Alterlab Research Pipeline

Academic Pipeline v2.6 — Full Academic Research Workflow Orchestrator

A lightweight orchestrator that manages the complete academic pipeline from research exploration to final manuscript. It does not perform substantive work — it only detects stages, recommends modes, dispatches skills, manages transitions, and tracks state.

v2.0 Core Improvements:

1. Mandatory user confirmation checkpoints — Each stage completion requires user confirmation before proceeding to the next step
2. Academic integrity verification — After paper completion and before review submission, 100% reference and data verification must pass
3. Two-stage review — First full review + post-revision focused verification review
4. Final integrity check — After revision completion, re-verify all citations and data are 100% correct
5. Reproducible — Standardized workflow producing consistent quality assurance each time
6. Process documentation — After pipeline completion, automatically generates a "Paper Creation Process Record" PDF documenting the human-AI collaboration history

Quick Start

Full workflow (from scratch):

I want to write a research paper on the impact of AI on higher education quality assurance

--> alterlab-research-pipeline launches, starting from Stage 1 (RESEARCH)

Mid-entry (existing paper):

I already have a paper, help me review it

--> alterlab-research-pipeline detects mid-entry, starting from Stage 2.5 (INTEGRITY)

Revision mode (received reviewer feedback):

I received reviewer comments, help me revise

--> alterlab-research-pipeline detects, starting from Stage 4 (REVISE)

Execution flow:

1. Detect the user's current stage and available materials
2. Recommend the optimal mode for each stage
3. Dispatch the corresponding skill for each stage
4. After each stage completion, proactively prompt and wait for user confirmation
5. Track progress throughout; Pipeline Status Dashboard available at any time

Trigger Conditions

Trigger Keywords

English: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow

Non-Trigger Scenarios

Trigger Exclusions

• If the user only needs a single function (just search materials, just check citations), no pipeline is needed — directly trigger the corresponding skill
• If the user is already using a specific mode of a skill, do not force them into the pipeline
• The pipeline is optional, not mandatory

Pipeline Stages (10 Stages)

Pipeline State Machine

1. Stage 1 RESEARCH -> user confirmation -> Stage 2
2. Stage 2 WRITE -> user confirmation -> Stage 2.5
3. Stage 2.5 INTEGRITY -> PASS -> Stage 3 (FAIL -> fix and re-verify, max 3 rounds)
4. Stage 3 REVIEW -> Accept -> Stage 4.5 / Minor|Major -> Stage 4 / Reject -> Stage 2 or end
5. Stage 4 REVISE -> user confirmation -> Stage 3'
6. Stage 3' RE-REVIEW -> Accept|Minor -> Stage 4.5 / Major -> Stage 4'
7. Stage 4' RE-REVISE -> user confirmation -> Stage 4.5 (no return to review)
8. Stage 4.5 FINAL INTEGRITY -> PASS (zero issues) -> Stage 5 (FAIL -> fix and re-verify)
9. Stage 5 FINALIZE -> MD + DOCX -> ask about LaTeX -> confirm -> PDF -> Stage 6
10. Stage 6 PROCESS SUMMARY -> ask language version -> generate process record MD -> LaTeX -> PDF -> end

See references/pipeline_state_machine.md for complete state transition definitions.

Adaptive Checkpoint System

Core rule: After each stage completion, the system must proactively prompt the user and wait for confirmation. The checkpoint presentation adapts based on context and user engagement.

Checkpoint Types

Decision Dashboard (shown at FULL checkpoints)

━━━ Stage [X] [Name] Complete ━━━

Metrics:
- Word count: [N] (target: [T] +/-10%)    [OK/OVER/UNDER]
- References: [N] (min: [M])              [OK/LOW]
- Coverage: [N]/[T] sections drafted       [COMPLETE/PARTIAL]
- Quality indicators: [score if available]

Deliverables:
- [Material 1]
- [Material 2]

Flagged: [any issues detected, or "None"]

Ready to proceed to Stage [Y]? You can also:
1. View progress (say "status")
2. Adjust settings
3. Pause pipeline
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Adaptive Rules

1. First checkpoint: always FULL
2. After 2+ consecutive "continue" without review: prompt user awareness ("You've auto-continued [N] times. Want to review progress?")
3. Integrity boundaries (Stage 2.5, 4.5): always MANDATORY
4. Review decisions (Stage 3, 3'): always MANDATORY
5. Before finalization (Stage 5): always MANDATORY
6. All other stages: start FULL, downgrade to SLIM if user says "just continue"

Checkpoint Rules

1. Cannot auto-skip MANDATORY checkpoints: Even if the previous stage result is perfect, explicit user input is required at MANDATORY checkpoints
2. User can adjust: At FULL and MANDATORY checkpoints, users can modify the mode or settings for the next step
3. Pause-friendly: Users can pause at any checkpoint and resume later
4. SLIM mode: If the user says "just continue" or "fully automatic," subsequent non-critical checkpoints switch to SLIM format (one-line status + auto-continue), but notifications are still sent
5. Awareness guard: After 4+ consecutive auto-continues, the system inserts a FULL checkpoint regardless of stage type to ensure user remains engaged

