让多模态检索决策可验证，确保结果可靠且能自动判断是否可信。
CertBind from Multimodal Connectivity to Certifiable Retrieval Decisions
- 基于多尺度理论构建可验证的连接图，实现安全组合。
- 在真实数据上恢复了96.3%的原始检索性能，无损害。
- 适合对可靠性要求高的实际部署场景使用。
轻量级连接器使冻结的多模态编码器在表示层面可组合。但部署后任务决策层面出现新问题：连通路径虽扩展跨模态能力，却可能破坏原有检索性能。本文提出 CertBind，一种针对冻结多模态连接图的可验证组合多尺度理论。节点层面，原生锚点确定任务识别边界；边层面，考虑合同的置信度排名实现全图族错误率控制；路径层面，通过重叠感知预算与校准获得有限样本下的恢复半径。查询层面，该半径生成被覆盖的top-k候选集，当大小等于k时即为点证书。因此，系统保留支持路径为直接返回，仅将标记路径送入恢复，成功恢复时返回‘认证’，无法解决则返回‘回避’。评估显示，共享路径使CLIP R@1从0.524降至0.290，生产级回退恢复至0.963±0.002的纯净检索性能，通过分支保持无害值1.000。CertBind 将多模态可组合性从表示层面延伸至可验证的任务决策层面。
原文摘要 · Abstract (English)
Lightweight connectors make frozen multimodal encoders composable at the representation level. Deployment exposes a second problem at the level of task decisions. A connected route can expand cross-modal reach while changing an established native retrieval capability. We introduce CertBind, a multiscale theory of certifiable composition for frozen multimodal connector graphs. At the node scale, native anchors establish the exact task identification boundary under the stated chart model. At the edge scale, contract-aware conformal ranks provide graph-wide family-wise error control. At the path scale, an overlap-aware budget and clean calibration yield a finite-sample recovery radius under declared conditions. At the query scale, this radius yields a covered top-k candidate set that becomes a point certificate when its size equals k. CertBind therefore retains supported routes as Direct, sends only flagged routes to recovery, returns Certified for decisive recovery, and returns Abstain for unresolved queries. The evaluated C-MCR shared route reduced native CLIP R@1 from 0.524 to 0.290. The production fallback recovered 0.963 +- 0.002 of clean retrieval, while the passing branch recorded a no-harm value of 1.000. CertBind extends multimodal composability from connected representations to certifiable task decisions.
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。