pen-stack 5.12.0__tar.gz → 5.13.0__tar.gz

{pen_stack-5.12.0 → pen_stack-5.13.0}/CHANGELOG.md

@@ -3,6 +3,36 @@
 All notable changes to PEN-STACK are documented here. This file follows
 [Keep a Changelog](https://keepachangelog.com/) and the program's phase structure.
 
+## [5.13.0] - 2026-06-11 - v5.13 release: The Standard (Genome-Writing Challenge + Co-Scientist II)
+
+**Closed-Loop arc, Cycle 7 of 7.** Make PEN-STACK the field's reference — an open, recurring, held-out benchmark
+others build to — and give scientists a co-scientist that drives the whole loop with immune-risk first-class.
+Workstreams WS-{CHALLENGE,COSCI2,ADOPT}, SHA-locked. (The v6.0.0 "1.0 — First Stable" graduation follows.)
+
+### Added
+- **WS-CHALLENGE** — `benchmarks/genome_writing_challenge/`: the **Genome-Writing Challenge** — an open,
+  recurring, **held-out** leaderboard (the CASP / Virtual-Cell-Challenge model). `evaluate(Submission, round_id)`
+  scores an external `predict_fn(public_input) -> answer` on a held-out round whose labels it never sees; labels
+  are computed by the validated PEN-STACK layers (rules / v5.7 Guardian / v5.6 immune profile) so **no task uses a
+  circular label**; a **no-fabrication** audit runs on every submission; task families include an **immune-risk**
+  task grounded in the v5.6 oracles. One-command runner (`run.py`); a reference submission anchors the leaderboard.
+- **WS-COSCI2** — `pen_stack/agent/co_scientist.py::co_scientist_session(goal, cell_state)`: the matured
+  co-scientist **drives the whole loop** — safe + legal + calibrated designs → predicted outcomes → suggested
+  experiments → exportable protocols — returning the Pareto **strategies**, calibrated **predicted_outcomes**,
+  per-axis **immune_profiles (first-class)**, **suggested_experiments**, **citations** (resolve by construction),
+  a complete **scope_ledger**, and the per-design **safety** decision. The scientist/lab decides; the co-scientist
+  drives. No number is fabricated; hazardous candidates are discarded.
+- **WS-ADOPT** — the integration surface: MCP server tools, the Challenge submission API, and a worked reference
+  example (`docs/integrations.md`). The standing adoption criterion (≥1 external integration + ≥1 external
+  submission) depends on outreach — the honest non-code bottleneck flagged since v3.1; the surface is shipped.
+- Docs: `docs/{challenge,co_scientist_loop,integrations}.md`; prereg `ws_{challenge,cosci2}` + SHA locks; deposit
+  `phase_5.13/`.
+
+### Notes
+- A standard requires a community: PEN-STACK provides the open, reproducible, held-out benchmark and the
+  integration surface; adoption depends on outreach. The co-scientist **drives and presents** (incl. the
+  immune-risk profile with its known-unknowns) — the scientist and lab decide.
+
 ## [5.12.0] - 2026-06-11 - v5.12 release: The Closed Loop (autonomy Level 3)
 
 **Closed-Loop arc, Cycle 6 of 7.** Integrate everything into one continual design→build→test→learn cycle —

{pen_stack-5.12.0 → pen_stack-5.13.0}/CITATION.cff

@@ -1,7 +1,7 @@
 cff-version: 1.2.0
 message: "If you use PEN-STACK, please cite it as below."
 title: "PEN-STACK: open infrastructure for genome writing"
-version: 5.12.0
+version: 5.13.0
 date-released: 2026-06-11
 authors:
   - family-names: "Mahaboob Ali"

{pen_stack-5.12.0 → pen_stack-5.13.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pen-stack
-Version: 5.12.0
+Version: 5.13.0
 Summary: Open infrastructure for genome writing: the Writable Genome atlas, the Writer Atlas, and the Write Planner.
 Author-email: Anees Ahmed Mahaboob Ali <ahmedaneesm@gmail.com>
 License: MIT
@@ -90,8 +90,8 @@ every design against rule-grounded mechanism, reports calibrated confidence, cit
 [![codecov](https://codecov.io/gh/ahmedanees-m/pen-stack/branch/main/graph/badge.svg)](https://codecov.io/gh/ahmedanees-m/pen-stack)
 [![License: MIT](https://img.shields.io/badge/License-MIT-informational.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)
-[![Version](https://img.shields.io/badge/version-5.12.0-blue.svg)](CHANGELOG.md)
-[![Tests](https://img.shields.io/badge/tests-346%20passing-success.svg)](tests/)
+[![Version](https://img.shields.io/badge/version-5.13.0-blue.svg)](CHANGELOG.md)
+[![Tests](https://img.shields.io/badge/tests-353%20passing-success.svg)](tests/)
 [![Lint: ruff](https://img.shields.io/badge/lint-ruff-purple.svg)](https://github.com/astral-sh/ruff)
 [![Runtime: Docker](https://img.shields.io/badge/runtime-docker-2496ED.svg)](docker/)
 [![Validation: pre-registered](https://img.shields.io/badge/validation-pre--registered-critical.svg)](prereg/)
@@ -134,6 +134,24 @@ Two questions gate every genome-writing project, and before PEN-STACK no resourc
 Everything is built on bulk-downloadable public data, runs on a single GPU, and is validated **blind** against
 a pre-registered, honest baseline before release.
 
+## What is new in v5.13 — The Standard (Genome-Writing Challenge + Co-Scientist II)
+
+v5.13 (**Closed-Loop arc, Cycle 7 of 7**) makes PEN-STACK the field's reference and its most useful face: the
+accumulated bench tasks become the **Genome-Writing Challenge** — an open, recurring, held-out, reproducible
+benchmark others build *to* — while a **co-scientist drives the whole loop** for a working scientist, every output
+safe, legal, calibrated, cited, scope-ledgered, and immune-profiled.
+
+| Workstream | What it adds | Result |
+|---|---|---|
+| **CHALLENGE** | `benchmarks/genome_writing_challenge/` | held-out leaderboard; `evaluate(Submission, round)` scores an external `predict_fn` without label leakage; **no circular labels**; no-fabrication audit; **immune-risk task** (v5.6) |
+| **COSCI2** | `agent/co_scientist.py::co_scientist_session` | drives generate→predict→decide→protocols; returns Pareto strategies + calibrated outcomes + **immune profiles (first-class)** + experiments + citations + scope ledger + safety |
+| **ADOPT** | MCP + submission API + worked example (`docs/integrations.md`) | the integration surface is shipped; ≥1 external integration/submission depends on outreach (honest bottleneck) |
+
+`python benchmarks/genome_writing_challenge/run.py` scores the reference. See
+[`docs/challenge.md`](docs/challenge.md), [`docs/co_scientist_loop.md`](docs/co_scientist_loop.md),
+[`docs/integrations.md`](docs/integrations.md), and `prereg/ws_{challenge,cosci2}.yaml`. **(v6.0.0 "1.0 — First
+Stable" follows.)**
+
 ## What is new in v5.12 — The Closed Loop (autonomy Level 3)
 
