# ICLR-style reviewer scorecard

This is a deliberately adversarial paper-level assessment, not an average of the best runs. It is
updated only when a frozen experiment is complete and audited. Development pilots, partial jobs,
and post-hoc subsets cannot raise the score. Failed gates remain visible and narrow the claim.

## Scoring convention

The overall score uses a 1--10 ICLR-like scale: 1 strong reject, 3 reject, 5 borderline reject,
6 borderline accept, 8 accept, and 10 strong accept. Component scores use 1--4. The overall score
is a reviewer judgment rather than the arithmetic mean of the components. Confidence uses 1--5.

Every formal result report records:

- the previous and new overall score;
- soundness, novelty, significance, empirical support, and reproducibility;
- which frozen evidence changed the assessment;
- the strongest remaining reviewer objections;
- whether the evidence is development, validation, or untouched confirmation.

## Current paper-level assessment (2026-07-27)

| Dimension | Score | Strict reviewer assessment |
|:--|--:|:--|
| Soundness | 4/4 | Theory, exact local-update checks, causal lesions, clustered uncertainty, cost accounting, and retained frozen failures make the implemented claims unusually well identified. |
| Novelty | 2/4 | Learned node-perturbation feedback is prior art. The defensible novelty is the per-cell innovation operation under mixed apical traffic, together with its causal and scaling analysis. |
| Significance | 4/4 | Dynamic innovation now tracks BP/KP while gaining accuracy from ResNet-20 to ResNet-56 over five paired seeds; a separate local actor--critic reproduces role-vectorized outcome surprise. Original-data biological validation remains absent. |
| Empirical support | 4/4 | Residual necessity, untouched ResNet-20 confirmation, the complete 60-record standard-depth panel, and a complete 30-record task-clustered BCI confirmation are strong. Useful-depth C2, broad endogenous C1, old oral-B, A3, and the original MT-1 remain disclosed failures. |
| Reproducibility | 4/4 | Code, exact provenance, seed panels, costs, failed branches, frozen selectors, and staged test-access rules are retained in git. |
| **Overall** | **9/10** | **Internal oral-A milestone: the preregistered 60-record panel establishes standard ResNet depth scaling in addition to load-bearing innovation and role-vectorized TD outcome surprise.** |
| Confidence | 4/5 | High confidence in the assessment because the positive and negative branches are both extensively audited. |

The conservative external-review forecast is **8/10**, not 9.  The
standard-depth result is unusually strong, but its clean-task transport
substrate is inherited reciprocal KP and the Harnett-specific gain remains a
conditional mixed-traffic result.  A reviewer can also discount the synthetic
BCI because terminal reward is supplied and the psychometric target range is
calibrated per policy.  The 9/10 value is the repository's predeclared
evidence milestone; 8/10 is the recommendation I would actually submit as a
reviewer today.  The ongoing 81-cell BP/FA/DFA/PEPITA/FF/EP/DualProp/KP/SDIL
crossover targets the strongest remaining baseline-and-cost objection and
cannot change this score until its complete frozen panels are audited.

### Evidence already carrying the paper

- On flattened CIFAR-10, SDIL changes by only `-0.214 +/- 0.349` accuracy points from depth 5 to
  depth 60, while DFA's early-layer alignment falls from `0.514` to `0.047`.
- Under strong soma-predictable apical traffic, raw and norm-matched raw learning fall to about
  chance (`10.38%` and `10.31%`) while innovation learning retains `97.35%` accuracy.
- On untouched CIFAR-10 test endpoints, dynamic innovation reaches `91.584%` versus clean KP's
  `91.388%` over five paired ResNet-20 seeds; its paired deficit upper bound is only `0.131`
  points and every frozen mechanism/cost invariant passes.
- In the complete 60-record standard-depth panel, dynamic innovation rises
  from `91.584%` at ResNet-20 to `92.254%` at ResNet-32 and `92.760%` at
  ResNet-56.  All five paired seeds improve from depth 20 to 56; mean gain is
  `1.176` points, while early-third alignment remains
  `0.99969/0.99961/0.99942` across depths 20/32/56.
- In the untouched six-task by five-model BCI panel, final task success is
  `100%`, terminal residual outcome decoding is `99.83%`, the acute
  outcome-lesion separation drop is `0.400`, critic expectedness is `0.319`,
  and all 30 causal signs are positive after label-free calibration.
- The local update has a proved descent condition and an explicit query/MAC/memory audit; direct
  node perturbation isolates the learned vectorizer as the useful-depth bottleneck.