Agent Team (3 Agents)

Orchestrator Workflow

The orchestrator runs a four-step loop for every stage:

1. INTAKE & DETECTION — Analyze the user's materials to pick the entry stage (no materials -> Stage 1; paper draft -> Stage 2.5; review comments -> Stage 4; final draft -> Stage 5) and confirm entry point + goal.
2. MODE RECOMMENDATION — Recommend per-stage modes by user type (novice -> socratic/plan/guided; experienced -> full; time-limited -> quick), explaining the trade-offs so the user chooses.
3. STAGE EXECUTION — Dispatch the stage's skill (never doing the work itself), monitor completion, compile deliverables, update state via state_tracker_agent, then raise a MANDATORY checkpoint.
4. TRANSITION — After confirmation, pass deliverables forward via the per-stage handoff protocol, then begin the next stage.

Full detection decision tree, mode-selection matrix, and the complete per-stage handoff mapping: see references/orchestrator_workflow.md.

Integrity & Two-Stage Review Protocols (v2.0)

Stage 2.5 — First Integrity Check (pre-review): After WRITE, before REVIEW. integrity_verification_agent Mode 1 runs Phases A-E (100% reference existence, >=30% citation-context spot-check, 100% statistical data, >=30% originality + self-plagiarism, 30% claim spot-check / min 10 claims). PASS -> Stage 3; FAIL -> correction list, fix item-by-item, re-verify (max 3 rounds).

Stage 4.5 — Final Integrity Check (post-revision): After RE-REVISE / RE-REVIEW-Accept, before FINALIZE. Mode 2 runs Phases A-E at full coverage (100% citation-context, 100% claim verification, zero MAJOR_DISTORTION + zero UNVERIFIABLE required) and cross-checks that every Stage 2.5 issue is resolved. Must PASS with zero issues to reach Stage 5.

Stage 3 — First Review: EIC + R1 (methodology) + R2 (domain) + R3 (interdisciplinary) + Devil's Advocate. Output: 5 reports + Editorial Decision + Revision Roadmap + Socratic Revision Coaching. Accept -> Stage 4.5 / Minor|Major -> Stage 4 / Reject -> Stage 2 or end.

Stage 3' — Verification Review: re-review mode over revised draft + Response to Reviewers. Output: revision-response comparison table + new-issues list + new Editorial Decision. Accept|Minor -> Stage 4.5 / Major -> Stage 4'.

Revision Coaching (Stage 3->4, max 8 rounds) and Residual Coaching (Stage 3'->4', max 5 rounds) use EIC Socratic dialogue; the user can say "just fix it" to skip. Full phase-by-phase execution steps, result handling, and coaching detail: see references/integrity_and_review_protocols.md.

Mid-Entry Protocol

Users can enter from any stage. The orchestrator will:

1. Detect materials: Analyze the content provided by the user to determine what is available
2. Identify gaps: Check what prerequisite materials are needed for the target stage
3. Suggest backfilling: If critical materials are missing, suggest whether to return to earlier stages
4. Direct entry: If materials are sufficient, directly start the specified stage

Important: mid-entry cannot skip Stage 2.5

• If the user brings a paper and enters directly, go through Stage 2.5 (INTEGRITY) first before Stage 3 (REVIEW)
• Only exception: User can provide a previous integrity verification report and content has not been modified

External Review Protocol (Added in v2.5)

Scenario: The user submitted to a journal and received feedback from real human reviewers, bringing those comments into the pipeline.

Trigger: User says "I received reviewer comments," "reviewer comments," "revise and resubmit," etc.

Unlike internal simulated review, external review handles unstructured, variable-quality human comments that must be judged (accept / partially accept / reject) rather than accepted wholesale. The four-step workflow is: (1) intake and structuring into an External Review Summary with user confirmation; (2) strategic revision coaching (judgment + strategy + risk assessment per Major comment, no default "accept all", max 8 rounds); (3) revision + point-by-point Response to Reviewers letter; (4) self-verification for completeness/consistency/truthfulness. Honest capability boundaries apply: AI verification does not equal human-reviewer satisfaction, and final scholarly judgment rests with the researcher.

Full comparison table, per-step templates (External Review Summary, Response to Reviewers), coaching questions, and the four capability-boundary caveats: see references/external_review_protocol.md.

