VLAコーパス選択における対照指示依存性の検証:関連性から意思決定価値へ
From Association to Decision Value: Testing Paired Instruction Dependence for VLA Corpus Selection
ロボット実演コーパスの選別指標として「目標のみ変化時の初回意思決定変化率」を提案し、136の四足歩行ナビゲーションコーパスで事前登録的に検証したが、下流の選択性能への増分寄与は限定的だった。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Nurmukhambet Serikbayev, Abdul Basit, Muhammad Shafique
分類: cs.AI
原文アブストラクト
Choosing among robot demonstration corpora is a ranking problem: an upstream diagnostic must preserve which candidates produce better downstream policies, not merely correlate with average performance. We study paired instruction dependence, the rate at which a demonstrator changes its first decision when only the goal changes. Across 136 independently seeded quadruped-navigation corpora, predictions developed on 56 corpora are evaluated prospectively on 80 held-out corpora. The audit is reliable and associated with downstream paired correctness, and lowers mean absolute prediction error when added to a correctness-aware baseline, but the primary proper-log-score increment is +0.059 nats (95% corpus-bootstrap CI [-0.027, 0.133]) and the prespecified top-20% comparison does not establish an incremental selection gain. An exploratory response decomposition suggests a structural source of this predictive-ranking mismatch: under the tested predictor specification, separating both-correct and both-wrong responses yields larger held-out gains than their unsigned switch statistic. Seed-to-seed agreement indicates that the held-out endpoint retains recoverable rank signal. These results show that counterfactual response structure can be reliable and predictive while providing limited incremental decision value in this setting when compressed into an unsigned statistic, motivating diagnostics that preserve outcome-relevant structure and are validated against the decisions they are intended to support.