LASER:针对长程协议依赖的可废止证书搜索
LASER: Defeasible Certificate Search for Long-Range Protocol Dependencies
AI总结:
LASER是针对长程协议依赖的可废止证书搜索方法,通过显式义务处理缺失支持与未解决修正,在91个BehaviorCheck族上提升Joint Edge+Proof性能并减少错误发现,瓶颈在于类型化义务闭合。
摘要:
协议规范很少在一处就说明可执行行为:一个转换可能从远程控制块继承其源状态,仅通过编号命名其事件,且仍需接受后续修正。因此仅恢复附近子句是不够的;系统必须组装源关联证书,并确定是否有更强的规则适用。我们提出LASER,一种针对稀疏、可废止协议证据的携带证明搜索方法。LASER将缺失的支持和未解决的修正表示为显式义务,搜索类型化证据路径,并让感知发生的符号检查器单独决定证书是否保证、反驳或留下行为未决。在匹配2K预算下的91个BehaviorCheck族上,LASER在两个模型族上将Joint Edge+Proof性能提升超过最强本地读取器(Δ=+.132,p=.017;Δ=+.198,p<.001),同时将错误发现减少2-3倍。受控重放归因于增益及其局限:仅参考路由或确定性引用扩展均未超过本地基线;全文本读取(29-65K token)、两轮迭代检索甚至神谕最小证书证据均无法达到LASER的效果,将瓶颈定位在类型化义务闭合而非证据访问上。权威损坏重放显示源关联错误仅导致弃权(不执行),而唯一的不安全保证机制是将Held勘误表错误记录为Verified,且仅局限于该勘误表的族。因此LASER改进了长程依赖恢复,同时将不完整证据和不确定权威转换为显式剩余义务,而非不受支持的行为。
英文摘要:
Protocol specifications rarely justify executable behavior in one place: a transition may inherit its source state from a remote control block, name its events only by number, and remain subject to a later correction. Recovering the nearby clause is therefore insufficient; the system must assemble a source-linked certificate and determine whether any stronger rule applies. We introduce LASER, a proof-carrying search method for sparse, defeasible protocol evidence. LASER represents missing support and unresolved corrections as explicit obligations, searches typed evidence routes, and lets an occurrence-aware symbolic checker alone decide whether a certificate warrants, refutes, or leaves a behavior unresolved. On 91 BehaviorCheck families under a matched 2K budget, LASER improves Joint Edge+Proof over the strongest local reader on two model families ($Δ=+.132$, $p=.017$; $Δ=+.198$, $p<.001$) while cutting false discoveries by 2--3$\times$. Controlled replays attribute the gain and its limits: neither reference routing nor deterministic citation expansion alone exceeds the local baseline; whole-document reading (29--65K tokens), two-round iterative retrieval, and even oracle minimal-certificate evidence all fail to reach LASER, localizing the bottleneck in typed obligation closure rather than evidence access. An authority-corruption replay shows source-link errors only cause abstention, while the only unsafe-warrant mechanism is mis-recording a Held erratum as Verified, confined to that erratum's family. LASER thus improves long-range dependency recovery while converting incomplete evidence and uncertain authority into explicit residual obligations rather than unsupported behavior.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。