Remediation Registry

Remediation Registry

Radical transparency means naming our own limitations and saying what we do about each one. This registry tracks every publicly-acknowledged limitation of a C.R.E.E.D.-monitored product — why it exists, the governance position, and who owns it. Product “Known Limitations” sections link directly into the matching entry here.

3 Accepted Trade-off 4 In Progress
What The Fact AI Model Constraints Accepted Trade-off

LLM analysis is bounded by the model's training cutoff

“LLM analysis is based on training data (cutoff 2024) — models do not have internet access or real-time fact databases.”
Why this exists

Local language models reason from their training corpus; they cannot look up events that post-date that corpus or query a live fact store. This is a property of how the models are run, not a configuration bug.

What we do about it

Facts are taken from the live article text, not the model's memory: summaries are extractive (drawn from the published body), and the LLM is used for framing, tone and bias interpretation rather than as a source of factual claims. A retrieval-augmented fact-check path (grounding on a live evidence store) is on the research roadmap.

Owner: D.A.R.W.I.N. — Research & Development Updated: 2026-05-31 #wtf-llm-training-cutoff
What The Fact Bias & Fairness In Progress

Bias scores may not match human expert consensus

“Bias scoring reflects the LLM's interpretation of language patterns; it may not match human expert consensus in all cases.”
Why this exists

A single model's reading of loaded language is one signal among several. Reasonable analysts — and reasonable models — can disagree on where a given article sits on the spectrum.

What we do about it

Bias is computed from multiple independent signals (LLM language analysis, outlet editorial-stance priors, and a separate DistilBERT NLI model) rather than one verdict, and the rationale is shown so readers can judge it themselves. Ongoing calibration measures the scorer against outlet editorial baselines.

Owner: B.I.A.S. — News & Media Updated: 2026-05-31 #wtf-bias-vs-human-consensus
What The Fact Data Coverage In Progress

Geolocation falls back to source province at low confidence

“Geolocation uses source province as fallback when AI confidence is low (<0.5).”
Why this exists

When the extractor cannot confidently locate a story, it attributes it to the publishing outlet's province rather than guessing a precise location it is not sure of.

What we do about it

Province-level fallbacks are labelled transparently rather than presented as precise geolocation. The L.O.C.A.L. agent's geo-extraction is being improved to raise the share of articles that clear the confidence threshold.

Owner: L.O.C.A.L. — News & Media Updated: 2026-05-31 #wtf-geolocation-province-fallback
What The Fact Throughput & Coverage In Progress

Not every article receives full LLM analysis

“Not all articles receive full AI analysis — only priority articles (top 20/cycle) get LLM treatment; all others receive heuristic + source-editorial bias scoring.”
Why this exists

Full LLM analysis is compute-bound. To keep the feed current, each ingest cycle prioritises the highest-signal articles for deep analysis and applies lighter heuristic + editorial scoring to the rest.

What we do about it

Analysis throughput is being scaled across the agent fleet and a backlog drains lower-priority articles toward full coverage over time. Articles that have not yet had full LLM analysis are scored by transparent heuristic + outlet-editorial methods in the interim.

Owner: F.A.C.T. — News & Media Updated: 2026-05-31 #wtf-priority-article-coverage
What The Fact Bias & Fairness Accepted Trade-off

Outlet bias profiles are rolling averages, seeded for new outlets

“Outlet bias profiles are rolling averages; new outlets are seeded from editorial stance data and refined over time.”
Why this exists

An outlet's bias profile is a moving aggregate of its analysed coverage. A newly added outlet has little history, so it starts from a documented editorial-stance prior and converges as articles accumulate.

What we do about it

This is the intended design: profiles update as evidence accumulates rather than being fixed labels. Seed priors are sourced from published editorial-stance research and are superseded by measured behaviour as the sample grows.

Owner: B.I.A.S. — News & Media Updated: 2026-05-31 #wtf-outlet-bias-rolling-average
What The Fact Data Coverage Accepted Trade-off

Paywalled articles are analysed from title + summary only

“Paywalled articles (Postmedia, Torstar) have limited body text — AI analysis relies on title + Open Graph description only.”
Why this exists

Where a publisher gates the article body behind a paywall, the full text is not lawfully or technically available to ingest, so analysis is limited to the headline and the publicly-served summary metadata.

What we do about it

Paywalled items are analysed only from the publicly-available title and Open Graph description, and this reduced basis is disclosed rather than hidden. We do not bypass paywalls to obtain body text.

Owner: F.A.C.T. — News & Media Updated: 2026-05-31 #wtf-paywalled-body-text
What The Fact Bias & Fairness In Progress

The DistilBERT signal is US-trained and used as a second opinion

“DistilBERT Signal 3 (US-trained NLI model) may not map cleanly to Canadian political framing; treated as a second opinion, not ground truth.”
Why this exists

The supplementary DistilBERT natural-language-inference model was trained primarily on US data, so its read of Canadian political framing can be imperfect.

What we do about it

Its output is weighted as one second-opinion signal, never as ground truth, and is cross-checked against the LLM and editorial signals. A Canadian-framing fine-tune is planned to improve its domain fit.

Owner: V.E.R.I.F.Y. — News & Media Updated: 2026-05-31 #wtf-distilbert-canadian-framing