### Strongest remaining objections

1. The matched standard-depth panel contains BP, tuned DFA, clean KP, and
   dynamic innovation, but not yet matched PEPITA, Forward-Forward, EP, Dual
   Propagation, and ordinary FA at every depth.  The frozen 81-cell crossover
   is active but incomplete.
2. The clean scaling result primarily establishes the inherited reciprocal-KP
   substrate; SDIL-specific necessity still comes from controlled predictable
   traffic and cannot be inferred from clean KP/SDIL equality.
3. The amortized perturbation-trained apical vectorizer failed the frozen
   useful-depth gate; the successful standard-depth path uses reciprocal local
   plasticity and a paired neutral microphase.
4. Innovation was not uniformly beneficial for arbitrary endogenous top-down traffic, so the
   supported mechanism is narrower than the initial claim.
5. The passed BCI is synthetic: reward is directly supplied, causal roles are
   experimenter-defined for diagnostics, and target quantiles are calibrated
   on a separate cursor split. Longitudinal prediction remains failed, and no
   original Francioni/Harnett event-level data are tested.

## Score trajectory and prospective gates

| Checkpoint | Overall | What changed | Remaining ceiling |
|:--|--:|:--|:--|
| Current audited package | 9 | D4 confirms load-bearing ResNet-20 innovation; calibrated oral-B-v2 confirms role-vectorized TD outcome surprise; oral-A-v2 confirms five-seed ResNet-20/32/56 scaling over 60 records | Complete matched strong-baseline crossover and original-data biological validation remain absent |
| Native baselines complete | 5 | BurstCCN is below its published endpoint; Dual Prop reproduces 92.46% versus 92.41%, with strict provenance and cost semantics | Fairness objection narrows, but SDIL gains no standard-scale evidence |
| Oral-A A1/A2 | 5 | BP reached 91.62%; short channel-gated SDIL reached 41.98% versus tuned DFA at 37.16% | Development screening alone cannot raise the score |
| Oral-A A3 fails | 5 | Full ResNet-20 SDIL became nonfinite at epoch 89 and ended at 10%; DFA ended finite at 33.06% | Standard-scale and oral-A claims are closed; A4 remains untouched |
| Oral-A-v2 causal capture fails | 5 | Structured perturbation improves early/all-layer alignment 6.5x/4.5x but misses the frozen early gate | Mechanism diagnosis sharpens; no full standard-scale endpoint opens |
| Oral-A-v3 causal capture fails | 5 | Direct A/G perturbation lowers synthetic estimator variance but leaves real early alignment at 0.0071 | Coefficient regression is not the dominant early bottleneck; full scale remains closed |
| Fixed hierarchical FA short gate fails | 5 | HFA reaches 43.52%, above DFA 37.16% and failed-v1 SDIL 41.98%, but below its frozen 50% full-run threshold | Spatial hierarchy helps; fixed random hierarchy remains insufficient and supplies no SDIL scale evidence |
| Hierarchical task-scalar V4 fails | 5 | Stable calibration leaves early alignment near zero; higher rates explode to 58.5x norm or become nonfinite after 800 queries | Correct mechanics and the right spatial family are insufficient when one global scalar estimates 267,904 feedback parameters |
| Normalized response mirror capture passes | 5 | Twenty local observations reach 0.446 early alignment and 0.915 feedback/forward cosine at zero task-loss queries | Strongly resolves the engineering bottleneck, but all credit belongs to an inherited weight-estimation baseline until innovation is load-bearing |
| Normalized response mirror short gate fails | 5 | WM reaches 64.04% and 0.939 early alignment at 0.9968x BP MACs, but misses its two accuracy gates by under one point | Strong inherited baseline and useful warning that alignment is insufficient; full run and any SDIL scale claim remain closed |
| Residual response mirror capture passes | 5 | RRM reaches 0.665 early and 0.730 all-layer alignment with 0.954 feedback/forward cosine after 20 zero-query local observations | Opens the frozen short accuracy gate, but remains inherited predictive weight estimation rather than SDIL evidence |
| Residual response mirror short gate passes | 5 | RRM reaches 65.08%, within 9.86 points of matched BP, at 0.9969x BP MACs and nearly exact alignment | Opens one full validation run; the inherited baseline still supplies no Harnett-specific evidence |
| Residual response mirror full gate fails | 5 | RRM ends at 10% with NaN validation loss although endpoint Q/W cosine is 0.999998 | Closes intermittent mirroring and proves endpoint alignment is an inadequate trajectory certificate; KP remains the separate strong substrate |
| Modified KP short gate passes | 5 | KP reaches 82.66% versus BP's epoch-20 81.02%, with 0.886 early alignment and 1.326x BP MACs | Strongly solves the substrate at useful scale, but all credit belongs to inherited reciprocal plasticity until innovation is load-bearing |
| Modified KP full gate passes | 5 | KP reaches 91.26% versus matched BP's 91.62%, with 0.9994 early alignment, 0.9997 late feedback cosine, zero queries, and 1.326x BP MACs | Establishes a stable near-BP ResNet substrate and opens MT-1, but inherited KP evidence cannot raise the SDIL score |
| Mixed-traffic MT-1 fails | 5 | Raw, norm-matched raw, and innovation all become nonfinite in epoch 1 and end at 10%; calibration and predictor warmup still pass | Closes the controlled standard-ResNet innovation path; MT-2/MT-3 remain untouched and no weaker traffic rescue is allowed |
| Mixed-traffic MT-2 | not opened | The prerequisite MT-1 gate failed | No full seed-0 validation claim is available |
| Mixed-traffic MT-3 | not opened | MT-2 was never opened; all five confirmation seeds remain untouched | No controlled ResNet innovation confirmation claim is available |
| Dynamic projection D1 | 5 | All 352 training-only steps remain finite while the fast neutral fit holds residual coupling near zero | Mechanics only; no held-out endpoint |
| Dynamic projection D2 | 5 | One frozen 20-epoch record reaches 83.58%, above clean KP's 82.66%, with all stability and cost gates passing | Short single-seed validation cannot establish the full scaling claim |
| Dynamic projection D3 | 6 | All 19 frozen checks pass at 91.18%, within 0.44/0.08 points of BP/clean KP, with 0.9994 early alignment and 1.326x BP MACs | One validation seed cannot establish robustness |
| Dynamic projection D4 | 7 | All ten untouched records pass: dynamic 91.584% versus clean KP 91.388%, paired upper deficit bound 0.131 points, early alignment 0.999687, and no invariant failures | Establishes ResNet-20 robustness/noninferiority, not positive depth utility |
| Oral-B recovery R1/R2 | failed at R2 | R1 selects eta 0.1 with 98.05% worst-task success; untouched R2 retains 99.53% mean success and 30/30 positive signs but fails outcome-vectorization and longitudinal gates | Score remains 7; the joint oral-B claim is not established |
| Oral-B-v2 initial grid | failed at development | All 24 records preserve role learning and residual identification but fail from a one-quarter dense-signal cold start | Failure retained; no confirmation touched |
| Oral-B-v2 fixed-target recovery | failed at development | Two seeds pass 18/18; the third passes 17/18 but its fixed target ladder has 98.96% success | Mechanism works, absolute assay scale does not generalize |
| Oral-B-v2 calibrated R1/R2 | 8 | Three fresh development seeds pass, then all 30 untouched records and every task-cluster bound pass under independent label-free calibration/evaluation splits | Establishes synthetic outcome surprise; does not establish cortex or added-depth utility |
| Oral-A dynamic depth recovery | closed | A 60-cell ResNet-20/32/56 BP/DFA/clean-KP/dynamic panel was frozen before any new endpoint | Its oral-B R2 prerequisite failed, so none of the 50 new cells may run |
| Oral-A-v2 standard-depth scaling | 9 | After the calibrated BCI-v2 prerequisite passed, all 60 records and every preregistered accuracy, depth-gain, alignment, mechanism, cost, query, and memory check pass | Strong matched-baseline breadth and original neural-data validation remain absent |
| Oral-A A4 | not opened | The prerequisite A3 gate failed | No oral-A confirmation claim is available |

These are conditional reviewer forecasts, not promised scores. A failed stage leaves its negative
result in the record and can lower the score if it invalidates a current claim. The original
oral-B branch and both v2 development failures remain failed. The calibrated
v2 pass does not reopen the old oral-A panel; it permits only a new
independently frozen oral-A-v2 protocol.

