Skip to content

YCC-Lover/research-starter-skills / skills/research-starter-paper

research-starter-paper

Unverified

科研学习与论文写作总入口,协调六个模块。帮助不知道提供什么材料的新手逐步产出、自动保存和恢复项目进度,也用于跨阶段研究任务;区分学习、执行和只读检查。

FileKindSize
SKILL.mdskill md8.8 KB
agents/openai.yamlconfig366 B
assets/evidence-ledger.tsvother106 B
assets/manuscript-plan.mdmarkdown423 B
assets/project-state.mdmarkdown928 B
assets/requirements-research.txtmarkdown263 B
assets/task-brief.mdmarkdown429 B
references/advanced-capabilities.jsonconfig8.5 KB
references/advanced-research.mdmarkdown8.5 KB
references/discipline-fit.mdmarkdown2.3 KB
references/evidence-and-figures.mdmarkdown2.8 KB
references/guided-start.mdmarkdown7.2 KB
references/handoff.mdmarkdown1.9 KB
references/learning.mdmarkdown3.2 KB
references/paper-sections.mdmarkdown5.6 KB
references/research-engine-notice.mdmarkdown1.6 KB
references/research-engine-patches.jsonconfig3.4 KB
references/research-practice.mdmarkdown3.2 KB
references/research.mdmarkdown3.2 KB
references/revision.mdmarkdown2.1 KB
references/runtime-helpers.mdmarkdown6.0 KB
references/source-manifest.jsonconfig34.8 KB
references/sources.mdmarkdown7.4 KB
references/task-brief.mdmarkdown1.6 KB
resources/research-engine/LICENSEother19.1 KB
resources/research-engine/MODE_REGISTRY.mdmarkdown6.7 KB
resources/research-engine/NOTICE.mdmarkdown1.0 KB
resources/research-engine/THIRD_PARTY.mdmarkdown5.0 KB
resources/research-engine/academic-paper-reviewer/WORKFLOW.mdmarkdown43.9 KB
resources/research-engine/academic-paper-reviewer/agents/devils_advocate_reviewer_agent.mdmarkdown42.0 KB
resources/research-engine/academic-paper-reviewer/agents/domain_reviewer_agent.mdmarkdown32.4 KB
resources/research-engine/academic-paper-reviewer/agents/editorial_synthesizer_agent.mdmarkdown41.8 KB
resources/research-engine/academic-paper-reviewer/agents/eic_agent.mdmarkdown28.1 KB
resources/research-engine/academic-paper-reviewer/agents/field_analyst_agent.mdmarkdown11.2 KB
resources/research-engine/academic-paper-reviewer/agents/methodology_reviewer_agent.mdmarkdown44.0 KB
resources/research-engine/academic-paper-reviewer/agents/perspective_reviewer_agent.mdmarkdown32.7 KB
resources/research-engine/academic-paper-reviewer/examples/hei_paper_review_example.mdmarkdown33.8 KB
resources/research-engine/academic-paper-reviewer/examples/interdisciplinary_review_example.mdmarkdown27.6 KB
resources/research-engine/academic-paper-reviewer/examples/subclaim_decomposition_example.mdmarkdown8.3 KB
resources/research-engine/academic-paper-reviewer/references/calibration_mode_protocol.mdmarkdown15.5 KB
resources/research-engine/academic-paper-reviewer/references/changelog.mdmarkdown1.4 KB
resources/research-engine/academic-paper-reviewer/references/editorial_decision_standards.mdmarkdown12.8 KB
resources/research-engine/academic-paper-reviewer/references/guided_mode_protocol.mdmarkdown2.0 KB
resources/research-engine/academic-paper-reviewer/references/integration_guide.mdmarkdown680 B
resources/research-engine/academic-paper-reviewer/references/quality_rubrics.mdmarkdown6.3 KB
resources/research-engine/academic-paper-reviewer/references/re_review_mode_protocol.mdmarkdown51.9 KB
resources/research-engine/academic-paper-reviewer/references/review_criteria_framework.mdmarkdown6.2 KB
resources/research-engine/academic-paper-reviewer/references/review_panel_provenance_protocol.mdmarkdown9.4 KB
