Manuscript Psy01-A@1 · Psy01-A.tex · section · 94477fa3
Claim-to-certificate ledger
Claim-to-certificate ledger · lines 2614–2689
Psy01-A@1#tab:ledger
| status of the proposed theorem candidates. | ||
|---|---|---|
| Proposed claim | Status | Valid replacement |
| Proposed claim | Status | Valid replacement |
| Universal cue-loss threshold near | False for the architecture class | Information obstruction, cue-sensitivity certificate, and a checkpoint-specific diagnostic. |
| High-density pruning necessarily increases selectivity and decreases stress tolerance | Not implied by density or magnitude ranking | Strict comparison using stress bounds and Theorem thm:transfer; solved conditional comparison model. |
| Hard-pruning accuracy surface is Lipschitz away from an empirical threshold | False without additional qualifications | Parameter-to-logit stability; margin-conditioned accuracy control; soft-density surrogate. |
| Early and late masks do not commute | False for fixed masks; fixed-weight nested rankings agree | Learning-induced ranking defect and the projection–gradient bound. |
| A unique increasing optimal late-pruning curve always exists | Not established; hard paths can have plateaus or jumps | Compact existence, an implicit branch under regularity assumptions, and an explicit comparison-model curve. |
| Surviving connection count controls observable variance | Insufficient on its own | Independent-mask matrix variance and bounded edge-influence concentration. |
| Same final density implies the same fragility | False | Noise sensitivity depends on margins, geometry, parameterization, and noise covariance. |
| Quantum landmark results directly prove neural pruning claims | Not a valid model identification | Independent classical proofs retaining the landmarks' construction, fluctuation, observation, and causal boundaries. |