## Evidence-to-score log

| Date / revision | Evidence status | Overall change | Reviewer interpretation |
|:--|:--|:--:|:--|
| 2026-07-22 / `2304e83` | Audit of all completed frozen branches | baseline → 5 | Strong preservation/residualization core, but no standard useful-scale result |
| 2026-07-22 / `c753f51`, `1b24c87`, `6d19078` | Existing 60-run innovation panel promoted to a strict main figure; conditional-projection and norm-direction identities made executable | 5 → 5 | Closes a presentation/theory objection and makes the narrow novelty legible, but adds no new held-out evidence and therefore earns no score inflation |
| 2026-07-22 / frozen Oral-A A1--A3 | A1 and A2 pass; full A3 SDIL becomes nonfinite and fails four of six checks; A4 untouched | 5 → 5 | Closes the standard-scale question negatively. The narrow mechanism paper survives, while any standard-ResNet or oral claim does not |
| 2026-07-22 / native C4 | BurstCCN and Dual Prop author-code records pass the strict audit; Dual Prop reproduces 92.46% test in 23119.8 s | 5 → 5 | Closes a baseline-fidelity objection and confirms a strong expensive comparator, but does not repair SDIL's failed A3 evidence |
| 2026-07-22 / Oral-A-v2 V2-1 | Six clean frozen-forward records: structured calibration raises early/all-layer alignment to 0.0072/0.0527 but fails two frozen advancement checks | 5 → 5 | Confirms representable-subspace variance was real, while showing that early-layer causal credit remains below the standard-depth gate; V2-2 and confirmation stay closed |
| 2026-07-22 / post-failure representation oracle | Current family has a 0.0240 cross-validated early-alignment ceiling on the fixed probe versus 0.0072 learned; unconstrained basis coefficients reach 0.0549 | 5 → 5 | Localizes both a causal-regression gap and an output-error-only capacity gap, but an oracle audit supplies no task-performance evidence |
| 2026-07-22 / Oral-A-v3 V3-1 | Four clean frozen-forward records: vectorizer-space estimation raises all-layer alignment to 0.0626 but leaves early alignment at 0.0071 and fails three advancement checks | 5 → 5 | Exact lower-variance mechanics do not repair early credit; no full ResNet or confirmation evidence is opened |
| 2026-07-22 / hierarchical oracle | Held-out gated 3x3 maps from exact child error fields reach 0.9998 early alignment; ordinary activation context remains 0.0321 | 5 → 5 | Strongly localizes the missing information to spatial hierarchical error fields, but exact-gradient oracle inputs provide no evidence that the proposed local learner can obtain them |
| 2026-07-22 / fixed HFA S1 | Three clean matched ResNet-20 records; selected HFA reaches 43.52% and 0.0404 early alignment but misses the frozen 50% gate | 5 → 5 | Establishes a stronger zero-query local baseline and confirms hierarchy helps, while closing an uncalibrated full run and leaving standard SDIL evidence absent |
| 2026-07-22 / hierarchical V4-1 | Four frozen-forward records: etaA 0.1 leaves early alignment near zero, etaA 1 explodes one feedback norm to 58.5x, and etaA 10 is nonfinite | 5 → 5 | Closes global-task-scalar calibration of the full hierarchy at the fixed budget; richer local information is required before another accuracy endpoint |
| 2026-07-22 / response-mirror WM-1 | Four clean frozen-forward records; selected etaM 0.1 reaches 0.4461 early and 0.5422 all-layer alignment with zero task-loss queries | 5 → 5 | Opens a strong inherited-baseline accuracy test and isolates information source as the bottleneck, but supplies no Harnett-specific task evidence |
| 2026-07-22 / response-mirror WM-2 | Two clean short ResNet records; selected WM reaches 64.04% with 0.9393 early alignment and 0.9968x BP MACs, missing both accuracy gates narrowly | 5 → 5 | Substantially strengthens the comparator and cost story, but closes its full run and demonstrates that high credit cosine alone is not a scale result |
| 2026-07-22 / residual response-mirror RRM-1 | Four frozen-forward records; selected etaM 0.1 reaches 0.6651 early and 0.7303 all-layer alignment with controlled norms, zero task-loss queries, and 2.4458e9 MACs | 5 → 5 | Residual prediction removes much of the fixed-point estimator noise and opens the short task gate, but the gain belongs to an inherited baseline and does not establish somato-dendritic innovation |
