> ## Documentation Index
> Fetch the complete documentation index at: https://docs.amlok.io/llms.txt
> Use this file to discover all available pages before exploring further.

# References and source scope

> Primary research, Canadian data authorities, and governance sources supporting this research specification.

Sources were reviewed for the November 1, 2026 research specification. A citation identifies related work or a source's own claim. It does not establish access to proprietary data, permission to train on a source, independent replication, or an AMLOK result. Record an exact revision when a source or model becomes an experimental dependency.

## Financial event and language models

| Source | Role in this program |
| - | - |
| [Slope TransFormer: an LLM for banks](https://slopepay.com/blog/slope-transformer-llm-for-banks) | Author-reported descriptor labeling method and narrow comparison, published in 2023. |
| [Revolut PRAGMA, arXiv 2604.08649v1](https://arxiv.org/html/2604.08649v1) | Typed-event representation, self-supervision, and adaptation. Version 1 is the supplied reference. |
| [RBC Borealis ATOM](https://rbcborealis.com/applications/atom/) | Canadian financial foundation-model prior work; not an AMLOK benchmark. |
| [Your Spending Needs Attention: Modeling Financial Habits with Transformers](https://arxiv.org/abs/2507.23267) | Nubank nuFormer research; recommendation and representation scope. |
| [TransactionGPT, arXiv 2511.08939](https://arxiv.org/abs/2511.08939) | Transaction-native representation and prediction research. |
| [BloombergGPT](https://arxiv.org/abs/2303.17564) | Financial-language pretraining context; different from borrower-outcome validation. |
| [LoRA](https://arxiv.org/abs/2106.09685) | Parameter-efficient adaptation method. |
| [Ditto: Deep Entity Matching with Pre-Trained Language Models](https://arxiv.org/abs/2004.00584) | Learned entity-matching baseline and experimental context. |

## Cash-flow scoring and monitoring

| Source | Role in this program |
| - | - |
| [Prism: creation of CashScore v4](https://www.prismdata.com/blog/the-creation-of-cashscore-v4-raising-the-bar-for-cash-flow-underwriting/) | Vendor account of score development. The gated full whitepaper was not acquired. |
| [Prism: five essential development standards](https://www.prismdata.com/blog/five-essential-market-standards-for-cash-flow-score-development/) | Multi-lender development and evaluation considerations. |
| [Prism Pulse](https://www.prismdata.com/blog/introducing-prism-pulse-for-cash-flow-monitoring/) | Longitudinal financial monitoring context. |
| [Prism support for Canada and Neo Financial](https://www.prismdata.com/blog/prism-data-announces-new-support-for-canada-partners-with-neo-financial/) | Existing Canadian cash-flow analytics activity. |

## Evaluation and baselines

| Source | Role in this program |
| - | - |
| [FinBen](https://arxiv.org/abs/2402.12659) | Broad financial task taxonomy; no substitute for Canadian lending labels. |
| [FinanceBench](https://arxiv.org/abs/2311.11944) | Financial-document question-answering evaluation. |
| [FinQA](https://arxiv.org/abs/2109.00122) | Numerical reasoning with financial evidence. |
| [TAT-QA](https://arxiv.org/abs/2105.07624) | Reasoning over financial text and tables. |
| [Revisiting Deep Learning Models for Tabular Data](https://arxiv.org/abs/2106.11959) | FT-Transformer and strong tabular baselines. |
| [TabPFN 3.5 technical report](https://priorlabs.ai/technical-reports/tabpfn-3-5) | Current tabular-model candidate; access and permitted use require checking for an actual run. |
| [On Calibration of Modern Neural Networks](https://arxiv.org/abs/1706.04599) | Probability calibration and validation methodology. |
| [OpenAI model announcement](https://openai.com/index/gpt-6-astra/), [Anthropic model page](https://www.anthropic.com/claude/fable), [Google Gemini catalogue](https://deepmind.google/models/gemini/) | Sources for candidate model availability. No hosted frontier model was evaluated in this package. |