resources/research-engine/academic-paper-reviewer/references/review_quality_thinking.mdmarkdown3.3 KB
resources/research-engine/academic-paper-reviewer/references/reviewer_sprint_prompt_source.mdmarkdown47.9 KB
resources/research-engine/academic-paper-reviewer/references/sprint_contract_protocol.mdmarkdown32.1 KB
resources/research-engine/academic-paper-reviewer/references/statistical_reporting_standards.mdmarkdown29.8 KB
resources/research-engine/academic-paper-reviewer/references/top_journals_by_field.mdmarkdown12.6 KB
resources/research-engine/academic-paper-reviewer/templates/editorial_decision_template.mdmarkdown11.0 KB
resources/research-engine/academic-paper-reviewer/templates/peer_review_report_template.mdmarkdown14.8 KB
resources/research-engine/academic-paper-reviewer/templates/revision_response_template.mdmarkdown7.4 KB
resources/research-engine/academic-paper/WORKFLOW.mdmarkdown63.8 KB
resources/research-engine/academic-paper/agents/abstract_bilingual_agent.mdmarkdown12.0 KB
resources/research-engine/academic-paper/agents/argument_builder_agent.mdmarkdown10.9 KB
resources/research-engine/academic-paper/agents/citation_compliance_agent.mdmarkdown23.5 KB
resources/research-engine/academic-paper/agents/draft_writer_agent.mdmarkdown56.1 KB
resources/research-engine/academic-paper/agents/formatter_agent.mdmarkdown63.8 KB
resources/research-engine/academic-paper/agents/intake_agent.mdmarkdown25.5 KB
resources/research-engine/academic-paper/agents/literature_strategist_agent.mdmarkdown46.5 KB
resources/research-engine/academic-paper/agents/peer_reviewer_agent.mdmarkdown29.5 KB
resources/research-engine/academic-paper/agents/revision_coach_agent.mdmarkdown20.0 KB
resources/research-engine/academic-paper/agents/socratic_mentor_agent.mdmarkdown27.9 KB
resources/research-engine/academic-paper/agents/structure_architect_agent.mdmarkdown18.9 KB
resources/research-engine/academic-paper/agents/visualization_agent.mdmarkdown17.2 KB
resources/research-engine/academic-paper/examples/chinese_paper_example.mdmarkdown21.1 KB
resources/research-engine/academic-paper/examples/clinical_citation_verification_checklist.mdmarkdown4.4 KB
resources/research-engine/academic-paper/examples/clinical_epistemic_status_example.mdmarkdown6.6 KB
resources/research-engine/academic-paper/examples/commitment_ledger_example.mdmarkdown8.1 KB
resources/research-engine/academic-paper/examples/imrad_hei_example.mdmarkdown23.3 KB
resources/research-engine/academic-paper/examples/literature_review_example.mdmarkdown30.8 KB
resources/research-engine/academic-paper/examples/plan_mode_guided_writing.mdmarkdown34.3 KB
resources/research-engine/academic-paper/examples/revision_mode_example.mdmarkdown20.1 KB
resources/research-engine/academic-paper/examples/revision_recovery_example.mdmarkdown41.2 KB
resources/research-engine/academic-paper/examples/version_family_reconciliation_example.mdmarkdown3.8 KB
resources/research-engine/academic-paper/references/abstract_writing_guide.mdmarkdown12.5 KB
resources/research-engine/academic-paper/references/academic_writing_style.mdmarkdown7.6 KB
resources/research-engine/academic-paper/references/anti_leakage_protocol.mdmarkdown4.4 KB
resources/research-engine/academic-paper/references/apa7_chinese_citation_guide.mdmarkdown14.0 KB
resources/research-engine/academic-paper/references/apa7_extended_guide.mdmarkdown6.6 KB
