Odds-Shift Slippage in One-vs-Rest Rankers: Diagnosing and Repairing Reweighting-Induced Top-K Errors

arXiv:2609.13810 · cs.IR, cs.LG · Submitted 2026-09-12 · Read on arXiv

cs.IR, cs.LG

Submitted: 2026-09-12

Updated: 2026-09-12

Comments: 10 pages, 4 figures, 2 tables; 9-page supplement as ancillary file. Code, result files and paper sources: https://github.com/souldrive7/odds-shift-slippage (Zenodo DOI 10.5281/zenodo.22719148)

Code: https://github.com/souldrive7/odds-shift-slippage

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 2× in this paper · explained in 7 episodes
• Benchmark — 1× in this paper · explained in 2 episodes

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models?
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory
• Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition