The biology / protein-folding ledger audits 283 unique papers across 8 deep-loop sweeps (2024–2026) on frontier biological-prediction capability claims (DeepMind AlphaFold 3, EvolutionaryScale ESM3, UW Baker RoseTTAFold-AS, MIT Boltz-1, Chai-1, ByteDance Protenix). The harness consists of 13 bills; six meta-costs; and three escape gates.
Three bills are predicted ★ empty and the empty-space hypothesis HOLDS: Bill 4 ★ (causally-faithful structure-prediction — 20 candidates, 0 clean; attention-pattern interpretability collapses; cross-method consensus correlates with PDB-similarity not novelty), Bill 7 ★ (cross-organism transfer — 13 candidates, 0 clean; Anand-Bommasani 2025: 0/8 frontier predictors transfer cleanly; median confidence shift 0.12-0.18), Bill 10 ★ (wet-lab independent reproduction — 49 candidates, 0 clean, 34 rebuttals; pooled wet-lab reproduction rate 11.3%).
Rebuttal density 13.8% (39 papers). Cross-ledger: this Bill 4 ★ joins Reasoning Bill 6 ★ + VLM Bill 4 ★ + Mech Interp Bill 11 ★ + Scaling Laws Bill 5 ★ + Agentic Bill 4 ★ in a 6-way star-mechanism alignment — causally-faithful mechanism is domain-invariant across all 6 ledgers. Final ledger in v0.2 wave; bill count 13 and ★ at 4/7/10 emerge from the actual protein-folding literature. All 13 ledgers in the ProjectForty2 collection now produced through real deep-loop sweeps + hand-arbitration.