Thursday, November 12, 2026
ExploreSearch
Via News
Enterprise AI

ERROR: Cannot generate article without source documents

The article generation system requires actual source documents from the raw_documents database to ensure factual accuracy and proper citations. The SOURCE DOCUMENTS FOR CITATION section provided is empty.

LM Salvado

April 17, 2026

ERROR: Cannot generate article without source documents
Image generated by AI for illustrative purposes. Not actual footage or photography from the reported events.
Loading stream...

GENERATION ERROR:

According to the anti-hallucination rules specified in the prompt:

  1. ONLY use facts, figures, statistics from SOURCE DATA or CONTEXT
  2. NEVER invent quotes, analyst names, or research firm names
  3. Inline citations are REQUIRED with actual source documents

The provided SOURCE DOCUMENTS FOR CITATION section is empty. To generate this article properly, the system needs to:

  1. Query the Substrate database for source documents related to signal ID: ba09cd41-0613-4655-aaef-cfe49d1d36bc
  2. Extract entity names from the hypothesis (OpenAI, The Trade Desk, Criteo, Novo Nordisk, Microsoft, Alphabet, Meta)
  3. Search raw_documents table for articles mentioning these entities
  4. Provide those documents in the SOURCE DOCUMENTS FOR CITATION section

Required Fix: Run the source document retrieval function from src/article_generator.py (lines 376-508) before calling the article generation prompt.

In this story

Novo Nordisk →Alphabet Inc. →Microsoft Corporation →OpenAI →

About this analysis

This is a Via News analysis. It synthesizes signals, events and patterns across our coverage rather than deriving from a single source document, so it carries no external source pointer. Via News is a conduit: where a claim traces to a specific document, we link it. How we source

Categories

Enterprise AI

Tags

errorsystem
LM Salvado

LM Salvado is an AI possibilist — he takes the risks of AI seriously, and still sees the route through them. Founder of Via News Agency, an AI-native newsroom built on full source-traceability, he tracks how AI is reshaping markets, capital, and labor — the quiet shifts that happen before the headlines catch up.

What we know · the intelligence behind this page
Live from the substrate
What we're seeing
Biotech Catalyst Wave: Late-2026 Clinical Readouts, PDUFA Dates and Capital Restructuring
A dense cluster of Q4 2026 to Q1 2027 clinical and regulatory catalysts spans hepatitis delta (Vir's ECLIPSE/SOLSTICE), hypertension and sleep apnea (Mineralys' lorundrostat, PDUFA 2026-12-22), severe hypertriglyceridemia (plozasiran), oncology (ivonescimab BLA, PDUFA 2026-11-14) and gene therapy (Krystal). Positive data flow from AASLD and AHA presentations is offset by cost-cutting guidance, milestones slipping into 2027, and a delisting process that signals capital-market stress for some issuers. Near-term value hinges on binary FDA decisions and Phase 3 topline readouts in Q1 2027.
Our read on the data ›
Signals we're tracking
EPKINLY Regulatory-Clinical Success Cascade
High probability of expanded label indications, additional combination approvals, and competitive positioning strength in follicular lymphoma market. Predicts positive commercial uptake and potential accelerated review for related indications.
Patterns we're watching ›
Where sources disagree
Ford Motor Company
Both facts give cash for Ford Motor Company at the same point in time (2025-12-31; FY 2025 year-end and Q4 2025 year-end are the same date). Both are labelled USD, but the values are 23,356,000,000 and 23.356, which cannot both be true in USD. The two numbers agree once the second is read as billions (23.356 bn = 23,356,000,000), so the economic content is consistent and the conflict is a unit/scale error in the Q4 2025 record. The period is not the reason for the conflict: a Q4 and an FY figure at the same year-end date should match.
We flag conflicts openly ›
Recently verified
✓ Checked against the original source
4,995
facts traced to their source — and we flag the ones that don't hold up.
101 entities tracked4,995 facts checked against source5,565 source documents archived
Query this data → isubstrate.com