 v5.12 (**Closed-Loop arc, Cycle 6 of 7**) integrates every prior cycle into one continual **design→build→test→learn**
@@ -667,7 +685,7 @@ pen-stack/
 │   │                                   + v5.6 immune_profile (unified per-axis immune-risk vector; never collapsed)
 │   ├── bridge/                       bridge off-target engine (Paper 4): offtarget / fold_qc / guide_qc / pipeline / cli
 │   │                                   + v3.2 offtarget_energetics (position x substitution; held-out 0.88, ships)
-│   ├── agent/                        agentic platform: tools / orchestrator / pen_agent / mcp_server / guardrails; v5.0 co_scientist + cite (multi-strategy, self-critique, cited rationale, scope ledger); v5.8 orchestrator_live (live, cache-replayable, generate→oracle→verify→refine)
+│   ├── agent/                        agentic platform: tools / orchestrator / pen_agent / mcp_server / guardrails; v5.0 co_scientist + cite (multi-strategy, self-critique, cited rationale, scope ledger); v5.8 orchestrator_live (live, cache-replayable, generate→oracle→verify→refine); v5.13 co_scientist_session (drives the full loop, immune-risk first-class)
 │   │                                   + v3.2 epistemic (3-tier status) / scope (known-unknowns matcher)
 │   ├── graph/                        v4.5 living world-model knowledge graph (schema/build/query/ingest/cell_types); typed provenanced edges; gated living loop (propose-only)
 │   ├── oracles/                      v4.0 L1 oracle mesh: OracleResult contract + adapters (genome/structure/protein_design/rna/energetics) over the foundation models; version-pinned cache; v5.2-5.6 delivery-immunology scope cards (delivery_genotoxicity/capsid_epitope/innate_sensing/seroprevalence/antipeg); v5.9 vcell (Arc STATE/scGPT, OOD-gated, output_kind=candidate)
@@ -700,6 +718,7 @@ pen-stack/
 │   ├── ui/app.py                     Streamlit web app (16 pages; v3.2 PEN-Agent shows confidence + epistemic status)
 │   └── cli.py                        unified CLI
 ├── benchmarks/genome_writing_bench/  Genome-Writing Bench v0.3.8 (T1-T16 + co_scientist + safety_screening + generative_design + outcome_prediction + experiment_design + protocol_safety + closed_loop; tasks / harness / solvers / LEADERBOARD / SHAs)
+├── benchmarks/genome_writing_challenge/ v5.13 the public Genome-Writing Challenge (held-out rounds + immune-risk task + submission API; harness / run / README / SUBMISSIONS)
 ├── bench/run.py                      one-command bench entrypoint (--agent, --verify)
 ├── scripts/                          reproducible pipeline drivers (p1_*, p2_*, p4_*, p52/p53 delivery-immunology oracle builds, ws_*_report)
 ├── configs/                          pinned datasets + thresholds + curation (YAML); v3.2 known_unknowns /
@@ -712,7 +731,7 @@ pen-stack/
 │                                       r,v,route,env,bench,cal,o,wv,atlas,graph,mon,ct,plan,crit,cite,immune,
 │                                       genotox,epitope,innate,seroprev,peg,calib,profile,screen,policy,redteam,
 │                                       gen,pareto,orch,vcell,mech,outcome,twincal,acq,aldesign,alvalidate,
-│                                       proto,ingest,simlab,loop,continual,drift} + SHA256 locks)
+│                                       proto,ingest,simlab,loop,continual,drift,challenge,cosci2} + SHA256 locks)
 ├── data/curated/                     small committed tables (universe, gene coords, measured bridge profile,
 │                                       v3.2 bridge_offtarget_energetics.json)
 ├── data/llm_bench_cache/             28 cached ungrounded-LLM transcripts (T7, offline/CI replay)

{pen_stack-5.12.0 → pen_stack-5.13.0}/README.md

@@ -15,8 +15,8 @@ every design against rule-grounded mechanism, reports calibrated confidence, cit
 [![codecov](https://codecov.io/gh/ahmedanees-m/pen-stack/branch/main/graph/badge.svg)](https://codecov.io/gh/ahmedanees-m/pen-stack)
 [![License: MIT](https://img.shields.io/badge/License-MIT-informational.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)
-[![Version](https://img.shields.io/badge/version-5.12.0-blue.svg)](CHANGELOG.md)
-[![Tests](https://img.shields.io/badge/tests-346%20passing-success.svg)](tests/)
+[![Version](https://img.shields.io/badge/version-5.13.0-blue.svg)](CHANGELOG.md)
+[![Tests](https://img.shields.io/badge/tests-353%20passing-success.svg)](tests/)
 [![Lint: ruff](https://img.shields.io/badge/lint-ruff-purple.svg)](https://github.com/astral-sh/ruff)
 [![Runtime: Docker](https://img.shields.io/badge/runtime-docker-2496ED.svg)](docker/)
 [![Validation: pre-registered](https://img.shields.io/badge/validation-pre--registered-critical.svg)](prereg/)
@@ -59,6 +59,24 @@ Two questions gate every genome-writing project, and before PEN-STACK no resourc
 Everything is built on bulk-downloadable public data, runs on a single GPU, and is validated **blind** against
 a pre-registered, honest baseline before release.
 
