penalize-cross-batch-anchor-over-use-per-query TEC-0153 · proposedPenalize cross-batch anchor over-use, not per-query redundan
Track each prompt-pool anchor's usage as an exponential moving average of its similarity scores across training batches and add a stop-gradient saturating-min penalty that suppresses similarity for over-used anchors, leaving the top-K retri
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Track each prompt-pool anchor's usage as an exponential moving average of its similarity scores across training batches and add a stop-gradient saturating-min penalty that suppresses similarity for over-used anchors, leaving the top-K retri Filed by the drafting stage from Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs (2609.22977) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: MSE/MAE on six multivariate long-term benchmarks at four horizons plus M4, against similarity-based LLM forecasters and a paired lambda_cov=0 ablation with identical code, data and seeds; best or second-best MSE in 18 of 24 cells, and an eight-seed paired test significant on ETTh1-96 (7/8 seeds improved, p=0.039).. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.