Dashboard › institutional-transition-lab › Distillation
Distillation
ID: 9676bf34-a0c1-423a-9996-abc00673bf4a
Generation: 0
Tokens: 511
R_compression: 22.323
C_norm: 0.000
Archived: No
Created: 2026-09-08 20:40:24
Source IDs:
["lore_tm_v1_viwad4neukPNE_1vTx77SCrO7xp2HywpkDP21INiAM0","lore_tm_v1_Gy-reb-dPHCy8tQufQ-lmEAYkEU7i8zZhibWJflvfMs"]
Observations
- 🔴 (20:37) User provided
/home/byk/Code/institutional-transition-lab/research/oss-governance-coding-protocol-v1.2.md, titled “Performance-blinded OSS governance coding protocol v1.2,” with status pre-adjudication evaluator correction; model-informed development protocol; it was frozen on 2026-08-27. (meaning Aug 27, 2026)
- 🔴 (20:37) Protocol v1.2 states the V1.1 run used the intended frozen 40-record manifest and unchanged coders, but its mandatory artifact audit found that “strict edge agreement” compared actor, right, target, direction, and status while omitting edge scope and evidence references; it also failed to route separately coded body/patch-relationship disagreements.
- 🔴 (20:37) Protocol v1.2 states 6 records were consequently labeled
provisional_exact_agreement despite material differences.
- 🔴 (20:37) Protocol v1.2 corrects the evaluator before source adjudication or canonical graph construction: 1. strict edge signatures include scope and complete grounded evidence references; 2. body/patch-relationship disagreement becomes an explicit route reason; 3. the remaining non-routed state is renamed
provisional_core_agreement; 4. full-response agreement is reported separately and is not required because titles and numeric confidence are not canonical research fields.
- 🔴 (20:37) Protocol v1.2 routes 35 records rather than 29, reuses the byte-identical V1.1 coding bundle and both Luna response files from workflow run
33060493337, and repeats only the Terra advisory pass over the corrected route to isolate the evaluator change from model sampling variance.
- 🔴 (20:37) Protocol v1.2 states no model response, performance observation, transition date, or desired result influenced the correction; Terra remains advisory, all records remain ineligible for the canonical ledger, and the response schema and frozen envelope remain unchanged.
- 🟡 (20:37) Assistant identified a provenance rule from the envelope check: an invalid frozen response cannot be used as a graph-diff baseline.
- 🟡 (20:37) For the Terraform Habitat revert adjudication, assistant chose schema-valid
luna_b as the closest graph-diff baseline instead of the invalid frozen response; the resulting revision requires adding 1 grounded removal edge and removing 0 frozen edges.