resources/research-engine/academic-paper/references/changelog.mdmarkdown2.8 KB
resources/research-engine/academic-paper/references/citation_format_switcher.mdmarkdown7.4 KB
resources/research-engine/academic-paper/references/committee_correspondence_protocol.mdmarkdown6.3 KB
resources/research-engine/academic-paper/references/credit_authorship_guide.mdmarkdown13.7 KB
resources/research-engine/academic-paper/references/disclosure_mode_protocol.mdmarkdown53.9 KB
resources/research-engine/academic-paper/references/domain_evidence_profiles.mdmarkdown4.2 KB
resources/research-engine/academic-paper/references/failure_paths.mdmarkdown14.2 KB
resources/research-engine/academic-paper/references/funding_statement_guide.mdmarkdown11.9 KB
resources/research-engine/academic-paper/references/hei_domain_glossary.mdmarkdown6.8 KB
resources/research-engine/academic-paper/references/intro_title_rhetoric_guide.mdmarkdown8.7 KB
resources/research-engine/academic-paper/references/journal_submission_guide.mdmarkdown8.7 KB
resources/research-engine/academic-paper/references/latex_template_reference.mdmarkdown9.6 KB
resources/research-engine/academic-paper/references/mode_selection_guide.mdmarkdown17.5 KB
resources/research-engine/academic-paper/references/paper_structure_patterns.mdmarkdown8.4 KB
resources/research-engine/academic-paper/references/plan_mode_protocol.mdmarkdown6.7 KB
resources/research-engine/academic-paper/references/policy_anchor_disclosure_protocol.mdmarkdown21.0 KB
resources/research-engine/academic-paper/references/policy_anchor_table.mdmarkdown21.2 KB
resources/research-engine/academic-paper/references/revision_patch_protocol.mdmarkdown12.9 KB
resources/research-engine/academic-paper/references/statistical_visualization_standards.mdmarkdown23.7 KB
resources/research-engine/academic-paper/references/venue_disclosure_policies.mdmarkdown38.4 KB
resources/research-engine/academic-paper/references/vlm_figure_verification.mdmarkdown9.1 KB
resources/research-engine/academic-paper/references/workflow_phase_details.mdmarkdown4.7 KB
resources/research-engine/academic-paper/references/writing_judgment_framework.mdmarkdown3.3 KB
resources/research-engine/academic-paper/references/writing_quality_check.mdmarkdown13.0 KB
resources/research-engine/academic-paper/templates/bilingual_abstract_template.mdmarkdown4.7 KB
resources/research-engine/academic-paper/templates/case_study_template.mdmarkdown2.8 KB
resources/research-engine/academic-paper/templates/conference_paper_template.mdmarkdown2.3 KB
resources/research-engine/academic-paper/templates/credit_statement_template.mdmarkdown4.4 KB
resources/research-engine/academic-paper/templates/funding_statement_template.mdmarkdown8.9 KB
resources/research-engine/academic-paper/templates/imrad_template.mdmarkdown4.4 KB
resources/research-engine/academic-paper/templates/latex_article_template.texother4.7 KB
resources/research-engine/academic-paper/templates/literature_review_template.mdmarkdown2.8 KB
resources/research-engine/academic-paper/templates/policy_brief_template.mdmarkdown3.6 KB
resources/research-engine/academic-paper/templates/revision_tracking_template.mdmarkdown10.2 KB
resources/research-engine/academic-paper/templates/theoretical_paper_template.mdmarkdown2.8 KB
resources/research-engine/academic-pipeline/WORKFLOW.mdmarkdown58.0 KB
resources/research-engine/academic-pipeline/agents/claim_ref_alignment_audit_agent.mdmarkdown44.3 KB
