Operational Pipeline v0.2.0Beta Multi-model 2026-08-12 00:48 UTC

Automated political fact-checking with multi-model consensus analysis.

Model panel insights


What each seat of the verdict panel actually predicted, per report — computed from the published per-claim provenance (panel_by_role), not from the reconciled verdicts. Disagreement between seats is the pipeline's error-catching mechanism: an escalation means the proposer and critic differed and the arbiter decided; a Severity-Classifier override means a second-stage model re-graded a boundary call. Both are disclosed per claim on its provenance strip.

George W. Bush — 2006-01-31

48 claims · 4 escalated to the arbiter (8.3%)

SeatModelSeat predictionsFalse-rateClaims voted
Proposeropus-workerTrue 33 · Misleading 3 · False 1 · Unverifiable 12.6%38
Criticgrok-4.3True 31 · Misleading 3 · False 3 · Unverifiable 17.9%38
Arbitergpt-5.5True 1 · Misleading 2 · False 125.0%4

Arbiter side-taking on the 4 escalated claims: sided with the proposer 2, with the critic 2, took a third position 0.

Severity-Classifier stage-2 overrides: False→Misleading 1.

Bill Clinton — 1998-01-27

92 claims · 15 escalated to the arbiter (16.3%)

SeatModelSeat predictionsFalse-rateClaims voted
Proposeropus-workerTrue 66 · Misleading 50.0%71
Criticgrok-4.3True 57 · Misleading 4 · False 8 · Unverifiable 211.3%71
Arbitergpt-5.5True 8 · Misleading 4 · False 320.0%15

Arbiter side-taking on the 15 escalated claims: sided with the proposer 8, with the critic 6, took a third position 1.

Severity-Classifier stage-2 overrides: False→Misleading 2.

Joe Biden — 2022-03-01

111 claims · 11 escalated to the arbiter (9.9%)

SeatModelSeat predictionsFalse-rateClaims voted
Proposeropus-workerTrue 82 · Misleading 50.0%87
Criticgrok-4.3True 74 · Misleading 4 · False 8 · Unverifiable 19.2%87
Arbitergpt-5.5True 7 · Misleading 1 · False 2 · Unverifiable 118.2%11

Arbiter side-taking on the 11 escalated claims: sided with the proposer 6, with the critic 2, took a third position 3.

Severity-Classifier stage-2 overrides: False→Misleading 1.

Barack Obama — 2014-01-28

96 claims · 8 escalated to the arbiter (8.3%)

SeatModelSeat predictionsFalse-rateClaims voted
Proposeropus-workerTrue 71 · Misleading 5 · False 11.3%77
Criticgrok-4.3True 67 · Misleading 2 · False 7 · Unverifiable 19.1%77
Arbitergpt-5.5True 3 · Misleading 2 · False 2 · Unverifiable 125.0%8

Arbiter side-taking on the 8 escalated claims: sided with the proposer 3, with the critic 3, took a third position 2.

Severity-Classifier stage-2 overrides: False→Misleading 2.

Donald Trump — 2026-02-24

182 claims · 30 escalated to the arbiter (16.5%)

SeatModelSeat predictionsFalse-rateClaims voted
Proposeropus-workerTrue 63 · Misleading 28 · False 35 · Unverifiable 127.6%127
Criticgrok-4.3True 56 · Misleading 9 · False 61 · Unverifiable 148.0%127
Arbitergpt-5.5True 8 · Misleading 9 · False 10 · Unverifiable 333.3%30

Arbiter side-taking on the 30 escalated claims: sided with the proposer 13, with the critic 12, took a third position 5.

Severity-Classifier stage-2 overrides: Disagreement→Misleading 1 · False→Misleading 7 · Misleading→False 1.

Method notes: seat predictions are each seat's own verdict before reconciliation; the False-rate is the share of that seat's votes reading False. See About for the full pipeline.