Source identity
| Field | Recorded value |
|---|---|
| Source type | archive member |
| Original record | tensor_validation.json |
| Date | Not specified in source |
| Path or archive member | archives/libsrc-5feba6626817/Supplementary_Material_S1/data/tensor_validation.json |
| Original SHA-256 | bab5c70eb7197abc7aa6780af35bc7ee41971d8bebfc65215141c05371ecc3db |
| Reading-copy SHA-256 | bab5c70eb7197abc7aa6780af35bc7ee41971d8bebfc65215141c05371ecc3db |
| Archive source | {"sourceId": "libsrc-5feba6626817", "member": "Supplementary_Material_S1/data/tensor_validation.json"} |
Every recorded occurrence
These 2 records contain identical original source bytes. Their paths and revisions remain part of the archive.
| Original record | Branch or archive | Revision / identifier | Original location |
|---|---|---|---|
| tensor_validation.json | {"sourceId": "libsrc-5feba6626817", "member": "Supplementary_Material_S1/data/tensor_validation.json"} | libsrc-a41bc1157ac7 | archives/libsrc-5feba6626817/Supplementary_Material_S1/data/tensor_validation.json |
| tensor_validation.json | {"sourceId": "libsrc-6c9313f7cdd5", "member": "Declaration_Study_v1/data/tensor_validation.json"} | libsrc-51192ebf337a | archives/libsrc-6c9313f7cdd5/Declaration_Study_v1/data/tensor_validation.json |
Recovered source transcript
Download complete source text ↓33 lines · 0.9 KB
{
"n_checkpoints": 167,
"n_training_steps": 792,
"n_eval_observations": 79,
"parameter_layer_index": 21,
"rank": 1,
"scale": 64,
"A_shape": [
1,
13824
],
"B_shape": [
5120,
1
],
"configurations_identical": true,
"zero_effective_update_steps": [
1
],
"effective_norm_strictly_increasing": true,
"B_norm_strictly_increasing": true,
"pca_variance_ratios": [
0.8109369033497655,
0.13896290956024188,
0.03310634943994352,
0.010324782029499699,
0.003771529911710381
],
"max_stable_vs_gram_corner_error": 4.490124128064821e-07,
"stable_corner_checks": 462,
"remote_derived_geometry_sha256": "6760abfbdf676bb5ad3bc85ea777bfe9313fcbcbe1a0ea692a06d57eece6f0f1",
"derived_table_scope": "The distributed checkpoint and sensitivity CSV files tabulate selected remote outputs. Recompute the full geometry using checkpoint_analysis.py and the public pinned sources."
}