Progress Dashboard

Users can say "status" or "pipeline status" at any time to view:

+=============================================+
|   Academic Pipeline v2.0 Status             |
+=============================================+
| Topic: Impact of AI on Higher Education     |
|        Quality Assurance                    |
+---------------------------------------------+

  Stage 1   RESEARCH          [v] Completed
  Stage 2   WRITE             [v] Completed
  Stage 2.5 INTEGRITY         [v] PASS (62/62 refs verified)
  Stage 3   REVIEW (1st)      [v] Major Revision (5 items)
  Stage 4   REVISE            [v] Completed (5/5 addressed)
  Stage 3'  RE-REVIEW (2nd)   [v] Accept
  Stage 4'  RE-REVISE         [-] Skipped (Accept)
  Stage 4.5 FINAL INTEGRITY   [..] In Progress
  Stage 5   FINALIZE          [ ] Pending
  Stage 6   PROCESS SUMMARY   [ ] Pending

+---------------------------------------------+
| Integrity Verification:                     |
|   Pre-review:  PASS (0 issues)              |
|   Final:       In progress...               |
+---------------------------------------------+
| Review History:                             |
|   Round 1: Major Revision (5 required)      |
|   Round 2: Accept                           |
+=============================================+

See templates/pipeline_status_template.md for the output template.

Revision Loop Management

• Stage 3 (first review) -> Stage 4 (revision) -> Stage 3' (verification review) -> Stage 4' (re-revision, if needed) -> Stage 4.5 (final verification)
• Maximum 1 round of RE-REVISE (Stage 4'): If Stage 3' gives Major, enter Stage 4' for revision then proceed directly to Stage 4.5 (no return to review)
• Pipeline overrides alterlab-paper-writer's max 2 revision rule: In the pipeline, revisions are limited to Stage 4 + Stage 4' (one round each), replacing alterlab-paper-writer's max 2 rounds rule
• Mark unresolved issues as Acknowledged Limitations
• Provide cumulative revision history (each round's decision, items addressed, unresolved items)

Reproducibility

v2.0 design ensures consistent quality assurance with each execution: mandatory Stage 2.5 + 4.5 integrity checks that cannot be skipped, five fixed review perspectives (EIC + R1/R2/R3 + Devil's Advocate), standardized verification search templates, explicit PASS/FAIL thresholds (zero SERIOUS + zero MEDIUM + zero MAJOR_DISTORTION + zero UNVERIFIABLE), and per-stage recorded deliverables for retrospective audit. When the pipeline ends, state_tracker_agent produces a complete audit trail.

Standardized-workflow guarantee table and the full end-of-pipeline audit-trail template: see references/reproducibility_and_audit.md.

Stage 6: Process Summary Protocol (Added in v2.4)

Trigger: After Stage 5 (FINALIZE) completion Purpose: Document the complete human-AI collaboration history for the paper creation process, for user sharing, reporting, or reflection

Workflow: ask language preference (zh / en / both) -> review session history and compile user quotes, per-stage decisions, iteration details, and pipeline statistics -> generate Markdown (paper_creation_process.md / _en.md) -> convert to LaTeX and compile PDF via tectonic (Chinese uses xeCJK + Source Han Serif TC VF). The record ends with a mandatory Collaboration Quality Evaluation — a /insight-style final chapter scoring the user 1-100 across six dimensions (Direction Setting, Intellectual Contribution, Quality Gatekeeping, Iteration Discipline, Delegation Efficiency, Meta-Learning) with honest, evidence-based, constructive analysis (What Worked Well / Missed Opportunities / Recommendations / Human vs AI Value-Add / Claude self-reflection).

Full workflow steps, required-content table, six-dimension score card, scoring-criteria bands, required subsections, evaluation principles, and output specifications: see references/process_summary_protocol.md.

Quality Standards

Error Recovery

Agent File References

Reference Files

Templates

Examples

Output Language

Follows user language. Academic terminology retained in English.

Integration with Other Skills

alterlab-research-pipeline dispatches the following skills (does not do work itself):

Stage 1: alterlab-deep-research
  - socratic mode: Guided research exploration
  - full mode: Complete research report
  - quick mode: Quick research summary

Stage 2: alterlab-paper-writer
  - plan mode: Socratic chapter-by-chapter guidance
  - full mode: Complete paper writing

Stage 2.5: integrity_verification_agent (Mode 1: pre-review)
Stage 4.5: integrity_verification_agent (Mode 2: final-check)

Stage 3: alterlab-paper-reviewer
  - full mode: Complete 5-person review (EIC + R1/R2/R3 + Devil's Advocate)

Stage 3': alterlab-paper-reviewer
  - re-review mode: Verification review (focused on revision responses)

Stage 4/4': alterlab-paper-writer (revision mode)
Stage 5: alterlab-paper-writer (format-convert mode)
  - Step 1: Ask user which academic formatting style (APA 7.0 / Chicago / IEEE, etc.)
  - Step 2: Auto-produce MD + DOCX
  - Step 3: Produce LaTeX (using corresponding document class, e.g., apa7 class for APA 7.0)
  - Step 4: After user confirms content is correct, tectonic compiles PDF (final version)
  - Fonts: Times New Roman (English) + Source Han Serif TC VF (Chinese) + Courier New (monospace)
  - PDF must be compiled from LaTeX (HTML-to-PDF is prohibited)

Related Skills

Version Info

Changelog