AI Transparency Statement

Last reviewed: 2026-04-24 · Corrected: 2026-09-24 · Operating entity: Quintessentia Network Inc. (operating as Quintarthai)

Version history

2026-09-24	Corrections. The Sentiment Analysis entry described a classifier that does not run in production; it is retired from this page (headlines are shown unscored). The Base LLM, Tool-calling and Prompt rows now describe the routing, loop and prompt in force.
2026-04-25	Quinn primary inference migrated to Cerebras qwen-3-235b for higher throughput; Groq Llama 3.3 70B retained as automatic fallback. Provider chain hardened; local Ollama retained as the last-resort fallback. (For the chain in force today, see the Base LLM row below.) Corpus expanded to 415 chunks.
2026-04-24	v2: per-engine sections rewritten with architecture / training / evaluation / limitations. Three additional sections added (Composite Intelligence Score · Technical Score · Sentiment Analysis). Cross-border processing notice for Quebec users added to /legal/disclosures.html.
2026-04-23	Quinn corpus v1 frozen at 415 chunks across 13 jurisdictions. 21-test E2E regression suite passing 21/21.
2026-04-16	Initial AI transparency statement (v1).

1. Systems in Use

Quintarthai operates six distinct AI systems. Each is described in detail below.

2. Quinn — Conversational RAG Assistant

Architecture

Base LLM	Quinn routes across several hosted providers — Cerebras · Groq · SambaNova · OpenRouter · NVIDIA · Cloudflare Workers AI · GitHub Models — and also uses a self-hosted Ollama model (Boston, USA), which some code paths call directly and which serves as the last-resort fallback. Which provider answers depends on the code path and provider availability. Specific model names are not published here because the routing configuration changes. A Mistral (EU) tier and an Anthropic tier exist in the code but are not configured in production and receive no traffic. There is no user-selectable local-only mode.
Retrieval	Qdrant 1.9 vector DB · `quintarth-regulations-v1` collection · Ollama `nomic-embed-text` 768-dim embeddings.
Tool-calling	Tool-calling loop (up to 4 rounds per answer) over deterministic data tools — 81 registered as of 2026-09-24, including regulatory search, Sharia screening, insider filings and quotes.
Prompt	System prompt v59 (2026-09-23) — requires a `search_regulations` call first for regulatory questions, refuses buy/sell/hold recommendations and house valuation verdicts, does not adapt answers to an individual’s circumstances, and cites retrieved passages with jurisdiction + section.

Training & Grounding Data

Retrieval corpus: 415 chunks across 13 jurisdictions — NI 43-101 (CA mining), S-K 1300 (US mining), NI 45-106/62-103/62-104/51-102 (CA securities), OSC/AMF/ASC/BCSC guidance, TSX/TSX-V listing manuals, NASDAQ rules, FINTRAC, MI 61-101, NI 33-109/31-103, CBCA, NI 51-101 (oil & gas), CIRO, Reg S-K/S-X/D/A+, Rules 144/144A, Forms 8-K/10-K/10-Q/20-F, SOX, Volcker, FCPA, OFAC, PIPEDA, CASL, MJDS, mining operations, deposit types, commodities, DeFi primitives, IFRS 9/15/16, ASC 606/740/805, VWAP/TWAP/Almgren-Chriss.
Base model training: We do not control the pre-training corpus of any third-party model we route to. See each provider’s published model cards for the models they serve.
No user data is used to train any model. User queries and uploaded documents are processed in-session and not used for weight updates.

Evaluation Methodology

21-test E2E regression suite covering core retrieval, answer grounding, refusal behavior on advice-seeking questions, and tool-call correctness. Run on every deploy. Current pass rate: 21/21 on 2026-04-23.
Retrieval quality sampled on 8 representative queries with similarity thresholds (e.g. “NI 43-101 resource classification” → CP §2.1 @ 0.785; “EigenLayer restaking” → 0.771).
Hallucination mitigation: regulation-grounded answers attach the retrieved source passages as citations, and Quinn declines questions that imply a specific investment recommendation.

