Source Consensus & Attribution Analyzer

Weigh anonymous leaks, aide accounts, and donor chatter with Bayesian attribution weighting to detect real political signals behind insider reports.

Intelligence Synthesis

Models Synchronized
Synthesized Consensus Verdict
Strong Consensus Against Launch
82% Probability "Won't Run"
-100% Solid "Won't Run" Split / Contested (0%) +100% Solid "Will Run"
Weighted Score
-0.64
Normalized stance [-1.00 to +1.00]
Source Entropy
0.24
0 = Unanimous | 1 = Pure Discord
Credible Weight Mass
6.82x
Aggregate effective proximity
Attribution Dispersion Map X: Stance (- to +) · Y: Sourcing Proximity · Bubble: Credibility Weight
Former Aides
Megadonors / Bundlers
Surrogates
Party Officials

Cohort Signal Breakdown

Source Cohort Count Avg Stance Attribution Quality Dominant Consensus
Generate Intelligence Brief Formatted narrative source attribution assessment memo.

Why Raw Source Headcounts Mislead in Political Journalism

Attribution Tiers Alter Predictive Value

As shown in reporting on prospective campaigns—such as Axios's reporting on Kamala Harris's inner circle—insider signals rarely come with equal access or candidness. A former senior West Wing chief of staff speaking on deep background provides far stronger structural insight than a third-tier surrogate seeking on-the-record visibility.

This tool weights each quote by three independent factors: Attribution Protocol (On Record vs Deep Background), Proximity (Direct Inner Circle vs Party Observer), and Historical Reliability.

Bayesian Entropy & Factional Leaks

When an entire cohort (e.g. 100% of bundlers and aides) independently conveys the same conclusion to multiple journalists over months, Source Entropy drops near zero. This mathematical convergence distinguishes deliberate strategic leaks from authentic internal consensus.

Export your evaluated matrix directly into campaign briefs, investigative reporting notebooks, or research data pipelines.

Enjoy this tool? Build your own with Super