resources/research-engine/academic-pipeline/agents/collaboration_depth_agent.mdmarkdown9.8 KB
resources/research-engine/academic-pipeline/agents/integrity_verification_agent.mdmarkdown70.7 KB
resources/research-engine/academic-pipeline/agents/pipeline_orchestrator_agent.mdmarkdown173.8 KB
resources/research-engine/academic-pipeline/agents/state_tracker_agent.mdmarkdown26.8 KB
resources/research-engine/academic-pipeline/examples/full_pipeline_example.mdmarkdown17.7 KB
resources/research-engine/academic-pipeline/examples/integrity_failure_recovery.mdmarkdown26.8 KB
resources/research-engine/academic-pipeline/examples/mid_entry_example.mdmarkdown13.4 KB
resources/research-engine/academic-pipeline/references/adapters/.gitkeepother0 B
resources/research-engine/academic-pipeline/references/adapters/overview.mdmarkdown10.0 KB
resources/research-engine/academic-pipeline/references/ai_research_failure_modes.mdmarkdown15.6 KB
resources/research-engine/academic-pipeline/references/changelog.mdmarkdown5.8 KB
resources/research-engine/academic-pipeline/references/claim_audit_calibration_protocol.mdmarkdown14.2 KB
resources/research-engine/academic-pipeline/references/claim_verification_protocol.mdmarkdown27.2 KB
resources/research-engine/academic-pipeline/references/external_review_protocol.mdmarkdown6.2 KB
resources/research-engine/academic-pipeline/references/integrity_review_protocol.mdmarkdown7.1 KB
resources/research-engine/academic-pipeline/references/literature_corpus_consumers.mdmarkdown11.7 KB
resources/research-engine/academic-pipeline/references/mode_advisor.mdmarkdown7.8 KB
resources/research-engine/academic-pipeline/references/passport_as_reset_boundary.mdmarkdown18.6 KB
resources/research-engine/academic-pipeline/references/pipeline_state_machine.mdmarkdown28.3 KB
resources/research-engine/academic-pipeline/references/plagiarism_detection_protocol.mdmarkdown13.5 KB
resources/research-engine/academic-pipeline/references/process_summary_protocol.mdmarkdown15.8 KB
resources/research-engine/academic-pipeline/references/progress_dashboard_template.mdmarkdown1.5 KB
resources/research-engine/academic-pipeline/references/reinforcement_content.mdmarkdown1.4 KB
resources/research-engine/academic-pipeline/references/reproducibility_audit.mdmarkdown2.6 KB
resources/research-engine/academic-pipeline/references/score_trajectory_protocol.mdmarkdown3.8 KB
resources/research-engine/academic-pipeline/references/team_collaboration_protocol.mdmarkdown10.1 KB
resources/research-engine/academic-pipeline/references/two_stage_review_protocol.mdmarkdown3.0 KB
resources/research-engine/academic-pipeline/templates/pipeline_status_template.mdmarkdown3.7 KB
resources/research-engine/agents/report_compiler_agent.mdmarkdown26.0 KB
resources/research-engine/agents/research_architect_agent.mdmarkdown25.3 KB
resources/research-engine/agents/screening_reviewer_agent.mdmarkdown4.8 KB
resources/research-engine/agents/synthesis_agent.mdmarkdown28.2 KB
resources/research-engine/commands/ars-3w.mdmarkdown1.1 KB
resources/research-engine/commands/ars-abstract.mdmarkdown1.2 KB
resources/research-engine/commands/ars-cache-invalidate.mdmarkdown1.8 KB
resources/research-engine/commands/ars-citation-check.mdmarkdown971 B
resources/research-engine/commands/ars-disclosure.mdmarkdown1.5 KB
resources/research-engine/commands/ars-format-convert.mdmarkdown1.0 KB
