# When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing

arXiv: https://arxiv.org/abs/2609.33505 · HTML: https://mlsanity.com/paper/2609.33505/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 48 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 30 of 37)

- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Attention, Learn to Solve Routing Problems!](https://mlsanity.com/paper/1803.08475/) (2018)
- [Neural Combinatorial Optimization with Reinforcement Learning](https://mlsanity.com/paper/1611.09940/) (2016)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization](https://mlsanity.com/paper/1809.05504/) (2018)
- [Show Your Work: Improved Reporting of Experimental Results](https://mlsanity.com/paper/1909.03004/) (2019)
- [Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities](https://mlsanity.com/paper/2307.13565/) (2023)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [Learning to Delegate for Large-scale Vehicle Routing](https://mlsanity.com/paper/2107.04139/) (2021)
- [Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions](https://mlsanity.com/paper/2106.01798/) (2021)
- [Croissant: A Metadata Format for ML-Ready Datasets](https://mlsanity.com/paper/2403.19546/) (2024)
- [Measurement to Meaning: A Validity-Centered Framework for AI Evaluation](https://mlsanity.com/paper/2505.10573/) (2025)
- [FinTextQA: A Dataset for Long-form Financial Question Answering](https://mlsanity.com/paper/2405.09980/) (2024)
- [CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization](https://mlsanity.com/paper/2504.04310/) (2025)
- [Destroy and Repair Using Hyper Graphs for Routing](https://mlsanity.com/paper/2502.16170/) (2025)
- [The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models](https://mlsanity.com/paper/2510.23191/) (2025)
- [FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization](https://mlsanity.com/paper/2505.16952/) (2025)
- [BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks](https://mlsanity.com/paper/2410.12974/) (2024)
- [Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science](https://mlsanity.com/paper/2506.04410/) (2025)
- [Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP](https://mlsanity.com/paper/2510.21453/) (2025)
- [DataSP: A Differential All-to-All Shortest Path Algorithm for Learning Costs and Predicting Paths with Context](https://mlsanity.com/paper/2405.04923/) (2024)
- [Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation](https://mlsanity.com/paper/2505.19804/) (2025)
- [RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation](https://mlsanity.com/paper/2601.04350/) (2026)

## Abstract (arXiv)

Modern learned systems increasingly combine learned components with search, repair, or external solvers. Benchmarks often measure the resulting end-to-end system, while scientific claims may concern only one component, creating an attribution problem: evidence can fail to support the requested component-level claim while still supporting a positive conclusion about the larger system. Existing evidence-to-claim methods primarily calibrate claim strength. We argue that composite systems require a second dimension: scientific subject. We address this problem with subject-typed claim licensing, which separates weaker conclusions about the requested subject from positive but non-substitutive credit about another subject. We instantiate this idea in SCOPE-Routing for preference-conditioned multigraph routing. Non-authors reproducibly apply the declared semantics; held-out review yields fewer reference-relative upward deviations than unstructured review, while the difference from a strong evidence checklist remains unresolved; and a controlled routing study shows that score-optimal and claim-eligible methods can differ while valid hybrid-system credit is preserved. These results motivate treating claim strength and scientific subject as distinct dimensions of evidence-based evaluation.