This paper presents LSG (Lightweight Supervised Gate), a shallow calibrated ensemble architecture for write-time memory novelty filtering in long-horizon LLM agents. Contemporary agentic memory systems rely on cosine similarity thresholds for filtering incoming conversational turns — a heuristic that suffers from O(N)...
Majumder Prithibe· Zenodo (CERN European Organi...· 0 citations
How can a small cue evoke a much larger pattern than appears to be explicitly present in the cue itself—and how can the same reconstructive ability eventually generate meanings that are no longer adequately constrained by their source? This paper develops the concept of the reconstructive signature: a carrier whose sou...
Reece O'Sullivan· Zenodo (CERN European Organi...· 0 citations
Modern language model training applies a uniform gradient update to every token, regardless of its information content. We introduce NS-weighted training, which filters training examples by their Shannon information. On a 50MB sample of the C4 web corpus, unigram NS-data filtering matches a 1000-step standard training...
Orders Of Magnitude LLC· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
資金曲線を見せて「最大ドローダウンは N pips でした」と書くことがある。だが合計は足す順番に依らない。どう並べ替えても同じであり、それは足し算がそういうものだからで、測定の結果ではない。一方で最大ドローダウンは途中経過を見る量であり、負けが固まって来れば深くなり、散らばって来れば浅くなる。同じ取引の集合でも並べ方で変わる...
Yuuki Yamagishi· Zenodo (CERN European Organi...· 0 citations
Let b(n) be a strictly increasing sequence of positive integers satisfyinglim_{n→∞} b(n+1)/b(n) = 1. Define a recurrence by taking a_n to be the element of b nearest to a_{n-1} + a_{n-2}, with ties broken by taking the smaller element. We prove that for any initial values a_1, a_2 in b, lim_{n→∞} a_n / a_{n-1} = φ := (...
Yixiang Wang· Zenodo (CERN European Organi...· 0 citations