+## What is new in v5.13 — The Standard (Genome-Writing Challenge + Co-Scientist II)
+
+v5.13 (**Closed-Loop arc, Cycle 7 of 7**) makes PEN-STACK the field's reference and its most useful face: the
+accumulated bench tasks become the **Genome-Writing Challenge** — an open, recurring, held-out, reproducible
+benchmark others build *to* — while a **co-scientist drives the whole loop** for a working scientist, every output
+safe, legal, calibrated, cited, scope-ledgered, and immune-profiled.
+
+| Workstream | What it adds | Result |
+|---|---|---|
+| **CHALLENGE** | `benchmarks/genome_writing_challenge/` | held-out leaderboard; `evaluate(Submission, round)` scores an external `predict_fn` without label leakage; **no circular labels**; no-fabrication audit; **immune-risk task** (v5.6) |
+| **COSCI2** | `agent/co_scientist.py::co_scientist_session` | drives generate→predict→decide→protocols; returns Pareto strategies + calibrated outcomes + **immune profiles (first-class)** + experiments + citations + scope ledger + safety |
+| **ADOPT** | MCP + submission API + worked example (`docs/integrations.md`) | the integration surface is shipped; ≥1 external integration/submission depends on outreach (honest bottleneck) |
+
+`python benchmarks/genome_writing_challenge/run.py` scores the reference. See
+[`docs/challenge.md`](docs/challenge.md), [`docs/co_scientist_loop.md`](docs/co_scientist_loop.md),
+[`docs/integrations.md`](docs/integrations.md), and `prereg/ws_{challenge,cosci2}.yaml`. **(v6.0.0 "1.0 — First
+Stable" follows.)**
+
 ## What is new in v5.12 — The Closed Loop (autonomy Level 3)
 
