xpertsystems/fin-qa-003-sample

Portfolio Management Knowledge Base — FIN-QA-003 (Sample)

A deterministic, ontology-driven synthetic prompt/response knowledge-base corpus for portfolio management: asset allocation, portfolio construction and optimization, risk and tail-risk measurement, performance attribution, institutional mandates, rebalancing, tax-aware investing, and multi-persona portfolio reasoning. Each question is rendered at four audience depths (beginner → institutional) over a concept ontology, with companion misconception, adversarial, conversation, relation, formula, worked-example, and use-case tables.

This repository is the public 500-question sample of a 20,000-question commercial product. It is built by an unmodified production engine and validated to Grade A+ (10.0/10) across 6 canonical seeds, with byte-identical determinism per seed.

• Unit of observation: the prompt/question (qa_pairs row)
• Sample size: 500 questions · Full product: 20,000 questions
• License: CC-BY-NC-4.0 (sample) / commercial (full)
• Contact: pradeep@xpertsystems.ai · https://xpertsystems.ai

Positioning note. Answers are templated, structurally-controlled prose rendered from a concept ontology — not human-verified factual ground truth. This corpus is built for structural / retrieval / reranker / adversarial-robustness / agent-evaluation work, not for teaching factual portfolio knowledge via supervised fine-tuning. See Limitations. Each item is educational and not investment advice.

Depth tiers, not a gold/distractor scheme

Every question in multi_depth_answers has exactly four answers, one per audience depth: beginner, intermediate, advanced, institutional. All four are legitimate renderings at different sophistication levels; there is intentionally no single "correct" answer. The structure supports depth-conditioned generation and depth-ranking tasks.

Calibration anchors

Metric	Observed (seed 42)	Target	Anchor
Difficulty mean (1–5)	3.45	3.30–3.75	Bloom's Taxonomy (portfolio skew)
Upper-difficulty (4–5) share	0.50	0.45–0.62	Bloom's upper-level concentration
Reasoning-required answer share	0.90	0.85–0.95	FinQA reasoning fraction
Formula-coverage share	0.03	0.01–0.10	formula coverage (advanced/institutional only)
Question-type spread	5 types, even	exactly 5 even	CFA PM question-type taxonomy
Persona spread	5 personas, even	exactly 5 even	retail/advisor/PM/quant/CIO breadth
Adversarial attack-type spread	4 types, even	exactly 4 even	OWASP LLM Top-10

Heavily-weighted structural integrity floors (all exact, all pass): exactly 4 distinct depth answers per question; full referential integrity across all FKs; md5-derived id uniqueness; ontology parent-node integrity; per-table column-count contract; complete adversarial behavior coverage; relation self-loops within the disclosed bound.

Tables (schema highlights)

Table	Rows (sample)	Key columns
finqa003_qa_pairs	500	qa_id, concept_id, question_text, question_type, persona_type, difficulty
finqa003_multi_depth_answers	2,000	answer_id, qa_id, depth_level, answer_text, contains_formula_flag, requires_reasoning_flag
finqa003_misconceptions	50	misconception_id, concept_id, incorrect_statement, why_wrong, correct_explanation, error_type
finqa003_adversarial_queries	120	adv_id, qa_id, attack_type, adversarial_question, expected_behavior
finqa003_conversations	80	conv_id, persona_type, turn_sequence (JSON), topic_drift_flag, resolution_flag
finqa003_concepts	100	concept_id, concept_name, category_l1, category_l2, difficulty_level, institutional_relevance_score, description_short, description_long
finqa003_ontology	145	node_id, node_type, name, parent_node, depth_level
finqa003_relations	42	relation_id, source_node, target_node, relation_type, strength_score
finqa003_formulas	6	formula_id, concept_id, formula_latex, variable_definitions, interpretation
finqa003_examples	100	example_id, concept_id, example_type, example_description, solution_steps
finqa003_use_cases	6	use_case_id, use_case_name, description, target_buyer

relations.source_node / target_node reference ontology node_id values (md5-derived from concept_id). Root ontology nodes (depth 1) have an empty parent_node. conversations.turn_sequence is JSON-encoded.

