arXiv:2601.19933cs.CLcs.AI2026-01被引 1

提出可检验的模糊状态维护接口,让模型保留多解并可控更新。

NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenance

  • 设计有类型的状态接口与显式更新规则,支持多解状态传递。
  • 2740次测试中记录权重熵零违规,验证规则有效性。
  • 适合需要可追溯、可验证推理过程的高可靠性系统开发。

模糊输入通过接口进入下游系统时,常被强制单一分辨。即使外部化多种可能,其表示与激活仍依赖更新规则。本文在非消歧推理(NRR)框架下,提出一种有类型的外部文本到状态接口(phi: T → S)及明确的状态更新契约。该接口生成带类型(v,c,w,m)的记录,声明的操作使记录传递可检查,而记录权重熵准则用于独立测试归一化权重集中度。契约涵盖抑制、校准、延迟消歧、矛盾保留融合与时间持久性。在580个构造状态对上,执行2740次操作-状态测量,非违规转移与校准/恒等检查均实现0%权重熵违规;统一减法对比在减法增大时分别出现1.7%、6.1%和17.8%违规。另一次68输入构造审计显示,基于规则与存档大模型辅助流程下,多个正权重记录平均熵为1.087比特,含日语标记集实例。熵准则本身不保证记录身份、数量、语义充分性或端到端行为提升。代码库提供确定性重运行、存档提示/输出、转录审计及固定18组大模型案例复测。因此,Phi将状态维护变为有类型、可执行、可证伪的接口:记录传递可检视,归一化权重集中度可在下游承诺前单独测试。

原文摘要 · Abstract (English)

Ambiguity-bearing inputs reach downstream systems through interfaces that favor a single resolved response before later context arrives. Even when alternatives are externalized, their representation and relative activation depend on the update rule. We address this state-maintenance problem within Non-Resolution Reasoning (NRR) by specifying a typed external text-to-state interface and explicit state-update contract. A mapping (phi: T -> S) constructs typed (v,c,w,m) records; declared operators make record carry-forward inspectable, while a record-weight entropy criterion separately tests normalized-weight concentration. The contract covers dampening, calibration, deferred resolution, contradiction-preserving integration, and temporal persistence. Across 580 constructed states/pairs, an executable suite performs 2,740 operator-state measurements. Tested non-violating transitions and calibration/identity checks show 0% record-weight entropy violations; a uniform-subtraction comparison violates the criterion at 1.7%, 6.1%, and 17.8% as subtraction increases. A separate 68-input construction audit finds multiple positive-weight typed records (mean record-weight entropy H = 1.087 bits) under the reported rule-based and archived LLM-assisted procedures, including a Japanese marker-set instantiation. The entropy criterion does not by itself certify record identity or cardinality, semantic adequacy, or end-to-end behavioral improvement. The repository provides deterministic reruns, archived prompt/output artifacts, transcript audit, and a fixed 18-set LLM-case sanity rerun. Phi therefore turns retained-state maintenance into a typed, executable, and falsifiable interface: record carry-forward is inspectable in declared operators, and normalized-weight concentration is separately testable before downstream commitment.

逻辑推理状态管理可验证性大模型

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。