anthropics/claude-code v2.1.251
## What's changed - Added `PreModelSwitch` and `PostModelSwitch` hook events (block, confirm, or annotate a model switch); `SessionStart` resume hooks now receive session staleness
01 DAILY RESEARCH SIGNALS / 2026.09.01
把市场噪声
压缩成可研究的信号。
聚合量化论文、开源项目与 AI 工程进展。每条信号经过筛选、排序与结构化，帮助研究者更快抵达真正重要的信息。
浏览今日信号 ↓
1 个数据源延迟，其余管线运行正常
02 CURATED INDEX
今日信号库
按内容类型浏览，或直接搜索标题与标签。
INDEXED 15
01 / REP
GitHub
SELECTED SIGNALS 04
openai/codex rust-v0.152.0-alpha.7
Release 0.152.0-alpha.7
TauricResearch/TradingAgents v0.4.0
## Summary Look-ahead and point-in-time fixes across the data and memory layers, clearer decision signals, working CLI checkpoint resume, and the GPT-5.6 / GLM-5.3 models.
ChatboxAI/Chatbox v1.22.3
## v1.22.3 - 2026.08.09 ### Downloads - macOS (Apple Silicon): [Chatbox-1.22.3-arm64.dmg](https://download.chatboxai.app/releases/Chatbox-1.22.3-arm64.dmg) - macOS (Intel): [Chatbo
02 / PPR
论文
SELECTED SIGNALS 11
What survives honest evaluation? Leakage-safe, search-aware assessment of LLM-driven trading strategy discovery
Large language models (LLMs) are increasingly used to discover trading strategies, and much of the resulting literature shares a methodological weakness: many candidate strategies
Market-Informed Valuation of GMMB Riders with Surrender Options under a Heston Stochastic-Local Volatility Model
We develop a market-informed valuation framework for guaranteed minimum maturity benefit (GMMB) riders with rational surrender under the Heston stochastic-local volatility (SLV) mo
Can ChatGPT Forecast Stock Price Movements?
Large language models were not originally designed to forecast financial markets.
RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants.
CURA: Certified Runtime Alarms for Computer-Use Agents
Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (CUAs) it fails precisely where oversight matters.
Pricing and Calibration of Bitcoin Inverse Options via the Rough Bergomi Model
Bitcoin inverse options, traded on the Deribit exchange and settled in the underlying cryptocurrency rather than in fiat currency, combine extreme and genuinely rough volatility dy
Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf
Search rankings are valuable because human attention is scarce and sequential.
TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervision
Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are generally more reliable but mor
HARTS: Efficient Agentic Reinforcement Learning for Hybrid-Attention Models over Arbitrary Rollout Trees
Agentic reinforcement learning (RL) often produces irregular rollout trees with shared histories.
Disaffection at Work: Employee Responses to Job-Related Information
Quiet quitting reflects a form of worker disaffection that operates along the intensive margin of labor supply rather than through job exit.
Do Customer Disclosures Affect Suppliers' Internal Capital Allocation Decisions?
This study examines whether customer disclosures affect how supplier firms allocate capital across business segments.