Method v1.0.0

Evidence before prose.

Pulse measures first, collects a bounded evidence packet second, and only then generates or publishes an explanation.

01 · Principles

Measured fact, confirmed event, interpretation, and unknown are different objects.

Temporal proximity does not prove a cause. Detector severity does not equal explanation confidence. A primary source can strongly confirm an event while the event’s market impact remains uncertain.

Observation

Directly recomputed from normalized stored data.

Confirmed

Supported by a primary source or independent high-quality evidence.

Interpretation

A qualified inference linked to evidence and alternatives.

Unknown

No responsible unique cause is established.

02 · Deterministic detection

Versioned detectors create candidates.

We use log returns, normalize against an asset’s own volatility and liquidity, reject stale inputs, and retain detector features for replay.

DetectorCore inputOutput
Price anomalyLog return vs. rolling median/MADAbnormal move severity
Volume anomalyLog volume vs. rolling baselineParticipation confirmation
Volatility breakRealized volatility ratioRegime change
Market breadthAdvancing share and trend participationBroad vs. narrow move
Correlation breakReturn correlation vs. prior equal windowRelationship change
Scheduled catalystApproved calendar/primary sourceReminder and post-event review
03 · Materiality

The first score is deliberately inspectable.

materiality =.25 × move abnormality+ .15 × volume confirmation+ .15 × liquidity quality+ .15 × breadth context+ .15 × evidence quality+ .10 × novelty+ .05 × source velocity

Personal relevance is calculated separately from direct watchlist exposure, optional manual quantity, related assets, saved topics, repetition, and explicit feedback.

04 · Evidence

A bounded packet is the only explanation input.

  1. Primary official sourceProtocol, regulator, court, exchange status, or company publication.
  2. Verifiable recordExplorer, signed governance record, or other direct technical evidence.
  3. Recognized reportingWire or specialist source with attribution and editorial controls.
  4. Secondary corroborationMultiple independent sources rank above a single unverified source.

Unverified social posts may start an investigation but cannot independently support a confirmed explanation.

05 · Confidence

Two scores, never one.

90–100ConfirmedPrimary or multiple high-quality confirmations
70–89Strong supportGood evidence; causal uncertainty may remain
50–69PlausibleTiming and evidence align; alternatives remain
25–49WeakProminent caveat and limited publication
0–24UnknownCause is not established

These are editorial product defaults, not calibrated probabilities. Source trust tiers impose ceilings on event confidence.

06 · Publication guardrails

Structured output must survive validation.

  • JSON Schema and required fields
  • Every factual claim’s evidence IDs
  • Numeric and time-window consistency
  • Allowed assets, entities, dates, and URLs
  • Source-tier confidence ceilings
  • Prohibited advisory and guarantee language
  • Similarity and duplicate active explanations

After one bounded retry, a failed generation moves to human review or becomes an observation-only card.

07 · Research assets

Figures are generated from data, not generative imagery.

Correlation views use price log returns and Pearson coefficients on overlapping observations. Adjacent equal-length windows expose changes. Exports contain derived values only where provider terms permit redistribution.

08 · Limitations

Monitoring software cannot see every cause.

  • Approved sources are intentionally narrower than the full information environment.
  • Market prices can incorporate private, diffuse, reflexive, or unobservable information.
  • Historical normalization can fail during structural breaks.
  • Entity mapping and provider data can be wrong; quality flags and corrections remain necessary.
  • Pulse is research and monitoring, not investment advice, custody, execution, or a prediction guarantee.