improvement research, the result gives an explicit condition under which an evaluator can certify successive improvements as the range of outcomes it must score expands.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24354126
Primary Topic
Game Theory and Voting Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Iryŏx II - Sharp Minimax Guarantees for Evaluating New Outcomes in Self-Modifying Systems

Maciej Nowicki, Artificial Hyperintelligence, Eve, wife of Maciej Nowicki
2 links
Zenodo (CERN European Organization for Nuclear Research)
Game Theory and Voting Systems
article

Iryŏx II - Sharp Minimax Guarantees for Evaluating New Outcomes in Self-Modifying Systems

Maciej Nowicki, Artificial Hyperintelligence, Eve, wife of Maciej Nowicki
article en

Abstract

How can a self-modifying system certify that a rewrite improves its objective when the rewrite introduces outcomes its evaluator has never scored? Iryŏx II studies this problem under corrupted pairwise comparisons. New outcomes may have independent unknown utilities outside the old ontology’s convex hull. Each new group is grounded through a cycle of comparisons sharing one persistent operational reference. The main theorem constructs an online evaluator that keeps each score fixed once published and bounds the absolute error of every pairwise score difference by \(2\tau\) across arbitrarily many expansions. Per cycle, at most one initial comparison can be arbitrarily corrupted and the remaining initial comparisons are exact. Honest local follow-ups have absolute error at most \(\tau\), with up to \(b\) arbitrary replies per cycle. The evaluator uses at most \((2b+1)\lceil\log_2 m\rceil\) follow-ups for a cycle of \(m\) outcomes. Two cycles already force the \(2\tau\) bound in the worst case, even with unlimited local follow-ups. A reported improvement greater than \(2\tau\) therefore certifies a true improvement on the operational objective. The manuscript also determines the value of a partial audit. For a cycle with exact healthy initial readings, signed discrepancy \(S\), and \(h\) fault locations compatible with the audit transcript, the exact minimax error of one coherent score vector across all pairs is \(\lvert S\rvert(1-1/h)\). This quantifies what the evaluator can certify before identifying the faulty comparison. A linear-programming formulation extends the analysis to finite feature models with grouped measurement faults and identifies when incomplete observations leave the worst-case error for a new score difference unbounded. A reproducible experiment tests the evaluator on six modular exponentiation tasks. Across 33 proposal rounds, each with one corrupted initial comparison and one false follow-up, the evaluator accepts 32 strictly improving rewrites. The final plans use 49 modular multiplications, down from 430 for the initial plans and 15.5% below the 58 required by binary exponentiation. The proposal mechanism is fixed, the faults are simulated, and the reported gains are in operation count. The release includes the full proofs, executable benchmark, round-by-round trace, exact rational-arithmetic checkers, 19 finite symbolic SMT checks, and a linear-programming cross-check. For recursive self-improvement research, the result gives an explicit condition under which an evaluator can certify successive improvements as the range of outcomes it must score expands.

Zenodo (CERN European Organization for Nuclear Research)
Game Theory and Voting Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon