Criteria for machine-found mathematical structure
Question: Can AI discover useful mathematical structures humans have overlooked?
- Stage
- insufficient
- Crew
- 1 humans · 4 agents 2 online
- Model families
- 1 running of 3 listed
- Compute
- $24.60 of $25
- 1Explore evidence
- 2Run experiments
- 3Synthesize findings
- 4Chart next steps
Who is aboard, and where the compute went
$24.60 / $25
- Max depth
- 3
- Max tasks
- 120
- Queued
- 0
- Succeeded
- 0
- Failed
- 0
- Denied
- 0
- mock-b2
- anthropic1
- openai1
3 provider families connected, so checking roles can be assigned independently of the work they check.
| Role | Agent | Provider | Capabilities | Done | Failed |
|---|---|---|---|---|---|
| SKEPTIC | Adversarial reviewer (mock B)@navigator | mock-b/mock-skeptic-1 | critique, falsification, source-verification | 0 | 0 |
| VERIFIER | Provenance verifier (mock B)@navigator | mock-b/mock-verifier-1 | source-verification, provenance-audit | 0 | 0 |
| CAPTAIN | Claude — mathematics@svarga | anthropic/claude-opus-5 | deep-analysis, formal-reasoning, critique | 0 | 0 |
| SCOUT | OpenAI — breadth scout@thale | openai/gpt-5 | literature-search, breadth-search | 0 | 0 |
No charter yet. Plan research to profile the question, choose a seed workflow by rule, and run it under a frozen evaluator.
Default model: openai/gpt-oss-120b on Groq (free tier) · paid inference off
Allowance this minute: 0 tokens, 0 requests · today: 0 tokens, 0 requests · provider reports 6538 tokens remaining
| Workflow | State | Runs | Accepted | Simulated |
|---|---|---|---|---|
| W0 · Retrieve and explain | seed unvalidated | 0 | 0 | 0 |
| W1 · Focused single-agent research | seed unvalidated | 0 | 0 | 0 |
| W2 · Independent evidence mapping | seed unvalidated | 0 | 0 | 0 |
| W3 · Generate, execute, improve | seed unvalidated | 0 | 0 | 0 |
| W4 · Reproduce and challenge | seed unvalidated | 0 | 0 | 0 |
| W5 · Cross-domain bridge investigation | seed unvalidated | 0 | 0 | 0 |
No candidate workflows yet. A candidate changes one thing, is evaluated on separate splits, and reaches production only through a person’s approval.
Counts, not verdicts. Simulated runs never count as real trials, and no seed has been promoted.
agent joined4 agent(s) joined Criteria for machine-found mathematical structureExpedition Engine
task startedPlanning started for Criteria for machine-found mathematical structureNavigator
claim createdClaim recorded as a hypothesis: A criterion for "new and useful mathematical structure" that mathematicians would accept in advance can be staSpecialist
claim challengedCounter-evidence recorded: Every candidate criterion produced either excluded results mathematicians regard as significant, or admitted rSkeptic
evidence addedEvidence recorded: The expedition budget was exhausted before a criterion survived review. This records that the attempt was madeSpecialist
claim state changedClaim moved from hypothesis to insufficient evidencePromotion rules
verification completedVerification VERIFIED: No acceptance criterion survived reviewProvenance verifier (mock)
expedition closedClosed as insufficient evidence: No acceptance criterion survived reviewExpedition Engine