Known Limitations

Base LLMs may produce plausible-but-incorrect statements. Always verify any factual claim against the original filing linked in the citation.
Regulatory corpus is current as of 2026-04-23 and does not include rule changes since that ingestion date.
Cerebras, Groq, SambaNova, OpenRouter, NVIDIA, Cloudflare Workers AI and GitHub Models are third-party inference providers. Outages or rate-limiting on their side degrade Quinn availability; the platform fails over between them automatically and, as a last resort, to the self-hosted Ollama model. See status.
Quinn does not know your personal circumstances and will not give personalized financial advice. Refusal is intentional.

3. Geo-LLM — Mining-Geology Specialist

Architecture

Model	Same provider stack as Quinn (see the Base LLM row above) but with a specialized retrieval namespace and system prompt tuned for mining terminology (orogenic, porphyry, VMS, IOCG, SedEx, Carlin deposit types; SAG/flotation/autoclave processing; NI 43-101 resource classification).
Retrieval	Subset of the Quinn corpus: ~160 chunks specific to mining geology, technical reports, and commodity markets (gold, silver, copper, lithium, uranium, iron ore).

Evaluation

Domain-specific test set: resource-classification distinctions (inferred vs indicated vs measured), cut-off-grade sensitivity questions, QA/QC protocol descriptions.
Retrieval quality target: ≥ 0.75 similarity on domain queries.

Limitations

Not a substitute for a Qualified Person's review. Any number quoted from a 43-101 must be verified against the original technical report.
Deposit-type classification may be ambiguous at property boundaries; Geo-LLM flags low-confidence answers explicitly.

4. Delisting Risk Composite Scorer

Architecture

Not an LLM. Deterministic 0-100 composite score computed from 12 declared sub-factors, each with a published weight. Output is reproducible given the same inputs.

Sub-factors	float concentration, insider-share ratio, institutional ownership, restricted-share overhang, promotional language NLP score (text classifier), jurisdiction risk (binary + regional), shell/reverse-merger flags, operations-country listing, audit-firm tier, minimum bid compliance, market-cap threshold, public-float compliance.
Language classifier	Lightweight keyword + pattern matcher (NOT an LLM). Scans press-release text for known promotional phrases (“game-changer”, “revolutionary”, superlative density). Deterministic output.

Evaluation

Back-tested against the 2023–2025 NASDAQ delisting notice population: composite score ≥ 70 correctly flagged 58% of eventual delistings in our sample window (n = 143). Not a guarantee — a prediction of elevated risk, not certainty.
Each sub-factor's contribution is displayed in the UI so users can audit the reasoning.

Limitations

Score reflects publicly available data only. Private events (regulatory investigations, undisclosed litigation) are not captured.
Language classifier is English-only. Non-English press releases are not scored.
Risk score is not a recommendation. A high score means “worth further research” — it does not mean “sell” or “avoid.”

5. VPIN Microstructure Estimator

Architecture

Not an AI model. Deterministic implementation of the Volume-Synchronized Probability of Informed Trading metric from Easley, López de Prado & O'Hara (2012), “Flow Toxicity and Liquidity in a High-Frequency World.”

Inputs	Trade-volume time series (bucketed by fixed volume slices), buy/sell volume imbalance.
Output	Rolling VPIN estimate [0..1] indicating order-flow imbalance.

Limitations

VPIN is an estimate of order-flow toxicity, not a prediction of price direction. Academic literature is divided on its forward-predictive power.
Quality depends on tick-data granularity. We estimate from 1-minute OHLCV in the absence of full tick feeds, which introduces bucketing error.
Presented as a research metric, not a trading signal.

6. Cross-Border FX-Adjusted Spread Engine

Architecture

Deterministic finance formula. Given a dual-listed pair (TSX vs NYSE/NASDAQ), pulls current price on both legs, converts CA leg to USD via live FX, computes percentage spread. Adds volume-divergence ratio (CA volume ÷ US volume) as a secondary signal.

Limitations

Quotes may be delayed up to 15 minutes. Posted spread is not executable.
Ignores transaction costs, borrow costs, tax treatment, and currency-hedge costs. Users must apply their own cost stack to evaluate whether a spread is trade-able.
FX feed: one provider; we display the rate used in each calculation for transparency.

7. Answer feedback (thumbs up/down)

What happens to it

When you rate a Quinn answer, the rating is stored with the question, the answer and the model that produced it, linked to your account, and counted in an internal statistics view. Ratings are not used to change retrieval or any model, and no model is fine-tuned on them. They are deleted with your account.

Limitations

No user content is sent to LLM providers for their training; we do not have training-data sharing agreements with Cerebras, Groq, SambaNova, Mistral, OpenRouter, Anthropic, Meta, Alibaba (Qwen team), or DeepSeek.

8. Composite Intelligence Score (Stock Report Card)

Architecture

Meta-score, not an LLM. Deterministic weighted aggregate of five sub-scores produced by other engines. The aggregator math is reproducible: same inputs ⇒ same output. The sub-scores themselves vary — some are deterministic (Risk, Volume), some are AI/ML (Sentiment), some are mixed (Fundamental, Insider Activity).

Sub-scores	Risk inverted (20%) · Fundamental (30%) · Momentum (25%) · Volume (15%) · Insider Activity (10%). Each on 0–100.
Confidence band	±3 large-cap · ±5 mid-cap · ±8 small-cap · ±12 micro-cap · ±18 nano-cap. Wider band signals lower reliability.
Interpretation labels	80–100 Strong · 60–79 Moderate · 40–59 Neutral · 20–39 Weak · 0–19 Distressed. Labels describe signal strength, not investment merit.

Evaluation

Each sub-score's individual evaluation is documented in its own section above (Risk → section 4, Fundamental/Insider → computed from publicly disclosed data with no model output).
The aggregate is back-tested on a rolling 24-month window for label-stability vs price drawdowns. We do not claim predictive power for forward returns.

Limitations

The Composite Score reflects a snapshot of public data. It does not capture private events (litigation, undisclosed regulatory inquiries, operational decisions).
The score is a research output. It is not a buy, sell, or hold recommendation. See the “Non-GAAP Notice” on /legal/disclosures.html § 3.4.
Confidence bands widen meaningfully below mid-cap. Treat micro/nano-cap composites as low-confidence by design.

9. Technical Score

Architecture

Deterministic finance formulas, not AI. Standard, widely-published technical indicators applied to publicly available OHLCV data:

Indicators	SMA · EMA · RSI · MACD · Bollinger Bands · OBV. Each computed from the same public OHLCV time-series; none are proprietary inventions.
Aggregation	Weighted scoring per indicator with weights documented in /legal/disclosures.html § 3.5. Same inputs ⇒ same output.
Why this engine is here	Listed for completeness. It is not an AI/ML system; we surface it on this page so any review of “all the engines that produce a score” is consolidated.

Limitations

Technical indicators describe past price/volume behavior. They do not predict future returns.
OHLCV data is sourced from a commercial market-data feed and may be delayed up to 15 minutes.
Indicator values can be sensitive to look-back window selection (we document each window in /disclosures § 3.5).

10. Sentiment Analysis (retired)

Quintarthai does not run a news sentiment classifier. Headlines are shown unscored (Disclosures § 3.6). The sentiment component of QuinnScore is the analyst mean price target compared with the current price — arithmetic over third-party analyst data, not an NLP reading of the news.

11. What AI Outputs Are NOT

12. How AI Content Is Labeled

13. Data Handling

14. Changes to This Statement

When an engine's architecture, model provider, or training data changes materially, we update this page and announce it in changelog. Version history is kept in this document's git log in our platform repository.

Quinn	Conversational RAG assistant that retrieves from 415 regulatory and reference chunks across 13 jurisdictions.
Geo-LLM	Mining-geology question answering grounded in NI 43-101 and S-K 1300 technical reports.
Delisting Risk Composite	Deterministic three-pillar scoring model (float concentration, promotional language, jurisdiction) — NOT an LLM; every input is a declared variable.
VPIN Microstructure	Volume-synchronized probability of informed trading, a published academic metric (Easley & O'Hara, 2012).
Cross-Border FX-Adjusted Spread Engine	Deterministic finance formula — no ML component.
Answer feedback (thumbs up/down)	Ratings of Quinn answers are stored and counted. They do not change retrieval or any model, and no model is fine-tuned on them.
Composite Intelligence Score	Meta-score that aggregates Risk, Fundamental, Momentum, Volume, and Insider sub-scores. Deterministic aggregation; sub-score sources vary.
Technical Score	Standard technical indicators (SMA / EMA / RSI / MACD / Bollinger / OBV). Deterministic formulas, no AI.