Separate authority projection and delivery in measured seed review

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9

research/evolution/EvolutionReport.md

@@ -55,9 +55,9 @@ Ten selected retrospective outcomes (not a historical census), followed by prosp
 | inconclusive | 0 |
 | merge | 0 |
 | rejection | 0 |
-| revision | 12 |
+| revision | 13 |
 
-Cycles with recorded research effort: 4/14. Unknown effort is neither zero nor estimated from commits, tokens or assertion counts.
+Cycles with recorded research effort: 5/15. Unknown effort is neither zero nor estimated from commits, tokens or assertion counts.
 
 ### Stream B / B-independent-navigation-source-v1
 
@@ -91,6 +91,14 @@ One bounded question counts at most one consequential outcome. Corroboration and
 
 One bounded question counts at most one consequential outcome. Corroboration and inconclusive work remain visible separately. Fewer than three comparable cycles: no trend assessment.
 
+### Stream cross-stream / CD-authority-projection-documentary-v1
+
+| Cycle | Outcome | Research minutes | Consequential outcome/hour |
+| --- | --- | ---: | ---: |
+| LEARN-0015 | revision | 3.128 | 19.18 |
+
+One bounded question counts at most one consequential outcome. Corroboration and inconclusive work remain visible separately. Fewer than three comparable cycles: no trend assessment.
+
 ## Coherence and maintainability
 
 Profile hashes and local references passed validation when this report was generated. That checks traceability, not source truth or external URL freshness.
@@ -569,3 +577,17 @@ Evidence: [ZulipNavigationSourceStudy](../../research/reviews/ZulipNavigationSou
 Remaining uncertainty: Static targeted ranges in twelve files, no Zulip runtime/upstream test execution or independent human/AT review. Auxiliary lookup/anchor continuations, deferred focus and callback wiring need a bounded follow-up before any race claim. One Zulip family supplies partial mechanisms, not full-contract recurrence or a no-script guarantee.
 
 Supersedes: none recorded.
+
+### LEARN-0015 — Do the six authority/projection seeds denote reusable patterns or a mixture of scoped acceptance, projection placement and delivery choices?
+
+2026-09-27 · stream cross-stream · prospective · revision
+
+Before: Authority is scoped and acknowledgement levels differ, but six seed names lack developed contracts and their projection/delivery relationships are not explicitly compared.
+
+Conclusion: Revise the research decision aid to separate scoped acceptance, projection computation and delivery timing with compatibility constraints. Six seed dispositions and two synthetic traces; retain all seeds, zero new drafts or candidate maturity changes.
+
+Evidence: [AuthorityProjectionComparison](../../research/reviews/AuthorityProjectionComparison.md), [2026-09-27-authority-projection-effort](../../research/evolution/cycles/2026-09-27-authority-projection-effort.json).
+
+Remaining uncertainty: Six living primary documents across four families, not independent full-contract implementations; exact revisions unknown. Synthetic VC-01/02 reasoning is not execution or demonstrated usefulness; authority/merge/storage and phase-specific recovery contracts still need application evidence. Existing candidate profiles unchanged; five prospective groups are not a comparable learning trend.
+
+Supersedes: none recorded.

research/evolution/cycles/2026-09-27-authority-projection-effort.json

@@ -0,0 +1,26 @@
+{
+  "start": 204294.311997571,
+  "start_utc": "2026-09-26T23:53:48.559040+00:00",
+  "execution_seconds": 1.9966537069994956,
+  "executions": [
+    {
+      "command": [
+        "make",
+        "classification-check",
+        "evolution-check",
+        "evolution-test",
+        "schema-test"
+      ],
+      "seconds": 1.9966537069994956,
+      "exit_code": 0
+    }
+  ],
+  "status": "complete",
+  "end_utc": "2026-09-26T23:57:12.882038+00:00",
+  "elapsed_seconds": 189.673,
+  "research_minutes": 3.128,
+  "execution_minutes": 0.033,
+  "method": "Monotonic single-agent elapsed session minus timed repository-check subprocesses. Source retrieval, interpretation and recording count as active research; no application or upstream tests executed.",
+  "excluded": "Preregistration and final receipt refresh, commit/snapshot/sync administration after cutoff. Tokens and cost unknown.",
+  "budget": "Six primary documents / four source families; within 45 research and 10 verification minutes."
+}

research/evolution/ledger.json

@@ -489,6 +489,40 @@
         "cost_usd": null
       },
       "supersedes": []
+    },
+    {
+      "id": "LEARN-0015",
+      "date": "2026-09-27",
+      "recording": "prospective",
+      "stream": "cross-stream",
+      "comparison_group": "CD-authority-projection-documentary-v1",
+      "protocol_ref": "research/evolution/cycles/2026-09-27-authority-projection.md",
+      "question": "Do the six authority/projection seeds denote reusable patterns or a mixture of scoped acceptance, projection placement and delivery choices?",
+      "previous_belief": "Authority is scoped and acknowledgement levels differ, but six seed names lack developed contracts and their projection/delivery relationships are not explicitly compared.",
+      "conclusion": "Revise the research decision aid to separate scoped acceptance, projection computation and delivery timing with compatibility constraints. Six seed dispositions and two synthetic traces; retain all seeds, zero new drafts or candidate maturity changes.",
+      "disposition": "revision",
+      "affected_patterns": [],
+      "evidence": [
+        "research/reviews/AuthorityProjectionComparison.md",
+        "research/evolution/cycles/2026-09-27-authority-projection-effort.json"
+      ],
+      "remaining_uncertainty": [
+        "Six living primary documents across four families, not independent full-contract implementations; exact revisions unknown.",
+        "Synthetic VC-01/02 reasoning is not execution or demonstrated usefulness; authority/merge/storage and phase-specific recovery contracts still need application evidence.",
+        "Existing candidate profiles unchanged; five prospective groups are not a comparable learning trend."
+      ],
+      "reviewer": {
+        "name": "Codex",
+        "role": "author-model",
+        "independent_human": false
+      },
+      "effort": {
+        "research_minutes": 3.128,
+        "execution_minutes": 0.033,
+        "reported_tokens": null,
+        "cost_usd": null
+      },
+      "supersedes": []
     }
   ]
 }