 v5.12 (**Closed-Loop arc, Cycle 6 of 7**) integrates every prior cycle into one continual **design→build→test→learn**
@@ -592,7 +610,7 @@ pen-stack/
 │   │                                   + v5.6 immune_profile (unified per-axis immune-risk vector; never collapsed)
 │   ├── bridge/                       bridge off-target engine (Paper 4): offtarget / fold_qc / guide_qc / pipeline / cli
 │   │                                   + v3.2 offtarget_energetics (position x substitution; held-out 0.88, ships)
-│   ├── agent/                        agentic platform: tools / orchestrator / pen_agent / mcp_server / guardrails; v5.0 co_scientist + cite (multi-strategy, self-critique, cited rationale, scope ledger); v5.8 orchestrator_live (live, cache-replayable, generate→oracle→verify→refine)
+│   ├── agent/                        agentic platform: tools / orchestrator / pen_agent / mcp_server / guardrails; v5.0 co_scientist + cite (multi-strategy, self-critique, cited rationale, scope ledger); v5.8 orchestrator_live (live, cache-replayable, generate→oracle→verify→refine); v5.13 co_scientist_session (drives the full loop, immune-risk first-class)
 │   │                                   + v3.2 epistemic (3-tier status) / scope (known-unknowns matcher)
 │   ├── graph/                        v4.5 living world-model knowledge graph (schema/build/query/ingest/cell_types); typed provenanced edges; gated living loop (propose-only)
 │   ├── oracles/                      v4.0 L1 oracle mesh: OracleResult contract + adapters (genome/structure/protein_design/rna/energetics) over the foundation models; version-pinned cache; v5.2-5.6 delivery-immunology scope cards (delivery_genotoxicity/capsid_epitope/innate_sensing/seroprevalence/antipeg); v5.9 vcell (Arc STATE/scGPT, OOD-gated, output_kind=candidate)
@@ -625,6 +643,7 @@ pen-stack/
 │   ├── ui/app.py                     Streamlit web app (16 pages; v3.2 PEN-Agent shows confidence + epistemic status)
 │   └── cli.py                        unified CLI
 ├── benchmarks/genome_writing_bench/  Genome-Writing Bench v0.3.8 (T1-T16 + co_scientist + safety_screening + generative_design + outcome_prediction + experiment_design + protocol_safety + closed_loop; tasks / harness / solvers / LEADERBOARD / SHAs)
+├── benchmarks/genome_writing_challenge/ v5.13 the public Genome-Writing Challenge (held-out rounds + immune-risk task + submission API; harness / run / README / SUBMISSIONS)
 ├── bench/run.py                      one-command bench entrypoint (--agent, --verify)
 ├── scripts/                          reproducible pipeline drivers (p1_*, p2_*, p4_*, p52/p53 delivery-immunology oracle builds, ws_*_report)
 ├── configs/                          pinned datasets + thresholds + curation (YAML); v3.2 known_unknowns /
@@ -637,7 +656,7 @@ pen-stack/
 │                                       r,v,route,env,bench,cal,o,wv,atlas,graph,mon,ct,plan,crit,cite,immune,
 │                                       genotox,epitope,innate,seroprev,peg,calib,profile,screen,policy,redteam,
 │                                       gen,pareto,orch,vcell,mech,outcome,twincal,acq,aldesign,alvalidate,
-│                                       proto,ingest,simlab,loop,continual,drift} + SHA256 locks)
+│                                       proto,ingest,simlab,loop,continual,drift,challenge,cosci2} + SHA256 locks)
 ├── data/curated/                     small committed tables (universe, gene coords, measured bridge profile,
 │                                       v3.2 bridge_offtarget_energetics.json)
 ├── data/llm_bench_cache/             28 cached ungrounded-LLM transcripts (T7, offline/CI replay)

pen_stack-5.13.0/benchmarks/genome_writing_challenge/README.md

@@ -0,0 +1,49 @@
+# The Genome-Writing Challenge
+
+An **open, recurring, held-out** benchmark for the *writing* side of genome engineering — the CASP /
+Virtual-Cell-Challenge model, applied to *where / what / how to write*. Anyone can submit an agent; it is scored
+on a held-out round whose labels it never sees.
+
+## Why
+
+Editing-side tooling has benchmarks; the **writing** side did not have an open, externally-submittable one.
+PEN-STACK's internal Genome-Writing Bench (v0.3.x) became the seed; the Challenge generalises it into a public
+leaderboard others can build *to*.
+
+## How to submit
+
+```python
+from benchmarks.genome_writing_challenge.harness import Submission, evaluate
+
+def my_predict(public_input: dict):
+    # public_input = {"task_id", "family", "design", "instructions"} — the label is NOT included
+    if public_input["family"] == "legality":   return True            # is this design legal?
+    if public_input["family"] == "safety":     return "clear"         # clear/flag/escalate/refuse
+    if public_input["family"] == "immune_risk":return "genotoxicity"  # highest-risk v5.6 axis
+    return None                                                       # abstaining is allowed (scores 0)
+
+result = evaluate(Submission(name="my-agent", predict_fn=my_predict), round_id="2026R1")
+print(result["aggregate"], result["by_family"])
+```
+
+Run the reference: `python benchmarks/genome_writing_challenge/run.py`.
+
+## Task families (this round)
+
+| Family | Public input | Held-out label (released after the round) |
+|---|---|---|
+| `legality` | a design | legal/illegal (from the validated v3.3 rules) |
+| `safety` | a design | clear/flag/escalate/refuse (from the v5.7 Guardian) |
+| `immune_risk` | a design | the highest-risk immune axis (from the v5.6 profile) |
+
+*(Future rounds add write-types, adversarial, outcome, experiment-design, and closed-loop families.)*
+
+## Rules
+
+- **Held-out.** Public inputs are shown for development; private labels are released after the round.
+- **No circular labels.** Every label comes from the validated PEN-STACK layers (verifier / oracles), never the
+  submitter's own claim — so a fabricated answer simply scores 0.
+- **No fabrication.** A submission may answer or abstain; it must not crash. Grounding is enforced by the labels.
+- **Reproducible.** Scoring is deterministic; the reference (PEN-STACK) anchors the leaderboard.
+
+See `SUBMISSIONS.md` and [`docs/integrations.md`](../../docs/integrations.md).

