← Back to Quintarthai

AI Transparency Statement

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

Summary. Quintarthai uses AI in well-bounded, clearly labeled ways. No AI output is presented as a buy/sell recommendation. Every engine below is documented with its (1) model architecture, (2) training/grounding data, (3) evaluation methodology, and (4) known limitations. We update this page whenever an engine's architecture, model provider, or training data changes materially.

Version history

2026-04-24v2: 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.
2026-04-23Quinn corpus v1 frozen at 404 chunks across 13 jurisdictions. 21-test E2E regression suite passing 21/21.
2026-04-16Initial AI transparency statement (v1).

1. Systems in Use

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

QuinnConversational RAG assistant trained on 404 regulatory chunks across 13 jurisdictions.
Geo-LLMMining-geology question answering grounded in NI 43-101 and S-K 1300 technical reports.
Delisting Risk CompositeDeterministic 12-factor scoring model (NOT an LLM) — every input is a declared, auditable variable.
VPIN MicrostructureVolume-synchronized probability of informed trading, a published academic metric (Easley & O'Hara, 2012).
Cross-Border FX-Adjusted Spread EngineDeterministic finance formula — no ML component.
RLHF Feedback LoopUser “thumbs up/down” feedback used to tune Quinn retrieval rankings. No fine-tuning of base model weights.
Composite Intelligence ScoreMeta-score that aggregates Risk, Fundamental, Momentum, Volume, and Insider sub-scores. Deterministic aggregation; sub-score sources vary.
Technical ScoreStandard technical indicators (SMA / EMA / RSI / MACD / Bollinger / OBV). Deterministic formulas, no AI.
Sentiment AnalysisFinancial-domain NLP classifier (transformer, ~110M params), Canadian-hosted. Outputs per-ticker sentiment score with time-decay.

2. Quinn — Conversational RAG Assistant

Architecture

Base LLMGroq Llama 3.3 70B (primary) · Claude Haiku 4.5 (fallback for tool calls) · local Ollama Llama 3 8B (air-gap mode).
RetrievalQdrant 1.9 vector DB · quintarth-regulations-v1 collection · Ollama nomic-embed-text 768-dim embeddings.
Tool-callingReAct loop (max 3 iterations) over 8 deterministic tools: watchlist quote, insider filings lookup, delisting risk scorer, Blue Sky checker, OCR parser, regulatory search, chart endpoint, vision upload.
PromptSystem-prompt v5 — enforces MUST-call on search_regulations for any jurisdictional question, refuses direct buy/sell advice, cites retrieved passages with jurisdiction + section.

Training & Grounding Data

Evaluation Methodology

Known Limitations

3. Geo-LLM — Mining-Geology Specialist

Architecture

ModelSame base LLM as Quinn (Groq Llama 3.3 70B) 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).
RetrievalSubset of the Quinn corpus: ~160 chunks specific to mining geology, technical reports, and commodity markets (gold, silver, copper, lithium, uranium, iron ore).

Evaluation

Limitations

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-factorsfloat 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 classifierLightweight keyword + pattern matcher (NOT an LLM). Scans press-release text for known promotional phrases (“game-changer”, “revolutionary”, superlative density). Deterministic output.

Evaluation

Limitations

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.”

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

Limitations

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

7. RLHF Feedback Loop

Architecture

User thumbs-up / thumbs-down on Quinn answers is stored with (query hash, retrieval context, response hash). Used to tune retrieval reranking weights over time. Does not modify base-LLM weights. Aggregated, anonymous feedback only.

Limitations

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-scoresRisk 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 labels80–100 Strong · 60–79 Moderate · 40–59 Neutral · 20–39 Weak · 0–19 Distressed. Labels describe signal strength, not investment merit.

Evaluation

Limitations

9. Technical Score

Architecture

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

IndicatorsSMA · EMA · RSI · MACD · Bollinger Bands · OBV. Each computed from the same public OHLCV time-series; none are proprietary inventions.
AggregationWeighted scoring per indicator with weights documented in /legal/disclosures.html § 3.5. Same inputs ⇒ same output.
Why this engine is hereListed 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

10. Sentiment Analysis

Architecture

ModelFinancial-domain NLP classifier (transformer encoder, ~110M parameters). Hosted on Canadian infrastructure — no third-party LLM call for sentiment.
InputsNews headlines + article abstracts from Yahoo Finance, Reuters/AP wire ingests, and SEDAR+/EDGAR filing summaries. Per-source weights are documented in /legal/disclosures.html § 3.6.
DecaySentiment scores carry an exponential time-decay (half-life ~7 days) so older articles fade in the rolling score.
OutputPer-ticker sentiment score in [−1, +1], plus a separate confidence band based on sample size and source diversity.

Training data

Evaluation

Limitations

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.