Arena / Backtests/arena-historical-1c4b6142-47d0-4220-a95e-d597816b2a18

Historical Arena playback

Mar 6, 8:00 PM UTC to Mar 6, 9:01 PM UTC · NYSE · All visible models

completedmodeinvestingarchive runs4Live Arena
cash$100,000universe12max trades3tool calls0createdMar 7, 7:32 PM UTC
Performance
Live
Replay models
Claude Sonnet 4.6
anthropic:sonnet-4.6
+0.0%
$100,000
Runs
4
Fills
0
Parse fails
4
Blocks
0
Final leaderboard
Sonnet 4.6
Anthropic
+0.00%
$100,000
Final portfolios
Cash
$100,000
100.0% reserve
Turnover
—
30d
Stock
Allocation
P&L
No open positions.
Total P&L: +$0Cash: $100,000
Replay timeline
The Evidence Referee
Claude Sonnet 4.6▲ $200,000
2026-03-06T21:00:09.387Z

Decision contract v2 parse failed: schema_validation_error

No thesis update generated because the model failed during historical replay.

The Evidence Referee
Claude Sonnet 4.6▲ $200,000
2026-03-06T20:45:57.041Z

Decision contract v2 parse failed: schema_validation_error

No thesis update generated because the model failed during historical replay.

The Evidence Referee
Claude Sonnet 4.6▲ $200,000
2026-03-06T20:30:09.548Z

Decision contract v2 parse failed: schema_validation_error

No thesis update generated because the model failed during historical replay.

The Evidence Referee
Claude Sonnet 4.6▲ $200,000
2026-03-06T20:13:16.883Z

Decision contract v2 parse failed: schema_validation_error

No thesis update generated because the model failed during historical replay.

Decision ledger

Evidence Referee · Arena could not certify the desk's decision before execution.

receipt arena-backtest:arena-historical-1c4b6142-47d0-4220-a95e-d597816b2a18:run:4:2026-03-06T21:00:09.387Z
Comparability: VerifiedWorkflow: completedArtifacts: 1/1League: paper_live_v1
Context Hash
4b35b6ec3a...ed89baa1
Prompt Hash
658a93d2a1...1dde153d
Candidate Hash
cf6e096bc4...886cde1d
Temporal Bounds
Requested as of: Mar 6, 9:00 PM UTC
Data through: Mar 6, 9:00 PM UTC
Exchange: NYSE
Harness
Harness version: arena-harness-v2
Policy profile: default-guardrails-v1
Freshness state: fresh
Model Comparison
Evidence Refereeselected
Claude Sonnet 4.6 · arena-pm-v1
contextpromptcandidatedecision
Historical decision generation failed.
Selected replay receipt
Model
Claude Sonnet 4.6
As of
Mar 6, 9:00 PM UTC
Headline
Historical decision generation failed.
Chat model
anthropic:sonnet-4.6
Confidence
0.0%
Return
+0.0%
Orders
No orders for this replay step.
Portfolio after replay
Equity
$100,000
Cash
$100,000
Holdings
0
Portfolio remained empty.
Workflow events
No workflow events were recorded for this session.