← 研踪 PaperTrailarXiv:2611.21096 · v1
Inference Equivalence and Quotient Coding
首次提交 2026-11-16 21:42
版本更新 2026-11-16 21:42
雷达观测 2026-11-17 17:11
摘要
Incomplete observations can admit multiple physical interpretations without making every task conclusion ambiguous. Recovering all compatible scenes is often unnecessary, whereas indiscriminate compression may change which claims are justified. We ask which distinctions among observation-compatible interpretation sets must be retained to preserve every valid conclusion of a specified task. We first define inference validity as truth across all physically compatible states and characterize it, under a closedness condition, by distances to physically realizable falsifying measurements. For a finite semantic claim family ordered by specificity, the Exact Inference Frontier forms the unique minimal antichain generating all valid claims. We then define inference equivalence between compatibility sets and construct a canonical quotient code from their frontiers. Among deterministic codes admitting exact inference decoding, it induces the coarsest partition, minimizing the number of distinguishable code values rather than storage or computation. Finally, we characterize inference errors from learned compatibility sets, derive conditions for exact inference preservation despite set errors, and evaluate an asymmetric learning surrogate under distribution shifts. On a registered finite bank, 145 compatibility sets yield 31 quotient codes with unchanged valid-claim sets. Across geometry, mechanism, and joint shifts, learned estimates exhibit different accuracy-specificity trade-offs. On 1,962 official HRSID test images, 1,913 distinct candidate sets induce only 36 seven-claim inference signatures, while a visual 3-NN baseline achieves 87.31% precision on issued claims.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 21:42 · 最新观测版本
Inference Equivalence and Quotient Coding
Incomplete observations can admit multiple physical interpretations without making every task conclusion ambiguous. Recovering all compatible scenes is often unnecessary, whereas indiscriminate compression may change which claims are justified. We ask which distinctions among observation-compatible interpretation sets must be retained to preserve every valid conclusion of a specified task. We first define inference validity as truth across all physically compatible states and characterize it, under a closedness condition, by distances to physically realizable falsifying measurements. For a finite semantic claim family ordered by specificity, the Exact Inference Frontier forms the unique minimal antichain generating all valid claims. We then define inference equivalence between compatibility sets and construct a canonical quotient code from their frontiers. Among deterministic codes admitting exact inference decoding, it induces the coarsest partition, minimizing the number of distinguishable code values rather than storage or computation. Finally, we characterize inference errors from learned compatibility sets, derive conditions for exact inference preservation despite set errors, and evaluate an asymmetric learning surrogate under distribution shifts. On a registered finite bank, 145 compatibility sets yield 31 quotient codes with unchanged valid-claim sets. Across geometry, mechanism, and joint shifts, learned estimates exhibit different accuracy-specificity trade-offs. On 1,962 official HRSID test images, 1,913 distinct candidate sets induce only 36 seven-claim inference signatures, while a visual 3-NN baseline achieves 87.31% precision on issued claims.
查看此版本解读 →查看此版本原文 ↗