Skip to content

Category

small language model

2,898 papers

#small language model Open access Sep 2026

Bars Cut by Tick Count Are a Different Clock from Bars Cut by the Clock: The Move Becomes Uniform (All 20 Cells; Session Ratio 1.7390 Against 3.5268) While the Directional Information Does Not [F018]

「ティック足にすると値動きの大きさがそろう」「時間で刻むと暇な時間帯の足が無駄になる」という言い方がある。だが「ティック足の方が良い」だけでは何も言えない。何がそろうのかを言っていないからである。そして比べ方に落とし穴がある。ティック足の方が細かければ値動きが小さいのは当たり前なので、比べるなら一本あたりの時間の中央を...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

Self-Normalization Brings In the Window You Divided By — The Layer Ratio Falls from 1.3795 Undivided to 1.0440 Divided, and the Median z Moves 4.3363 Times Across the Hours [F039]

「直近の平均で割って正規化した」。指標ではよく行われる。だが割り算は、分子と分母の両方を答えに入れる操作である。z が大きいのは分子が大きいからかもしれないし、分母が小さいからかもしれない。そして分母は「直近 N 本」から作られるので、z は N 本前までの相場の状態を必ず持ち込んでいる。本稿の分離子は「何で割ったか」である。分...

Yuuki Yamagishi · 0 citations
#graph neural networks Open access Sep 2026

Structure-Aware Dependency Retrieval for Repository-Level Code Completion via Graph Attention

When Large Language Models (LLMs) write code inside an existing repository, the quality of their output depends heavily on the context they are given. The difficulty is that a function’s docstring rarely mentions the base class, callee, or field the function actually depends on. Lexical and dense retrievers both treat...

Parmeet Chani, Amanpreet Kaur, Dr. Gursimran Kaur · 0 citations
#small language model Open access Sep 2026

Structured PREreview of "Evidence Graph Consistency in Retrieval-Augmented Generation: A Model-Dependent Analysis of Hallucination Detection"

This Zenodo record is a permanently preserved version of a Structured PREreview. You can view the complete PREreview at https://prereview.org/reviews/22904739. Does the introduction explain the objective of the research presented in the preprint? Yes It clearly explains the objective. The introduction states plainly th...

Mayur Jain · 0 citations
#small language model Open access Sep 2026

Scalable Oversight Across Generative Visual AI: Toward Visual Storytelling for Everyone

Generative visual AI has advanced by scaling data and compute, but its next bottleneck is oversight: the expert signals that evaluate, reward, and teach models what ``good'' looks like. Providing such oversight is increasingly difficult because foundation vision-language models now match or surpass most humans at the s...

Zhiqiu Lin · 0 citations
#small language model Open access Sep 2026

labplan: exact measurement planning, calibration and audit trails for any lab model

Fixed Model.jacobian (used by information, design and fit) took its finite-difference step as 1e-6 * max(|theta|, 1e-3). For a parameter smaller than 1e-3 in its own units the step, 1e-9, was too coarse; for a time constant of 1e-9 s it was the size of the parameter itself. The planned error bars then depended on the u...

Tanvir M. Mahim · 0 citations
#small language model Open access Sep 2026

The "True Range" in ATR Is, Most of the Time, Just the Range — At the Median, ATR ÷ the Mean of the Range Alone Is Exactly 1.0000 and the Gap Binds on Only 0.0370 to 0.0897 of Bars, Yet at the Weekly Open It Binds 11.3968 Times as Often [F047]

ATR は「平均的な値幅」と説明される。だが中身の真の値幅は TR = max(高値 − 安値, |高値 − 前の終値|, |安値 − 前の終値|) であって、前の終値を含んでいる。つまり足の中の動きだけでなく、足と足のあいだに起きたことも測っている。この二つは別の量である。片方は市場が開いているあいだの動きで、もう片方は市場が止まっていたあいだに起...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

The Three-Way Ichimoku Signal Does Nothing Beyond Cutting the Count — The Count Falls by a Factor of 3.0700 While the Directional Value Moves 0.1922, and the Gap of +0.1984 Against Random Conditions at the Same Pass Rate Falls Below the Standard Error of 0.6338 [F052]

一目均衡表の「三役好転」は、三つの条件を同時に満たした状態を指す。①転換線が基準線の上にある、②価格が雲の上にある、③遅行スパンが二十六本前の価格の上にある、の三つである。条件を足せば件数は減る。それは定義から決まっている。問題は、減った分のほかに何かが起きているかである。本稿の分離子は、条件をいくつ掛けたかである。銘柄...

Yuuki Yamagishi · 0 citations
#small language model Dataset Open access Sep 2026

Research Gap Discovery Dataset: LLM-Extracted Limitations and Research Gaps from 3,326 Scientific Papers

This dataset contains 3,326 recent arXiv computer science papers (first versions dated 16 March to 17 July 2026). For each paper, a large language model read the title and abstract and wrote one sentence each on the paper's main limitation, an open research gap for future work, and why that gap matters. It was built to...

Mounata Saha · 0 citations
#small language model Open access Sep 2026

RAGGlass: Beyond the Black Box — A User-Centric Glass Box Framework for Inspecting and Diagnosing Retrieval- Augmented Generation

Retrieval-Augmented Generation (RAG) mitigates factual hallucinations in Large Language Model (LLM) workflows by extracting corroborating passages from an external corpus prior to response synthesis. Nevertheless, conventional production pipelines operate as opaque black boxes, obscuring intermediate operations such as...

khushboo pingle · 0 citations
#small language model Open access Sep 2026

A Naive t Value Inflates with the Number of Observations per Day: Changing the Bar Size Moves the Count by a Factor of 11.9751, and Even a Synthetic Series with No Edge Exceeds 2 in 0.5437 of Five-Minute Cells [F014]

手法の成績に t 値が添えられていることがある。その多くは、標準偏差を件数の平方根で割ったものを分母にした素朴な t である。だが同じ日の観測は独立でない。同じ相場の同じ動きを、何度も数えているからである。一日あたり m 件、日の中の相関を ρ とすると、標準誤差の比は √(1 + (m − 1)ρ) になる。ρ が 0 なら膨らまず、1 なら √m 倍にな...

Yuuki Yamagishi · 0 citations
#small language model Open access Sep 2026

When a Judgment Layer's Self-Reported Fields Lie: Cost, Latency and the Failure Boundary of Three Judgment Layers on the Same Items

Handing the judgment work in a long-horizon task to a cheap, specialised judge is a divisionof labour usually sold on the grounds that it **saves money**. This paper measures that claimagainst a controlled three-way comparison, and reports four claims — one of which our owndata refutes. **First, cost is not the binding...

Perry Link · 0 citations

From tech blogs

See all →

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.