Phase 6: Generate the fixed prediction corpus #440

Open
opened 2026-10-20 15:05:02 +02:00 by erikinkinen · 0 comments
Owner

Plan ID: P6-02
Record type: Implementation leaf
Scientific protocol: 2.2 · Backlog revision: 2.2.1
Specification: sections 10.1; common contracts in sections 3–5, 11 and 17.4.
Source: AES_PHASES_2_6_PLAN.md, issue heading at line 8065.
Plan SHA-256: 8acdaeb52d6a94fcad7de64d64521cd465f608344d63560b45f9202f5af71212
Protocol snapshot: Download the complete governing plan.

Goal

obtain the 192*(1600+M)-trace internal corpus using existing exact mechanisms.

Prerequisites

Steps

  • Implement the four family and three load-schedule compositions from section 10.1.
  • Add the 192*(1600+M) internal-corpus manifest with the fixed 1200/400 training/validation seeds and M test seeds, capacity preflight and trace identities.
  • Verify natural class prevalence and keep noncollapsing/late-onset traces.

Definition of Done

no new failure event or prediction-controlled intervention exists;
post-onset data remain archived but are ineligible for prediction windows.

Execution and acceptance contract

Apply the governing semantic/data/statistical contracts in sections 3–5 and the relevant phase section, plus the section-11 checks applicable to this task. Section 17.4 defines the required acceptance evidence. Store the outcome and immutable prerequisite/input/output hashes at

artifacts/backlog/2.2.1/P6-02/acceptance.json.

Only explicit dependency and parent-closure edges govern readiness; numbering adds no predecessor dependency. Checkboxes are work/acceptance items, not commit quotas. Keep implementation changes independently reviewable using the existing PR template. Execution, review and gate tasks close with their evidence/decision records and a PR only when tracked artifacts change.

An unsupported scientific effect is a valid result. Missing correctness validation, invalid inference or absent required review is not completion. Do not change endpoints, matrices, margins, inference rules or sample sizes outside the protocol change-control process.

<!-- aes-plan-id: P6-02; backlog-revision: 2.2.1 --> **Plan ID:** `P6-02` **Record type:** Implementation leaf **Scientific protocol:** 2.2 · **Backlog revision:** 2.2.1 **Specification:** sections 10.1; common contracts in sections 3–5, 11 and 17.4. **Source:** `AES_PHASES_2_6_PLAN.md`, issue heading at line 8065. **Plan SHA-256:** `8acdaeb52d6a94fcad7de64d64521cd465f608344d63560b45f9202f5af71212` **Protocol snapshot:** [Download the complete governing plan](https://git.erikinkinen.fi/attachments/31cb768b-4788-4e38-aba9-9d7f0d1ee16d). ## Goal obtain the 192*(1600+M)-trace internal corpus using existing exact mechanisms. ## Prerequisites - [P5-32 (#427)](https://git.erikinkinen.fi/erikinkinen/AES/issues/427) - [P6-01 (#439)](https://git.erikinkinen.fi/erikinkinen/AES/issues/439) ## Steps - [ ] Implement the four family and three load-schedule compositions from section 10.1. - [ ] Add the 192*(1600+M) internal-corpus manifest with the fixed 1200/400 training/validation seeds and M test seeds, capacity preflight and trace identities. - [ ] Verify natural class prevalence and keep noncollapsing/late-onset traces. ## Definition of Done no new failure event or prediction-controlled intervention exists; post-onset data remain archived but are ineligible for prediction windows. ## Execution and acceptance contract Apply the governing semantic/data/statistical contracts in sections 3–5 and the relevant phase section, plus the section-11 checks applicable to this task. Section 17.4 defines the required acceptance evidence. Store the outcome and immutable prerequisite/input/output hashes at `artifacts/backlog/2.2.1/P6-02/acceptance.json`. Only explicit dependency and parent-closure edges govern readiness; numbering adds no predecessor dependency. Checkboxes are work/acceptance items, not commit quotas. Keep implementation changes independently reviewable using the existing PR template. Execution, review and gate tasks close with their evidence/decision records and a PR only when tracked artifacts change. An unsupported scientific effect is a valid result. Missing correctness validation, invalid inference or absent required review is not completion. Do not change endpoints, matrices, margins, inference rules or sample sizes outside the protocol change-control process.
erikinkinen added this to the Phase 6 milestone 2026-10-20 15:05:02 +02:00
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Reference
erikinkinen/AES#440
No description provided.