{"total":23,"rows":[{"id":"2410.16270","title":"Reflection-Bench: Evaluating Epistemic Agency in Large Language Models","created":"2024-10-21","cited_by_count":7,"area":null},{"id":"2605.14175","title":"Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2605.30219","title":"When Should Models Change Their Minds? Contextual Belief Management in Large Language Models","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2512.13478","title":"NRR-Core: Non-Resolution Reasoning as a Computational Framework for Contextual Identity and Ambiguity Preservation","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2601.04889","title":"Faithful Summarisation under Disagreement via Belief-Level Aggregation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2603.20162","title":"Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.03255","title":"Do LLMs have core beliefs?","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2608.03699","title":"TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2505.06505","title":"On Definite Iterated Belief Revision with Belief Algebras","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2506.11110","title":"AssertBench: A Benchmark for Evaluating Self-Assertion in Large Language Models","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2601.19933","title":"NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenance","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2607.19360","title":"Lifted State Hypothesis in Large Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.23568","title":"RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2608.27716","title":"PCFBench: A Diagnostic Benchmark for Product Carbon Footprint Estimation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.16245","title":"Metacognitive Steering: Learning the Structure of Scientific Judgment","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26035","title":"Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35308","title":"Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38612","title":"StreamDecisionBench: Evaluating Decisions in Force on Evolving Language Streams","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39608","title":"Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39909","title":"DoGBench: Can Agents Meet Expert Standards for User-Facing Documentation?","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02684","title":"Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18126","title":"Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19215","title":"Narrowing the Collaboration Gap, Probably","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}