resources/research-engine/commands/ars-full.mdmarkdown1.1 KB
resources/research-engine/commands/ars-lit-review.mdmarkdown1.3 KB
resources/research-engine/commands/ars-mark-read.mdmarkdown2.4 KB
resources/research-engine/commands/ars-outline.mdmarkdown953 B
resources/research-engine/commands/ars-plan.mdmarkdown965 B
resources/research-engine/commands/ars-rebuttal-audit.mdmarkdown1.3 KB
resources/research-engine/commands/ars-reviewer.mdmarkdown1.1 KB
resources/research-engine/commands/ars-revision-coach.mdmarkdown1.5 KB
resources/research-engine/commands/ars-revision.mdmarkdown944 B
resources/research-engine/commands/ars-unmark-read.mdmarkdown1.3 KB
resources/research-engine/deep-research/WORKFLOW.mdmarkdown51.3 KB
resources/research-engine/deep-research/agents/bibliography_agent.mdmarkdown34.4 KB
resources/research-engine/deep-research/agents/devils_advocate_agent.mdmarkdown10.9 KB
resources/research-engine/deep-research/agents/editor_in_chief_agent.mdmarkdown7.9 KB
resources/research-engine/deep-research/agents/ethics_review_agent.mdmarkdown21.7 KB
resources/research-engine/deep-research/agents/meta_analysis_agent.mdmarkdown16.3 KB
resources/research-engine/deep-research/agents/monitoring_agent.mdmarkdown9.2 KB
resources/research-engine/deep-research/agents/report_compiler_agent.mdmarkdown26.0 KB
resources/research-engine/deep-research/agents/research_architect_agent.mdmarkdown25.3 KB
resources/research-engine/deep-research/agents/research_question_agent.mdmarkdown10.1 KB
resources/research-engine/deep-research/agents/risk_of_bias_agent.mdmarkdown12.2 KB
resources/research-engine/deep-research/agents/socratic_mentor_agent.mdmarkdown52.3 KB
resources/research-engine/deep-research/agents/source_verification_agent.mdmarkdown10.3 KB
resources/research-engine/deep-research/agents/synthesis_agent.mdmarkdown28.2 KB
resources/research-engine/deep-research/agents/timeline_extraction_agent.mdmarkdown9.1 KB
resources/research-engine/deep-research/examples/exploratory_research.mdmarkdown6.9 KB
resources/research-engine/deep-research/examples/fact_check_mode.mdmarkdown12.9 KB
resources/research-engine/deep-research/examples/handoff_to_paper.mdmarkdown12.5 KB
resources/research-engine/deep-research/examples/idea_diversity_coverage_gap_advisory.mdmarkdown3.2 KB
resources/research-engine/deep-research/examples/policy_analysis.mdmarkdown9.4 KB
resources/research-engine/deep-research/examples/review_mode.mdmarkdown17.3 KB
resources/research-engine/deep-research/examples/socratic_guided_research.mdmarkdown22.9 KB
resources/research-engine/deep-research/examples/systematic_review.mdmarkdown7.7 KB
resources/research-engine/deep-research/references/apa7_style_guide.mdmarkdown4.6 KB
resources/research-engine/deep-research/references/argumentation_reasoning_framework.mdmarkdown3.9 KB
resources/research-engine/deep-research/references/arxiv_api_protocol.mdmarkdown6.5 KB
resources/research-engine/deep-research/references/changelog.mdmarkdown2.3 KB
resources/research-engine/deep-research/references/chinese_literature_api_protocol.mdmarkdown34.4 KB
resources/research-engine/deep-research/references/cross_agent_quality_definitions.mdmarkdown1.4 KB
resources/research-engine/deep-research/references/crossref_api_protocol.mdmarkdown5.0 KB
resources/research-engine/deep-research/references/equator_reporting_guidelines.mdmarkdown41.8 KB

resources/research-engine/academic-paper/references/revision_patch_protocol.md

View on GitHub
# Revision Patch Protocol (#390)

**Spec:** `docs/design/2026-06-10-390-diff-patch-revision-mode-spec.md` (mechanism §3, coverage claim §4, escalation §3.6).
**Toolchain:** Slice A (#423) — `scripts/_block_parser.py`, `scripts/ars_anchorize_draft.py`, `scripts/ars_apply_revision_patch.py`, schemas under `shared/contracts/patch/`.
**Audience:** the pipeline orchestrator (Mode A) and any user running revision rounds phase-by-phase across sessions (Mode B). The commands below are the same in both modes — Mode A wraps them, Mode B types them.

**What this buys, stated honestly:** under patch apply, a block no operation names cannot be silently distorted, because no generation pass runs over it — that is a property of the apply script, not of the model. It does NOT make the edits themselves better, and structural rewrites are not patch-protected (they escalate, §3.6). Every summary of this feature must survive that sentence.

---

## Artifacts and naming

| Artifact | Produced by | Convention |
|---|---|---|
| Anchored draft | `ars_anchorize_draft.py` (in place) | every block carries `<!--block:BNNNN-->`; IDs never renumbered |
| Block manifest | same run, sidecar | `<draft>.block-manifest.json` — `base_draft_hash` + `{block_id, old_hash, first_line_excerpt}` per block; the ONLY legitimate hash source for a patch |
| Immutable roadmap | editorial synthesizer / confirmed standalone adapter | `revision-roadmap/1.0`, exact draft + block-manifest bindings |
| Claim surface manifest | deterministic registry builder | `claim-surface-manifest/1.0`, exact Claim Intent + UTF-8 surface bindings |
| Author adjudication | `scripts/revision_roadmap.py build-adjudication` from explicit choices | `author-adjudication/1.0`; complete choices and exact authority only |
| Integrity correction list | issuing integrity gate | `integrity-correction-list/1.0`; correction descriptions and exact `proposed_targets` only — a proposal, never write authority |
| Integrity author input | author, from the exact proposed patch shown in-session | `integrity-correction-authorization-input/1.0`; explicit event receipts, one decision per issue, authorized targets/operations, and the author-approved `revision_patch_sha256` |
| Integrity authorization | `scripts/revision_roadmap.py build-integrity-authorization` | `integrity-correction-authorization/1.0`; a deterministic sidecar that copies the author-approved patch hash and adds exact base/list/round bindings |
| Patch document | `draft_writer_agent` (revision invocation) | current `patch_format_version: 1.1`, schema `shared/contracts/patch/revision_patch.schema.json` |
| Revised draft | `ars_apply_revision_patch.py` | `--output` MUST be a new file (versioned artifact; the base is never modified) |
| Apply report | same run, sidecar | `<output>.apply-report.json`, format 1.3 — exact patch/pre/post bindings, replayed authorization witness, per-op claim/collateral declarations, structural and byte-preservation facts |
| Revision-Evidence Bundle | orchestrator | `revision-evidence-bundle/1.0`, continuous chain from exact integrity PASS through every write/no-op round to final draft |

The apply report shares the revised draft's lifecycle: it is a **required input to re-review and the Stage 4.5 integrity gate** — re-reviewers read it to see exactly which blocks changed (`ops_applied[]`, `fresh_block_ids`, `pure_move_pairs`) and which are machine-guaranteed untouched. Consumers verify report-to-artifact freshness by the #576 §11 ORDERED-CHAIN rule (which supersedes the old single-report `output_draft_hash`-vs-handed-draft check — that rule is wrong for multi-round sequences and misses base-link breaks): with reports ordered as applied, the FIRST report's `base_draft_hash` must equal the original (pre-revision) draft's hash prefix, each subsequent report's `base_draft_hash` its predecessor's `output_draft_hash`, and the LAST report's `output_draft_hash` — and only the last's — the handed revised draft's hash prefix. Any broken link means some patch ran against a different text than the chain claims (a rewritten-after-apply draft breaks the last link; a wrong base skews every diff-supported judgment) — treat the affected report(s) as stale and re-derive provenance before relying on them (the same report-to-artifact freshness class as the submission verifier's `STALE-REPORT` guard in `scripts/verify_submission_package.py`; at Stage 3' the chain is checker-enforced as `apply_chain_witness`, `manifest_hash_mismatch` on breakage).

