mlsanityData to 14 Oct 2026

Certify or Refuse: A Cross-Model Map for Selective Risk Control with Coverage Floors under Covariate Shift

arXiv 2608.10893 ↗First posted 11 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Certified selective predictors attain whatever coverage they attain; operators impose an automation floor: answer at least a β-fraction of shifted target traffic with at most an α-fraction of answers wrong. Under bounded-ratio covariate shift we prove the Floor Certification Map: once that floor must be certified alongside the selection-conditioned risk α, certification acquires a feasibility frontier and a two-resource complexity map, additive up to constants: risk in labeled source, the floor in unlabeled target samples. The rates are local, needing a regular frontier margin, slack below the local-regime threshold, and lattice conditions: pre-registered with a lattice margin for the upper bounds, compatible per-slack for the lower. The displayed split is the operational route; oracle weights also allow a labeled-source floor estimate. Three model-tagged results: a lower bound (Model-B), a matching oracle-weight upper bound (Model-A), and an implementable upper bound (Model-B') valid under a pre-registered exact stratified-shift model with nuisance cost priced explicitly. The match is across these models rather than a single-model minimax theorem, and necessarily so: over the full bounded-ratio class no unknown-weight procedure matches at any sample size (Model-B is inconsistent, witnessed at α=β=1/2). The nuisance's necessity is only partially settled. Complexity tracks a localized accepted-region functional, not global effective sample size (ESS), on both sides, though a fixed-ESS separation theorem is left open; both lower-bound axes vanish as β→0, so the floor creates the map. Empirically, the registered bite family diverges with log-log slope -2.002 within its pre-registered band; a 1,024-cell audit records 0 violations where the formal certificates fire; and a single-corpus SQuAD-to-NewsQA feasibility audit returns honest refusal.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 64 references that are in the map. First posted on arXiv 11 Aug 2026.

Builds on

21 of 64 references.

References · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
  3. 2024Mitigating LLM Hallucinations via Conformal Abstentioncited by 59
  4. 2023Model-free selective inference under covariate shift via weighted conformal p-valuescited by 29
  5. 2026Conformal Selective Prediction with General Risk Controlcited by 12
  6. 2025Selective Conformal Risk Controlcited by 11
  7. 2025LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systemscited by 7
  8. 2026RACER: Risk-Aware Calibrated Efficient Routing for Large Language Modelscited by 7
  9. 2023Double Debiased Covariate Shift Adaptation Robust to Density-Ratio Estimationcited by 6
  10. 2025Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shifts with Unlabeled Datacited by 5
  11. 2026A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Controlcited by 5
  12. 2026Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shiftscited by 4
9 more
  1. 2026BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generationcited by 4
  2. 2026Reliable Abstention under Adversarial Injections: Tight Lower Bounds and New Upper Boundscited by 3
  3. 2026Conformal Risk Control under Non-Monotone Losses: Theory and Finite-Sample Guaranteescited by 3
  4. 2026Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Modelscited by 3
  5. 2025Conformal Prediction Adaptive to Unknown Subpopulation Shiftscited by 2
  6. 2026Multi-Distribution Robust Conformal Predictioncited by 2
  7. 2026KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matchingcited by 2
  8. 2026Chance-Constrained Inference for Hallucination Risk Control in Large Language Modelscited by 1
  9. 2026Multicalibration Boosting: Theory, Convergence, and Transferabilitycited by 1

Built on by

Not cited yet.