diff options
| -rw-r--r-- | MIXED_TRAFFIC.md | 7 | ||||
| -rw-r--r-- | REVIEW_SCORECARD.md | 1 | ||||
| -rw-r--r-- | ROADMAP.md | 4 | ||||
| -rw-r--r-- | results/kp_innovation_mechanics.json | 36 |
4 files changed, 47 insertions, 1 deletions
diff --git a/MIXED_TRAFFIC.md b/MIXED_TRAFFIC.md index 521d108..0f14e05 100644 --- a/MIXED_TRAFFIC.md +++ b/MIXED_TRAFFIC.md @@ -79,6 +79,13 @@ Before any task endpoint, the float64/CPU smoke suite must establish all of: Failure closes this branch. Passing mechanics does not change the reviewer score. +MT-0 passes. CPU float64 errors are zero or at most `8.88e-16`; the exact +predictor error is `1.39e-17`. A task-data-free synthetic ResNet-20 batch-128 +audit of the most expensive matched path on a GTX 1080 remains finite and peaks +at 0.857 GB allocated / 0.906 GB reserved after reset, with float32 layer-ratio +error `4.77e-7`. The machine-readable record is +`results/kp_innovation_mechanics.json`. No CIFAR endpoint was evaluated. + ## MT-1: frozen 20-epoch load-bearing screen This screen is conditional on a KP-2 pass. Run exactly raw, matched, and diff --git a/REVIEW_SCORECARD.md b/REVIEW_SCORECARD.md index 191145d..bf08e18 100644 --- a/REVIEW_SCORECARD.md +++ b/REVIEW_SCORECARD.md @@ -97,6 +97,7 @@ retroactively reopened by success on standard vision benchmarks. | 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 / 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 | 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 @@ -482,7 +482,9 @@ gain calibration, norm/direction control, reciprocal local correlations, and parameter independence pass at zero or float64 machine error. A realistic 20-step neutral warmup leaves `0.1360` of traffic RMS versus the frozen `0.25` ceiling. Elementwise traffic/predictor work is reported separately from affine -MACs, and every control pays the predictor schedule. +MACs, and every control pays the predictor schedule. The synthetic batch-128 +matched path is finite on a GTX 1080 and peaks at 0.857 GB allocated after +reset; no task endpoint was used for this hardware check. MT-1 remains sealed until KP-2 passes. A 20-epoch pass opens one full seed-0 validation panel but cannot raise the reviewer score; a full pass opens the diff --git a/results/kp_innovation_mechanics.json b/results/kp_innovation_mechanics.json new file mode 100644 index 0000000..159af9b --- /dev/null +++ b/results/kp_innovation_mechanics.json @@ -0,0 +1,36 @@ +{ + "protocol": "kp_mixed_traffic_mechanics_v1", + "status": "passed", + "source_commit": "f8f5583189fcb47bb97416934d40e3d62d360aaa", + "tracked_dirty": false, + "task_data_used": false, + "task_endpoints_touched": false, + "synthetic_audit": { + "device": "GTX 1080", + "physical_gpu": 5, + "batch_size": 128, + "depth": 20, + "width": 16, + "normalization": "batchnorm", + "traffic_rule": "matched", + "traffic_ratio": 4.0, + "predictor_warmup_steps": 20, + "predictor_eta": 0.1, + "finite_step_loss": true, + "peak_allocated_bytes": 857338880, + "peak_reserved_bytes": 905969664, + "max_layer_ratio_error": 4.76837158203125e-07 + }, + "cpu_float64_invariants": { + "zero_traffic_limit_error": 0.0, + "traffic_ratio_error": 8.881784197001252e-16, + "exact_predictor_error": 1.3877787807814457e-17, + "matched_norm_error": 0.0, + "matched_direction_error": 8.881784197001252e-16, + "reciprocal_correlation_error": 0.0, + "predictor_parameter_independence_error": 0.0 + }, + "review_score_before": 5, + "review_score_after": 5, + "score_change_rule": "mechanics and memory feasibility do not establish task utility" +} |