{"arxiv_id":"2608.15089","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":6,"sentences":8,"groups":[{"kind":"background","label":"Cites as background","papers":3,"sentences":3,"quotes":[{"arxiv_id":"2605.22166","title":"Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents","url":"/paper/2605.22166","section":"Related Work","sentence":"Life-Harness converts recurring failures into reusable interventions over environment contracts, procedural skills, action realization, and trajectory regulation, then freezes the resulting harness for held-out evaluation [ref] .","intent_p":0.82,"contests_p":null},{"arxiv_id":"2606.09498","title":"Self-Harness: Harnesses That Improve Themselves","url":"/paper/2606.09498","section":"Related Work","sentence":"Self-Harness lets an agent mine its weaknesses, propose harness modifications, and promote them through regression-aware validation [ref] .","intent_p":0.87,"contests_p":null},{"arxiv_id":"2605.26302","title":"Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems","url":"/paper/2605.26302","section":"Related Work","sentence":"AgingBench frames deployed agents as time-evolving systems whose effective behavior can change even when model weights remain frozen [ref] .","intent_p":0.87,"contests_p":null}]}],"unlabelled_sentences":5},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2608.15089"}}