## Mode B command sequence (one revision round)

```bash
# 1. Anchorize / refresh the manifest (idempotent; safe on legacy drafts).
#    Run at EVERY round entry, and rewrite nothing afterwards until apply —
#    any rewrite (including a finalizer pass) invalidates the manifest.
python scripts/ars_anchorize_draft.py draft.md

# 1a. Acronym check (#849): read-only, on the anchored draft. A report with
#     findings goes to the writer with the round's authority artifacts
#     (writing_quality_check.md § F); an integrity-correction round skips it.
python scripts/check_acronyms.py --input draft.md --lang en

# 2. Validate the immutable roadmap, registered claim surfaces, and explicit
#    author sidecar. The writer receives all exact artifacts/bindings and emits
#    phase6_*/revision_patch_round1.json (current format 1.1, never a full draft).
python scripts/revision_roadmap.py validate-adjudication \
    roadmap.json author-adjudication.json \
    --base draft.md \
    --block-manifest draft.md.block-manifest.json \
    --claim-surface claim-surface-manifest.json \
    --artifact-root revision-authority/

# 3. Apply — two-phase fail-closed; output must be a NEW file.
python scripts/ars_apply_revision_patch.py draft.md \
    phase6_revision/revision_patch_round1.json \
    --block-manifest draft.md.block-manifest.json \
    --roadmap roadmap.json \
    --author-adjudication author-adjudication.json \
    --claim-surface-manifest claim-surface-manifest.json \
    --artifact-root revision-authority/ \
    --output draft.rev1.md

# 4. Run your normal post-revision steps (finalizer / citation checks, and
#    the acronym check, whose report goes to the user) on draft.rev1.md,
#    then re-review with draft.rev1.md.apply-report.json attached.
```

Exit codes: `0` applied · `2` Phase 1 rejection (structured failure report on stdout; base byte-untouched) · `3` structural refusal (see escalation) · `4` post-write self-check bug.

**On exit 2 (stale hash / unknown target / authorization/schema failure):** feed the failure report back to the writer for ONE re-emission of the whole patch against the same exact authority artifacts, unless the failure shows that author scope must change. On a second failure, stop: re-anchorize and rebuild the bound authority chain, collect a new explicit author adjudication, narrow the round, or abort. Never hand-edit a patch to force it through — a mismatch means the writer and gate did not share the same exact evidence.

**On exit 3 (structural flags):** the patch touches structure — heading rewrites/deletes, net section-count change, or `touched_ratio` strictly above **0.6** (the #424 ship decision; `insert_after` merely *anchored* on a heading is exempt — inserting body text under a section heading is routine, not structural). Read the flags in the refusal output, then either narrow the patch, or — if the structural change is intended — re-run with the acknowledgment recorded:

```bash
python scripts/ars_apply_revision_patch.py draft.md patch.json \
    --block-manifest draft.md.block-manifest.json \
    --roadmap roadmap.json \
    --author-adjudication author-adjudication.json \
    --claim-surface-manifest claim-surface-manifest.json \
    --artifact-root revision-authority/ \
    --output draft.rev1.md --acknowledge-structural
```

`--acknowledge-structural` is a deliberate user decision, never a default; the flags stay recorded in the apply report either way. `--touched-ratio-threshold 1.0` disables the ratio trigger (the comparator is strict `>`); overriding 0.6 in pipeline runs requires a recorded user decision.

### Integrity-correction variant (one revision round)

An integrity FAIL and its `integrity-correction-list/1.0` identify work to
propose; neither the gate verdict nor the list authorizes a write. The list
contains only `proposed_targets`. The writer first emits an exact patch 1.1
with `authorization_context: integrity_correction`, the supplied exact
`issue_list_sha256`, correction IDs in `roadmap_item_ids`, and empty
`claim_strength_changes[]` / `collateral_authorization_ids[]`. It does not
create or infer author approval.

Present those exact patch bytes and their deterministically computed SHA-256
to the author. Collect `integrity-correction-authorization-input/1.0` with the
same `revision_patch_sha256`, one explicit `authorize` or
`stop_without_write` decision per issue, and the exact authorized target and
operation subset for every `authorize` decision. A `stop_without_write`
decision grants no scope. If the author does not approve the exact patch, stop
without writing; any changed proposal is new bytes and requires a new explicit
input.

The deterministic builder validates the input against the exact patch and
copies the author-approved digest into a hash-bound sidecar:

```bash
python scripts/revision_roadmap.py build-integrity-authorization \
    integrity-correction-list.json \
    --base draft.md \
    --patch phase6_revision/integrity_patch_round1.json \
    --author-choices integrity-author-input.json \
    --output integrity-authorization.json
```

Only then may apply run, and both integrity artifacts are mandatory:

```bash
python scripts/ars_apply_revision_patch.py draft.md \
    phase6_revision/integrity_patch_round1.json \
    --block-manifest draft.md.block-manifest.json \
    --integrity-issue-list integrity-correction-list.json \
    --integrity-authorization integrity-authorization.json \
    --output draft.integrity-rev1.md
```

The apply gate replays the exact patch hash, list/base/round bindings, author
events and decisions, and target/operation subsets before structural analysis
or output creation. An op citing `stop_without_write`, an op outside the exact
authorized subset, or even a one-byte change to the patch rejects the whole
write. Review-roadmap authority arguments are forbidden on this branch.

**Structural scope escalation:** current #670 rounds remain patch-based. If the
authorized scopes cannot express the intended change, stop and collect a new
explicit author sidecar with exact expanded targets, or narrow the edit.
Historical full re-emission remains a visibly separate legacy workflow; it
cannot emit a current 1.3 authorization PASS witness or appear as a current
Revision-Evidence Bundle round.

## Current authorization rules (#670)

- The current CLI rejects patch 1.0. Archived 1.0 schema/runtime live only
  under `shared/contracts/patch/legacy/v1_0/` and `scripts/legacy/`.
- Every review op cites only `will_address` items and stays inside their exact
  authorized block/operation subsets.
- Declined items authorize neither work nor claim movement. An overlapping
  target requires an exact, single-use collateral authorization for every
  declined item on that target.
- Every registered claim surface remains exact or uses one exact single-use
  author-approved replacement (manifest, claim, surface, block, hashes, text,
  rungs, direction). `will_address` alone is not claim authority.
- The report always discloses
  `unregistered_claim_drift_review_required: true`; unregistered semantic
  movement remains an E6 review surface.
- An all-declined round is a `review_noop`: no patch/report and byte-identical
  pre/post drafts.
- An integrity correction list and an integrity-gate result are proposal
  evidence only. The exact writer-emitted patch must be separately approved
  through explicit author input binding its `revision_patch_sha256` and exact
  targets/operations.
- Integrity apply requires both `--integrity-issue-list` and
  `--integrity-authorization`. `stop_without_write` grants no operation, and a
  substituted patch invalidates the hash-bound sidecar before any write.

Validate the accumulated bundle before re-review/final integrity:

```bash
python scripts/revision_roadmap.py validate-bundle \
    revision-evidence-bundle.json --root revision-authority/
```

## Marker lifecycle (one rule for all marker kinds)

`<!--block:-->` markers live in **working drafts only**, exactly like `<!--ref:-->` / `<!--anchor:-->`. Two authoritative rules govern them — this doc indexes them rather than re-owning the wording, so the rule cannot drift out of sync with the surfaces the #390 lint guards:

- **Word counts exclude markers** — strip every `<!--...-->` before `len(body.split())`. Authoritative: `shared/references/word_count_conventions.md` § HTML-comment markers.
- **Phase 7 strips markers from converted final outputs**, after the marker-dependent gates run on the working draft; working drafts and `phase6_*/` artifacts keep theirs (the anchor layer the next round's manifest needs). Authoritative: `formatter_agent.md` § ARS Marker Stripping.
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: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall
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: 115kUpdated Claude CodeCodexVerifiedInstall