| 2026-07-22 / residual response-mirror RRM-2 | Two clean short ResNet records; selected RRM reaches 65.08%, 9.86 points below BP, with 0.9991 early alignment and 0.9969x BP MACs | 5 → 5 | Narrowly opens the full baseline run and strengthens the efficient comparator; the remaining accuracy gap despite near-exact direction warns that alignment is not trajectory equivalence |
| 2026-07-22 / residual response-mirror RRM-3 | The sole frozen full record reaches only 10%, has NaN validation loss, and peaks at `1.5808e16` training loss despite 0.999998 endpoint Q/W cosine | 5 → 5 | Closes intermittent residual mirroring and turns alignment latency into a measured negative; it neither weakens the surviving SDIL mechanism claim nor supplies positive scale evidence |
| 2026-07-22 / modified KP-1 | One clean constant-LR ResNet record reaches 82.66%, above BP's epoch-20 81.02%, with 0.8856 early alignment, 0.8546 train-period feedback cosine, zero queries, and 1.326x BP MACs | 5 → 5 | Establishes a stable strong substrate under a gate that observes the training trajectory, but reciprocal Kolen--Pollack plasticity is prior art and adds no Harnett-specific evidence |
| 2026-07-22 / `2ef7f94` modified KP-2 | One clean full ResNet record reaches 91.26%, 0.36 points below matched BP, with 0.9994 early alignment, 0.9997 late feedback cosine, zero queries, and 1.326x BP MACs | 5 → 5 | Removes substrate stability as the immediate blocker and opens the load-bearing innovation experiment, but prior-art reciprocal plasticity earns no novelty credit |
| 2026-07-22 / mixed-traffic MT-0 | Exact raw/matched/innovation mechanics pass; synthetic ResNet-20 matched batch peaks at 0.857 GB allocated on GTX 1080 without task data | 5 → 5 | Removes implementation, graph, and memory objections before endpoint access; supplies no evidence yet that innovation is useful |
| 2026-07-22 / `f310ad5` mixed-traffic MT-1 | All three frozen conditions become nonfinite in epoch 1 and end at 10%; ratio calibration, predictor warmup, zero-query, and cost checks pass | 5 → 5 | Fails to make innovation load-bearing on a standard ResNet and closes MT-2/MT-3; the prior mechanism-only evidence survives but empirical support does not improve |
| 2026-07-22 / `6531aed`, `d818fc2` MT-1 diagnosis | Training-only localization finds the first active failure at stem steps 23/69/74 for raw/matched/innovation; residual coupling yields the verified multiplicative operator `D W C` | 5 → 5 | Sharpens the failure into an operator-stability requirement and improves soundness of the negative analysis, but adds no successful held-out SDIL endpoint |
| 2026-07-22 / `8d28fd9` stability S0 | A frozen training-only four-margin grid has no eligible candidate; sign-certified margins either overflow BN state or produce enormous transient loss and parameter growth | 5 → 5 | Closes fixed one-sided predictor bias and motivates a two-sided dynamic gain condition, but no validation endpoint or empirical support is gained |
| 2026-07-22 / `6b85249` dynamic projection D1 | The sole frozen training-prefix record passes 14/14 checks; a 0.0058 neutral residual is reduced to 3.0e-8 while weights, momentum, BN, and loss stay bounded | 5 → 5 | Establishes a nontrivial operator-stability repair, but training-only mechanics cannot change the recommendation |
| 2026-07-22 / `9bc58d6` dynamic projection D2 | The sole frozen short validation record reaches 83.58% versus clean KP's 82.66% and failed controls' 10%, with 0.884 early alignment, zero queries, and 1.326x BP MACs | 5 → 5 | First positive standard-ResNet load-bearing innovation endpoint, but one short seed is insufficient; full D3 and independent confirmation remain decisive |
| 2026-07-22 / `15c60d0` dynamic projection D3 | The sole frozen full validation record passes 19/19 checks at 91.18% versus BP's 91.62% and clean KP's 91.26%, with 0.9994 early alignment, zero queries, and 1.326x BP MACs | 5 → 6 | Resolves the primary full-scale objection and opens the already frozen D4 panel; one validation seed and narrow biological scope prevent a stronger recommendation |
| 2026-07-22 / `32122d0` oral-B recovery freeze | Before any recovery task endpoint, the untouched 30-record R2 protocol, task-cluster uncertainty, original B1/B2 signatures, plasticity lesion, digest binding, and immutable analyzer are executable | 6 → 6 | Removes a preregistration gap but supplies no empirical evidence; R1 is still sealed behind D4 and confirmation seeds remain untouched |
| 2026-07-22 / `1853620` oral-A recovery freeze | Before any new standard-depth endpoint, a D4-reusing 60-cell ResNet-20/32/56 panel and exact runner/analyzer contract are executable, with BP/DFA/KP controls, positive depth gain, alignment, projection, query, MAC, and memory gates | 6 → 6 | Precommits the final oral claim without bypassing the required sequence; no experiment opens unless D4 reaches 7 and oral-B R2 reaches 8 |
| 2026-07-23 / `2fed62a` dynamic projection D4 | All ten untouched paired test records pass the frozen gate: dynamic 91.584% versus clean KP 91.388%, clean-minus-dynamic upper bound 0.131 points, 0.999687 early alignment, and zero invariant failures | 6 → 7 | Establishes the strict accept bar with independent ResNet-20 robustness/noninferiority; opens oral-B R1 but does not support added-depth or desired-velocity claims |
| 2026-07-23 / `1ff7cb7` oral-B recovery R1 | The complete two-rate development grid selects eta 0.1; all 30 seed-level checks pass, with 98.05% worst-task final success, positive sign inversion, and 0.945 minimum role cosine | 7 → 7 | Strong development support for the repaired causal-role/velocity factorization, but R1 cannot change the score and only opens untouched R2 |
| 2026-07-23 / `03c94a1` oral-B recovery R2 | Thirty untouched records retain 99.53% mean success, 90.45-point gain, 30/30 positive signs, and strong decorrelation, but fail seven population-vectorization/longitudinal checks | 7 → 7 | The recovery fixes learning, causal role, and sign but not the broader Harnett-like signature; oral-B and oral-A close without threshold repair |
| 2026-07-23 / `2a6f72e` audited D4 main figure | The strict renderer independently rechecks the ten D4 records and visualizes paired test accuracy, layerwise raw-versus-innovation direction, all 200 tracking epochs, and explicit neutral/MAC/memory/wall costs | 7 → 7 | Makes the accept evidence reviewable without adding or selecting data; presentation improves, but visualization alone cannot repair oral-B or justify score inflation |
| 2026-07-23 / `87cfb93` evidence-bound manuscript | A 3,238-word working draft binds 34 central numbers and all four figures to source manifests, retains the passed D4 gate and all seven failed R2 checks, and is re-audited by the accept finalizer | 7 → 7 | Substantially improves submission readiness and guards against claim drift; it adds no empirical evidence, so soundness and recommendation do not inflate |
| 2026-07-23 / `eb021a6` oral-B-v2 initial R1 | The complete 24-record grid learns causal roles and identifies innovations but reaches at most 0.78% evaluation success because terminal reward remains unreachable | 7 → 7 | Localizes a cold-start created by scaling the only pre-reward drive to one quarter; confirmation remains untouched |
| 2026-07-23 / `378e68d` fixed-target recovery R1 | Unit dense velocity restores 100% task learning and 17--18 biological checks per seed, but one fresh seed has 98.96% challenge success | 7 → 7 | Confirms the algorithmic repair while falsifying an absolute target ladder as a model-independent assay |
| 2026-07-23 / `70e180c`, `9a8c057` calibrated oral-B-v2 R1/R2 | Three new development seeds pass all 18 gates; all 30 untouched confirmation records then pass every clustered learning, innovation, decoder, lesion, and expectedness bound | 7 → 8 | Establishes role-vectorized TD outcome surprise in the synthetic paradigm and raises the formal milestone; ecological validity and added depth remain the external-review ceiling |
| 2026-07-23 / `75a6488` audited oral-B-v2 figure | The strict renderer visualizes all 30 records, task-cluster learning, residualization, independent psychometrics, and acute lesions | 8 → 8 | Improves reviewability without adding evidence or inflating the score |
| 2026-07-26 / `cdc7d5e` oral-A-v2 scaling | All 60 preregistered ResNet-20/32/56 records pass; dynamic accuracy rises `91.584% → 92.254% → 92.760%`, all five depth pairs improve, and mean early alignment remains above `0.9994` | 8 → 9 | Establishes the internal standard-depth oral-A milestone. The conservative external recommendation is 8 because reciprocal KP is inherited and the full matched strong-baseline crossover is not yet complete |

Future rows are appended only after an audited frozen stage. A score staying flat is informative:
engineering, theory exposition, or visualization may make the paper more defensible without
resolving the empirical objection that determines the recommendation.