From https://github.com/tang-vu/keryx/releases/tag/v0.27.68, prepare an editor's release summary that states what changed and what a release note cannot establish about actual user adoption. Cite only material actually retrieved; keep unread sources and unsupported points explicit. Do not force a purchase or a reward.
· llm:deepseek:deepseek-v4-pro
Decision log · 119 steps
Sign in with the original report owner to review its decisions.
Read checkpoints
Verify locally replays supported recorded query-local reserve, release, debit and hold decisions, attribution normalization and exact micro-USDC citation/author allocations. Model proposals and eligibility are asserted inputs. Query capacity is separate from signer exposure; verification does not establish funding, reward authority or settlement.
Economic families or records marked unavailable are not verified. Missing, fractional-micro or unsafe operands are never repaired; an empty family means no captured economic decision, not complete monetary coverage.
- Query-local budget records
- Recorded decisions can be replayed
- Citation allocation records
- Recorded decisions can be replayed
- Author split records
- Not captured
Model proposals and selected plan actions are recorded when available. Model generation is not replayed or expected to reproduce; verification checks only deterministic checkpoints.
Micro-USDC is shown only where the existing exact converter accepts the amount. Other monetary assertions are unavailable; numeric predicate replay preserves the recorded comparison.
- Recorded checkpoint policy
- ordinary-query-economics-v4
- SHA-256 retained by this report
- d6fa5ca425ab078b2a0422559bf989e8acf473f9d90c35476aac263e7fc71f82
Keep this digest separately from the downloaded sidecar. The offline audit command uses it as the expected digest.
Model proposal → selected plan → code checkpoint
Latest terminal checkpoint outcome per recorded candidate; continuing checks and global stops are excluded. These are not settled purchases or quality scores.
Global stop checkpoints: 1 · Candidate rounds with continuing checks only: 0
| Candidate | Read round | Model proposed | Selected plan | Checkpoint | Code result | Reason / rule |
|---|---|---|---|---|---|---|
| 65 | 0 | CACHE | CACHE | selection | CONTINUE | selected-plan |
| 87 | 0 | CACHE | CACHE | selection | CONTINUE | selected-plan |
| 1 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 2 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 3 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 4 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 5 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 6 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 7 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 8 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 9 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 10 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 11 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 12 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 13 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 14 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 15 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 16 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 17 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 18 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 19 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 20 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 21 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 22 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 23 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 24 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 25 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 26 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 27 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 28 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 29 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 30 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 31 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 32 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 33 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 34 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 35 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 36 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 37 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 38 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 39 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 40 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 41 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 42 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 43 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 44 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 45 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 46 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 47 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 48 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 49 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 50 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 51 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 52 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 53 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 54 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 55 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 56 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 57 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 58 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 59 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 60 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 61 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 62 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 63 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 64 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 66 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 67 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 68 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 69 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 70 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 71 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 72 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 73 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 74 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 75 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 76 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 77 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 78 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 79 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 80 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 81 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 82 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 83 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 84 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 85 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 86 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 88 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 89 | 0 | CACHE | SKIP | selection | SKIP | plan-skip |
| 90 | 0 | SKIP | SKIP | selection | SKIP | plan-skip |
| 65 | 0 | CACHE | CACHE | duplicate | CONTINUE | duplicate |
| 65 | 0 | CACHE | CACHE | public-route | FREE | public-channel |
| 87 | 0 | CACHE | CACHE | duplicate | CONTINUE | duplicate |
| 87 | 0 | CACHE | CACHE | public-route | FREE | public-channel |
| Run context | 0 | — | — | expansion | CONTINUE | expansion |
| Run context | 1 | — | — | attention | CONTINUE | attention |
| Run context | 1 | — | — | recommendation | CONTINUE | engine-recommendation |
| Run context | 1 | — | — | recommendation | STOP | engine-recommendation |
Try a different limit
Compare only recorded budget and attention checks. Later reads, model choices and a whole alternative answer are unknown. These controls never change a live policy or authorize a purchase.
Portable research receipt
Take the evidence trail with you
One deterministic JSON bundle binds the answer, visible decisions, exact article versions, claim evidence and a Circle-settlement snapshot under SHA-256. Retain the digest to detect later changes; the self-check is not a publisher or Keryx signature.
Recorded purchase outcomes
Recorded purchase outcomes are unavailable for this retained snapshot. No score or zero-cost success is inferred; the original report and receipt remain available.
Carries this dispatch’s question as context — never its answer. The next dispatch is read from sources bought for it.