zrwangems/dsh-zrwang-plugin / ars/skills/academic-paper
academic-paper
Flagged学术论文写作:按 IMRaD 或领域结构成稿,含大纲、论证地图、双语摘要、图表与题注、引用格式转换、返修与逐条回复、AI 使用声明。Triggers: write a paper, academic paper, paper outline, revise paper, reviewer comments, rebuttal, citation check, abstract | 写论文, 论文大纲, 修改论文, 审稿意见, 返修, 审稿回复, 引文核对, 写摘要。
_shared/contracts/passport/uncited_audit_failure.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://github.com/Imbad0202/academic-research-skills/shared/contracts/passport/uncited_audit_failure.schema.json",
"title": "Material Passport Uncited Audit Failure Entry",
"description": "One entry in Material Passport Schema 9 uncited_audit_failures[] aggregate (v3.8.2 / #118). Per uncited-sentence × manifest pair where the constraint judge raised a JudgeInvocationError during §4 step 5 stream (d) judging. Rides in its own aggregate because the cited-path INV-14 audit_tool_failure row (a claim_audit_result entry carrying ref_retrieval_method=audit_tool_failure) cannot be reused — claim_audit_result.ref_slug is required and the uncited path has no ref to bind; uncited_assertion is LOW-WARN advisory and routing UAF through it would conflate D4-c detector signal with audit-time infrastructure failure. Drives the [CLAIM-AUDIT-TOOL-FAILURE-UNCITED — <fault-class>] formatter annotation at MED-WARN advisory tier; gate passes — retry-next-pass remediation. Pre-v3.8.2 behaviour silently substituted NOT_VIOLATED on JudgeInvocationError and suppressed HIGH-WARN constraint checks; v3.8.2 routes failures through this aggregate so operational signal surfaces without dropping audit coverage. Cross-field invariants UAF-INV-1..UAF-INV-6 are lint-enforced in scripts/check_claim_audit_consistency.py. See docs/design/2026-05-15-issue-103-claim-alignment-audit-spec.md §3.6.",
"type": "object",
"additionalProperties": false,
"required": [
"finding_id",
"claim_text",
"section_path",
"scoped_manifest_id",
"fault_class",
"rationale",
"judge_model",
"judge_run_at",
"rule_version"
],
"properties": {
"finding_id": {
"type": "string",
"pattern": "^UAF-[0-9]{3,}$",
"description": "Per-passport unique finding identifier for uncited_audit_failures[]. UAF-INV-1 enforces uniqueness."
},
"claim_text": { "type": "string", "minLength": 1, "maxLength": 2000 },
"section_path": {
"type": "string",
"minLength": 1,
"description": "Hierarchical path from document root to the section containing the offending sentence. Mirrors uncited_assertion.section_path."
},
"scoped_manifest_id": {
"type": "string",
"pattern": "^M-[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}Z-[0-9a-f]{4}$",
"description": "Points to the claim_intent_manifest.manifest_id whose MNC/NC-C set was being judged when the failure occurred. Required — no MANIFEST-MISSING sentinel admitted; UAF emission requires an active manifest scope. UAF-INV-2 enforces cross-array resolvability."
},
"manifest_claim_id": {
"type": ["string", "null"],
"pattern": "^C-[0-9]{3,}$",
"description": "When the sentence was bound to a manifest claim (sentence carries manifest_claim_id per §4 step 5 stream (d) NC-C judging path), points to that claim. Null when the judge call was against MNCs only (manifest-wide constraints, no claim binding). UAF-INV-3 enforces (scoped_manifest_id, manifest_claim_id) pair integrity when non-null. Mirrors constraint_violation.manifest_claim_id polarity."
},
"fault_class": {
"enum": [
"judge_timeout",
"judge_api_error",
"judge_parse_error",
"cache_corruption",
"retrieval_api_error",
"retrieval_timeout",
"retrieval_network_error"
],
"description": "Same closed enum as INV-14 fault-class taxonomy on the cited path. Sourced from JudgeInvocationError.fault_class at the raise site in claim_audit_pipeline.py."
},
"rationale": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "MUST begin with this row's fault_class value followed by ': ' and a free-form detail. UAF-INV-5 enforces the prefix match. Example: 'judge_timeout: judge timed out after 30s'. Mirrors INV-14 rationale format on the cited path."
},
"judge_model": { "type": "string", "minLength": 1 },
"judge_run_at": { "type": "string", "format": "date-time" },
"rule_version": {
"const": "D4-c-v1-uaf-v1",
"description": "Frozen literal for the v3.8.2 release. UAF surface version. Distinguishes from D4-c-v1 (uncited_assertion D4-c detector) and D4-a-v1 (constraint_violation). Future revisions bump the literal and require re-lint."
},
"upstream_owner_agent": {
"enum": ["synthesis_agent", "draft_writer_agent", "report_compiler_agent", null]
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |