Show HN: FinTrace – point-in-time guardrails for financial LLM agents
FinTrace · PITfall Auditable, point-in-time financial research agents & the PITfall leakage-controlled benchmark — every claim traceable to as-filed evidence, zero look-ahead. ⚠️ Research software under active development. See docs/00-STATE.md. 💡 Total LLM cost of both full baseline runs: ≈ ¥4.4 (~$0.6). The naive agent's T3 "forecasting" jump (50% → 80%) and the 82% impossible-question leakage are look-ahead access, not intelligence: on T1-positive tasks the naive agent is flat vs gated (93% vs 92%).
- ▪FinTrace · PITfall Auditable, point-in-time financial research agents & the PITfall leakage-controlled benchmark — every claim traceable to as-filed evidence, zero look-ahead. ⚠️ Research software under active development.
- ▪See docs/00-STATE.md. 💡 Total LLM cost of both full baseline runs: ≈ ¥4.4 (~$0.6).
- ▪The naive agent's T3 "forecasting" jump (50% → 80%) and the 82% impossible-question leakage are look-ahead access, not intelligence: on T1-positive tasks the naive agent is flat vs gated (93% vs 92%).
Hacker News (AI / LLM) files mainly under ai. We currently carry 6,999 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/FredXing1/FinTrace |
| Publication time | Wed, 30 Sep 2026 12:16:37 +0000 |
| Retrieval time | 2026-09-30T12:22:01.681Z |
| Last seen | 2026-09-30T12:22:01.681Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | ozqgVs7Tw7uw · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
FinTrace · PITfall Auditable, point-in-time financial research agents & the PITfall leakage-controlled benchmark — every claim traceable to as-filed evidence, zero look-ahead. ⚠️ Research software under active development. Not investment advice. 🧪 Live demo (no sign-up, no API key): fintrace-demo.streamlit.app — pick a company, a metric, and a knowledge cutoff; watch the point-in-time answer vs what a naive live-data API returns. 📍 Status: baselines complete — 125M as-filed facts, core-200 benchmark (T1 92% / T2 93.3% / T3 50%, bootstrap 95% CI), leakage audit showing a naive live-data agent answers 82% of "impossible" questions with the true future value. See docs/00-STATE.md. 💡 Total LLM cost of both full baseline runs: ≈ ¥4.4 (~$0.6).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.