πŸƒ Sprint 02: Triage Module + Baseline

Goal: Functional triage module with 4 prompting strategies evaluated on Jira SR subset (200 issues, stratified), baseline implemented, Wilcoxon test applied. Period: 2026-03-29 β†’ 2026-04-08 PEC2 Deadline: 2026-04-08


πŸ“‹ Backlog

  • Download and verify Jira SR dataset (DOI: 10.5281/zenodo.5901893) πŸ“… 2026-03-30
  • Implement stratified sampling script (50 issues Γ— 4 priority classes = 200 total, seed=42) πŸ“… 2026-03-31
  • Implement heuristic baseline (majority class + TF-IDF+SVM) πŸ“… 2026-04-01
  • Implement Zero-Shot prompting template for triage agent πŸ“… 2026-04-01
  • Implement Few-Shot-3 prompting template πŸ“… 2026-04-02
  • Implement Few-Shot-6 prompting template πŸ“… 2026-04-02
  • Implement Chain-of-Thought (CoT) prompting template πŸ“… 2026-04-02
  • Run benchmark: Llama 3.2 8B Γ— 4 strategies Γ— 200 issues (temperature=0, seed=42) πŸ“… 2026-04-03
  • Run benchmark: Mistral 7B Γ— 4 strategies Γ— 200 issues πŸ“… 2026-04-04
  • Generate F1-macro / Precision / Recall results table πŸ“… 2026-04-05
  • Run Wilcoxon signed-rank test (Ξ±=0.05), compute effect size r πŸ“… 2026-04-05
  • Write error analysis by issue type (qualitative) πŸ“… 2026-04-06
  • Integrate CodeCarbon measurement per condition πŸ“… 2026-04-06
  • Update Ch.2 + Ch.3 with methodology description πŸ“… 2026-04-07
  • Commit reproducible code to GitHub with seed=42, requirements.txt fixed πŸ“… 2026-04-07
  • Final review + PEC2 submission πŸ“… 2026-04-08

πŸ”„ In Progress

  • Validate Ollama inference environment (Llama 3.2 8B + Mistral 7B running, latency < 60s) πŸ“… 2026-03-30

πŸ‘οΈ Review

  • Architecture spec updated (SP-Architecture-v1) β€” awaiting advisor feedback

βœ… Done

  • Environment setup: Ollama + models + test inference log βœ… 2026-03-08
  • PEC1: Chapter 1 complete βœ… 2026-03-08
  • H1 + H2 hypotheses formalised βœ… 2026-03-08
  • SLR initial: β‰₯40 references reviewed βœ… 2026-03-08

πŸ“Š Sprint Metrics

MetricValue
Total tasks16 backlog + 1 in progress
Completed4
Carried over from Sprint 10
Target velocity16 tasks / 10 days

πŸ” Sprint 1 Retrospective

What went well: PEC1 delivered on time with strong theoretical framing. 40+ references reviewed. Hypotheses formally falsifiable.

What to improve: Start coding earlier. Set up CodeCarbon before running any experiments.

Sprint 2 focus: Execution. Every day should produce measurable output (code / results / text).