Runs
Every model that was trained, every model that was planned and never trained, and the lineage that connects them.
Lineage
Two independent initializations exist. One continuation exists. Five planned models do not exist.
| Node | Scientific role | Parent | Parameters | Training status | Evidence status | Notes |
|---|---|---|---|---|---|---|
| Model-0 | Independent model birth #1 | — | 26,653,440 | Trained; completed | Official / frozen result (STOP-v1). Final checkpoint file NOT FOUND; hash and expected size on record. | Independent initialization. |
| Pilot-0.2 / Local-70M-0 | Independent model birth #2 | — | 69,970,848 | Trained; completed through verified checkpoint recovery | Diagnostic-only Birth Map; compatibility-adapter final chain. Checkpoint and receipt present. | Independent initialization. Not an 88.9M model. |
| Pilot-0.3 | Continued training of Pilot-0.2 — NOT a third independent birth | Pilot-0.2 / Local-70M-0 | 69,970,848 | Trained; COMPLETED | Diagnostic-only continuation scan. Checkpoint and receipt present. Final capability UNMEASURED. | Same 69,970,848-parameter model. Second exposure to the same corpus; schedule restarted. |
| Model-1 | Planned cohort member | — | — | NOT TRAINED | Experimental-design evidence only: seed 668309859 locked in the manifest before results were seen. | No model result exists. The empty evaluation row means the model was never produced, not that it performed badly. |
| Model-2 | Planned cohort member | — | — | NOT TRAINED | Experimental-design evidence only: seed 1658757876 locked in the manifest before results were seen. | No model result exists. The empty evaluation row means the model was never produced, not that it performed badly. |
| Model-3 | Planned cohort member | — | — | NOT TRAINED | Experimental-design evidence only: seed 315576475 locked in the manifest before results were seen. | No model result exists. The empty evaluation row means the model was never produced, not that it performed badly. |
| Model-4 | Planned cohort member | — | — | NOT TRAINED | Experimental-design evidence only: seed 1003306941 locked in the manifest before results were seen. | No model result exists. The empty evaluation row means the model was never produced, not that it performed badly. |
| Model-5 | Planned cohort member | — | — | NOT TRAINED | Experimental-design evidence only: seed 744367755 locked in the manifest before results were seen. | No model result exists. The empty evaluation row means the model was never produced, not that it performed badly. |
Trained runs
- Model-0
First reference model — independent model birth #1 · 26,653,440 parameters · 531,988,480 tokens · 32,470 steps.
- Pilot-0.2 / Local-70M-0
Second independent model birth · 69,970,848 parameters · 531,988,480 tokens · 32,470 steps.
- Pilot-0.3
Continued training of Pilot-0.2 — not a new initialization · 69,970,848 parameters · 1,000,013,824 tokens · 61,036 steps.
- Model-1 … Model-5 — planned cohort
Five initialization seeds were locked before results were seen. Training never started. This is experimental-design evidence, not model-performance evidence.
Two births, not three
Pilot-0.3 is not a third independent model
Pilot-0.3 began from the Pilot-0.2 final checkpoint. It is the same 69,970,848-parameter model trained further, not a new initialization with a new seed.
Counting it as a third birth would inflate the apparent number of independent observations from two to three, which is a large distortion when the total is two.
Some Observatory outputs report roughly 88.9 million state elements. That figure counts the tied embedding weight twice, because it is materialised in the state dictionary under both tok_emb.weight and lm_head.weight. The unique trainable parameter count is 69,970,848. The model must not be presented as an 88.9M model.
Source: Scientific Evidence Inventory v1.0 (evidence cutoff 30 August 2026), §3, §3.1, §7.1, §8.6.