About solver.press
solver.press is the public window into the AegisMind research discovery engine. It publishes cross-domain scientific hypotheses that were generated, debated, and formally validated entirely by AI — hypotheses that connect ideas across fields in ways that don't appear in any single paper.
How a discovery is made
- 1Paper ingestion: arXiv and Semantic Scholar papers across 15+ scientific domains are embedded into a vector store. Bridge-detection algorithms identify papers that span multiple fields — these are where novel hypotheses hide.
- 2Hypothesis generation: A five-model ensemble (Claude, GPT, Gemini, Grok, Mistral) independently proposes cross-domain hypotheses based on the bridging papers. Near-duplicate hypotheses are filtered using semantic similarity.
- 3Adversarial debate: Models take turns critiquing each other's hypotheses. A debate score (0–1) reflects how well a hypothesis survives adversarial scrutiny. Only hypotheses above threshold are published.
- 4Formal verification: Z3 theorem prover checks whether the hypothesis is internally logically consistent. This is not empirical proof — it checks whether the stated claim is self-contradictory.
- 5Novelty check: A novelty checker queries the vector store for prior art. Hypotheses that closely match existing work are scored down. The novelty score reflects genuine contribution, not just unfamiliarity.
- 6Experimental Validation Package (EVP): High-confidence discoveries receive a Claude-generated EVP: a full experimental protocol including methodology, required datasets, success/failure criteria, cost estimates, and dependency map.
Model roles in debate
- Claude: Analytical evaluator — reasoning consistency and boundary conditions.
- GPT: Skeptical opponent — challenges assumptions and prior art.
- Gemini: Creative synthesiser — cross-domain connections and novel framings.
- Grok: Contrarian — adversarial edge cases and failure modes.
- Mistral: Pragmatic analyst — implementation feasibility and testability.
Available models rotate based on API availability. The circuit breaker pauses models that are rate-limited and resumes them automatically.
What these discoveries are not
Discoveries on solver.press are AI-generated hypotheses, not validated experimental findings. They represent plausible, formally consistent, novel connections between research fields. The EVP provides a protocol for empirical testing — that testing has not yet been done. Treat them as high-quality research leads, not established science.
Published research
The Precision Tetrahedron: Loss Landscape Topology Across Number Formats and Multi-Target Drug Discovery — John Goodman, AegisMind Research, May 2026.
A 42-phase empirical study characterising inter-precision Linear Mode Connectivity barriers across FP32, BF16, FP16, and INT8. Key findings: a model-size scaling law placing ~10M parameters as the practical basin-separator for mixed-precision training; an isosceles precision triangle (FP32↔BF16 ≈ 0.014 eV vs FP32↔FP16 ≈ 0.150 eV); and a four-vertex INT8 precision tetrahedron replicated across transformer, LSTM, and ResNet architectures. Applied to drug discovery with Nash equilibrium combination optimisation converging on EPTIFIBATIDE as a dual KPC-3 / MSH3 candidate (Spearman ρ = 0.827, six therapeutic targets).
DOI: 10.5281/zenodo.20363636 · All 42 phases on Google v6e-8 TPUs via Google TRC