Loading

import pandas as pd

qa = pd.read_csv("finqa003_qa_pairs.csv")
answers = pd.read_csv("finqa003_multi_depth_answers.csv")
merged = qa.merge(answers, on="qa_id")
print(merged.groupby("qa_id").size().value_counts())  # all == 4

# ontology: preserve empty-string roots (do not coerce to NaN)
ontology = pd.read_csv("finqa003_ontology.csv", keep_default_na=False)

from datasets import load_dataset

qa = load_dataset("xpertsystems/fin-qa-003-sample", "qa_pairs")["train"]
answers = load_dataset("xpertsystems/fin-qa-003-sample", "multi_depth_answers")["train"]

Use cases

• SFT (style/format/depth): depth-conditioned portfolio-answer generation (retail-plain vs CIO/institutional voice).
• Preference / ranking data: depth-preference pairs encoding audience fit (not factual correctness) for reranker / RLHF-style signals.
• RAG & reranker evaluation: topic-calibrated (query, answer-shape) pairs over a portfolio-management ontology for MRR/NDCG-style metrics.
• Adversarial robustness: adversarial_queries provides prompt-injection, misleading, oversimplification, and hallucination-bait probes appended to legitimate questions, with expected_behavior labels (refuse/correct/clarify).

Limitations (full disclosure)

The build process inspected the engine line-by-line. Disclosed observations:

1. Answers are templated prose, not verified facts. Answer text is rendered from concept metadata and persona/depth templates; it is plausible and structurally complete but not human-verified portfolio truth. Do not use (question, answer) pairs as factual SFT ground truth.
2. No gold/preferred tier. This is a 4-level depth corpus by design.
3. Question-type, persona, and adversarial attack-type mixes are deterministic (round-robin / modulo cycling), so they are exactly uniform by construction. Difficulty is the principal sampled quantity (via a shared random.Random(seed)).
4. One relation self-loop per run (disclosed, deterministic). The category-cycle relation builder uses target = items[(i+1) % len(items)]; when a category contains a single concept this yields a self-loop. The sample contains exactly one such edge. The scorecard verifies self-loops stay within a small disclosed bound rather than requiring zero.
5. Misconceptions cover only the first max(50, n_concepts//2) concepts, cycled from a 5-pattern pool (50 rows at sample scale). The incorrect_statement text applies a literal .replace("portfolio", concept_name.lower()), which can read awkwardly when the substring appears mid-word; treat misconception text as templated exemplars.
6. formulas are inherited from base concept templates only (6 rows at sample scale); expanded concept variants carry the base formula metadata but most concepts have no formula, so contains_formula_flag is sparse (≈0.03) and only set at advanced/institutional depth.
7. IDs are content-derived (md5) for ontology nodes, answers, and formulas, and sequential for qa/adv/misconception/example. All id sets are verified unique.
8. Manifest carries no wall-clock timestamp and no output path, so it is fully reproducible per seed; data files are byte-identical per seed.

No benchmark-theater was found: no hardcoded validation values, no max(actual, target) floors, no always-true passes, no referential-integrity leaks. Scorecard ranges were calibrated to observed 6-seed behavior; deterministic distributions are scored as exact-target floors and the heavy weight sits on structural integrity.

Sample vs. full product

Dimension	Sample (this repo)	Full product
Questions	500	20,000
Concepts	100	1,000
Multi-depth answers	2,000	80,000
Misconceptions	50	~500
Adversarial queries	120	3,000
Conversations	80	3,000
License	CC-BY-NC-4.0	Commercial
Validation	6/6 seeds Grade A+ (10.0/10)	Full-scale QA suite

Determinism

Re-running the engine with the same seed produces byte-identical data files (verified across all 11 CSVs) and identical scored metrics. The wrapper reproduces the engine's exact main() orchestration order so the single shared random.Random(seed) is consumed identically (verified byte-identical to the native engine). The manifest carries no wall-clock timestamp.

Citation

@misc{xpertsystems_finqa003_2026,
  title        = {Portfolio Management Knowledge Base (FIN-QA-003): A Synthetic,
                  Ontology-Driven Multi-Depth Portfolio-Management Q&A Corpus},
  author       = {XpertSystems.ai},
  year         = {2026},
  howpublished = {Hugging Face Datasets},
  note         = {Sample (500 questions) of a 20,000-question commercial product.
                  Difficulty mix calibrated to Bloom's Taxonomy; topic and
                  question-type taxonomy to the CFA Institute portfolio-management
                  curriculum; reasoning-required fraction to FinQA-style
                  financial-reasoning corpora; adversarial attack-type taxonomy to
                  the OWASP LLM Top-10. License CC-BY-NC-4.0.},
  url          = {https://xpertsystems.ai}
}

Anchored benchmarks referenced for calibration: Bloom's Taxonomy of educational objectives; CFA Institute candidate body of knowledge (portfolio-management topic and question-type taxonomy); FinQA (Chen et al., financial numerical-reasoning QA); OWASP Top-10 for LLM Applications (adversarial attack taxonomy).

Disclaimer

This dataset is synthetic and provided for AI/ML research and engineering. Its content — including allocation, optimization, risk, and performance concepts — is educational and illustrative only, is not investment advice, is not a recommendation to buy, sell, or allocate to any security or asset class, and is not a substitute for professional financial, legal, or compliance guidance.