## Canadian sources and governance

| Source | Role in this program |
| - | - |
| [Corporations Canada data services](https://ised-isde.canada.ca/site/corporations-canada/en/data-services) and [API documentation](https://api.ised-isde.canada.ca/en/docs?api=corporations\&wbdisable=true) | Federal registry scope and access mechanism. |
| [Office of the Superintendent of Bankruptcy statistics](https://ised-isde.canada.ca/site/office-superintendent-bankruptcy/en/statistics-and-research) | Aggregate insolvency context, not individual labels. |
| [Statistics Canada WDS](https://www.statcan.gc.ca/en/developers/wds/user-guide) and [open licence guidance](https://www.statcan.gc.ca/en/terms-conditions/open-licence-faq) | Public statistical acquisition and reuse context. |
| [Bank of Canada Valet documentation](https://www.bankofcanada.ca/valet/docs) and [terms](https://www.bankofcanada.ca/terms/) | Source for the executed FX descriptive analysis. |
| [BDC debt-service coverage definition](https://www.bdc.ca/en/articles-tools/entrepreneur-toolkit/templates-business-guides/glossary/debt-service-coverage-ratio) | Financial definition reference; agreement-specific ratios can differ. |
| [CMHC GDS and TDS calculation](https://www.cmhc-schl.gc.ca/professionals/project-funding-and-mortgage-financing/mortgage-loan-insurance/calculating-gds-tds) | Mortgage affordability definitions within CMHC's stated scope. |
| [OSFI Guideline E-23 (2027)](https://www.osfi-bsif.gc.ca/en/guidance/guidance-library/guideline-e-23-model-risk-management-2027) | Model-risk governance; revised guideline effective May 1, 2027. |
| [Canadian privacy authorities' generative-AI principles](https://www.priv.gc.ca/en/privacy-topics/technology/artificial-intelligence/gd_principles_ai/) | Privacy, purpose, and accountability reference. |
| [Québec private-sector privacy statute, section 12.1](https://www.legisquebec.gouv.qc.ca/fr/version/lc/P-39.1?code=se%3A12_1\&history=20250414\&langCont=en) | Exclusively automated decisions within the provision's scope; linked official version must be rechecked for an actual deployment. |

The initial research consulted public source pages and selected AMLOK starter documents. It did not acquire competitor datasets, commercial model weights, private borrower histories, or a Canadian loan-outcome corpus. Public-data availability and source quality are evaluated separately from permission to collect, redistribute, or train.

## Original records and acquisition sources

The [public-source inventory](https://docs.amlok.io/research/canadian-data.md) contains the full source-by-source access and field register. The executed source analysis uses original [EDC disclosures](https://www.edc.ca/en/about-us/corporate/disclosure/reporting-transactions/individual-transaction-information.html), [Investissement Québec intervention records](https://www.investquebec.com/fr/tout-sur-nous/diffusion-de-linformation/archives), [CSBFP data](https://open.canada.ca/data/dataset/3f718801-099d-4037-bb0a-1d41ba8aca8b), [Kinross financing disclosure](https://www.kinross.com/news-and-investors/news-releases/press-release-details/2022/Kinross-announces-US1.0-billion-term-loan/default.aspx), [Lundin Mining's amendment](https://www.lundinmining.com/news/lundin-mining-increases-existing-credit-facility-to-us45-billion), and [BCE's financial report](https://www.bce.ca/cs-assets/2025-bce-annual-financial-report.pdf-blt5d552f866d8a58a3).

The [SBA data portal](https://data.sba.gov/dataset/7a-504-foia) supplies the inspected US loan schema. The original [FinQA repository](https://github.com/czyssrs/FinQA) supplies the executed retrieval task; [TAT-QA](https://github.com/NExTplusplus/TAT-QA) supplies development examples. [FinanceBench's publisher page](https://www.patronus.ai/research/financebench) identifies the open sample and its use conditions. [CUAD](https://www.atticusprojectai.org/cuad) is a candidate contract-clause benchmark, not an executed result here.

The [acquisition manifest](https://docs.amlok.io/downloads/research/public-records/acquisition-manifest.json) records the exact file URLs and hashes. A citation alone is not evidence that the entire archive was collected, labels were adjudicated or a model was trained.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.