Partial-Failure Taxonomy and the Correction Protocol
Agent-Assisted Engineering Check
Prerequisites
Day 88 score sheet and unmet-criteria ledger.
Learning Objective
Classify every sub-2 rubric item into concept_gap, slip, ambiguity, or evidence_gap, and apply the five-step correction protocol: restate, locate, minimal reproduction, fix, retest.
Instructions
1. The four miss types and their signatures:
- concept_gap: you could not produce the method at all (e.g., could not set up the chain rule). Routes to the mapped recovery day — restudy then attempt a NEW variant task.
- slip: method correct, arithmetic/detail wrong (e.g., sign error, off-by-one). Retest the same task; no full recovery day needed.
- ambiguity: the task wording was unclear. Record the unclear wording and resolve it before retesting.
- evidence_gap: answer correct but no verifying command run. Produce the command output; no restudy needed.
2. The correction protocol, applied to each ledger row: (a) restate the task in your own words; (b) locate the exact point of failure; (c) build the smallest reproduction that shows the failure; (d) fix exactly that point — nothing else; (e) retest and record the verifying output.
3. Feedback quality rule: every self-comment must cite the rubric criterion that failed, not just state 'wrong'. Example: 'PY-1 failed criterion tie-order: most_common returned insertion order; fix = sort by (-count, word)'.
4. Decide per row: full recovery day (concept_gap) versus 20-minute targeted review (slip, evidence_gap).
Practice & Prediction Log
Produce corrections_plan.json: every Day-88 ledger row annotated with miss_type, the failed rubric criterion, the correction step taken, and the retest command or task variant.
If you cannot state which rubric criterion failed, classify as concept_gap — not slip.
{
"corrections": [
{"task_id":"PY-2","miss_type":"slip","failed_criterion":"edge-case handling","correction":"added empty-input guard + unittest","retest_command":"python -m unittest -v"},
{"task_id":"MR-1","miss_type":"concept_gap","failed_criterion":"causal-mask mechanism","correction":"restudy day-43 masking derivation, then solve variant MR-1b","retest_command":"paper derivation + mask matrix check"}
]
}
Every failed item carries a miss_type, the failed rubric criterion, a correction step, and a retest plan — classified honestly.
Authoritative Source Resources & Provenance
Improving Students' Learning With Effective Learning Techniques: Promising Directions From Cognitive and Educational Psychology
Relevant Section / Range: Psychological Science in the Public Interest 14(1): 4-58; practice testing and distributed practice sections
Verified Version & Date: Psychological Science in the Public Interest, 2013 (Verified: 2026-10-30)
Detailed comparative review rating practice testing and distributed practice as high-utility techniques while rating highlighting and rereading low-utility; anchors the retrieval, correction, and spaced-review design of Days 88-90.
None beyond general academic reading.
Curriculum restates the utility ratings and application conditions in original prose; every task remains runnable offline.
Compared Candidate Sources & Selection Analysis (2)
Important negative result on learning-styles matching but narrower scope; Dunlosky et al. rates a broader set of techniques directly usable for this curriculum.
Strong trade-book synthesis of the same evidence base; the peer-reviewed review is preferred for citation precision and technique-by-technique utility ratings.
Python Standard Library: Built-in Exceptions
Relevant Section / Range: Concrete exceptions and Exception hierarchy
Verified Version & Date: Python 3.12 (Verified: 2026-10-30)
Normative exception hierarchy used to justify the narrowest correct except clause and FileNotFoundError attributes such as filename and errno.
Basic Python syntax from Study Days 01-09
The drill reproduces FileNotFoundError and ValueError locally, and help(ValueError) documents the hierarchy offline.
Compared Candidate Sources & Selection Analysis (2)
Beginner-friendly but non-normative; omits the OSError attributes and hierarchy precision the diagnosis drills require.
Broader class-oriented chapter; the dedicated exceptions reference is the tighter fit for reading and diagnosing concrete error types during debugging checks.