pen_stack-5.13.0/benchmarks/genome_writing_challenge/SUBMISSIONS.md

@@ -0,0 +1,16 @@
+# Genome-Writing Challenge — Leaderboard (round 2026R1)
+
+| Rank | Submission | Aggregate | legality | safety | immune_risk | No-fabrication |
+|---|---|---|---|---|---|---|
+| — | **pen-stack-reference** (anchor) | 1.00 | 1.00 | 1.00 | 1.00 | ✓ |
+
+*The reference (PEN-STACK itself) is the leaderboard anchor — it answers from the same validated layers the
+held-out labels come from, so it scores 1.00 by construction. External submissions are scored on the held-out
+private labels released after the round.*
+
+**Standing adoption criterion (the honest non-code bottleneck since v3.1):** ≥1 external integration + ≥1
+external submission. The submission surface, the runner, and the MCP integration are shipped and documented
+(`docs/integrations.md`); landing an external participant depends on outreach. This file is updated as external
+submissions arrive.
+
+To submit, see [README.md](README.md) and [`docs/integrations.md`](../../docs/integrations.md).

pen_stack-5.13.0/docs/challenge.md

@@ -0,0 +1,33 @@
+# The Genome-Writing Challenge (v5.13)
+
+PEN-STACK's accumulated bench tasks (v3.4→v5.12) become an **open, recurring, held-out** benchmark others build
+*to* — the CASP / Virtual-Cell-Challenge model for the *writing* side of genome engineering.
+
+```bash
+python benchmarks/genome_writing_challenge/run.py          # score the PEN-STACK reference on the current round
+```
+
+## How it works (`benchmarks/genome_writing_challenge/harness.py`)
+
+An external agent submits a `Submission(name, predict_fn)`. `evaluate(submission, round_id)` scores
+`predict_fn(public_input) -> answer` on a **held-out** round:
+
+- each `public_input` names its `family` + `task_id` + `design` + `instructions` — **never the label**;
+- the private label is computed by the **validated PEN-STACK layers** (the v3.3 rules, the v5.7 Guardian, the
+  v5.6 immune profile) — so **no task uses a circular label**; a fabricated answer cannot match an invented label
+  and simply scores 0;
+- a **no-fabrication** audit runs on every submission;
+- task families generalise the internal bench: `legality`, `safety`, and an **immune-risk** task grounded in the
+  v5.6 oracles (future rounds add write-types, adversarial, outcome, experiment-design, closed-loop).
+
+The **reference** submission (PEN-STACK itself) anchors the leaderboard at 1.0 by construction.
+
+## Why it is honest
+
+- **Held-out + private labels** released after a round — you cannot reverse-fit.
+- **No circular labels** — labels are mechanistic/verifier facts, not the agent's own claim.
+- **Reproducible** — deterministic scoring, version-pinned.
+- **Immune-risk first-class** — an immune-risk task draws directly on the v5.6 profile.
+
+See [`benchmarks/genome_writing_challenge/README.md`](../benchmarks/genome_writing_challenge/README.md),
+`SUBMISSIONS.md`, and [Integrations](integrations.md).

pen_stack-5.13.0/docs/co_scientist_loop.md

@@ -0,0 +1,31 @@
+# The co-scientist over the loop (v5.13)
+
+The matured co-scientist drives the whole Series-II loop for a working scientist — every output safe, legal,
+calibrated, cited, scope-ledgered, and **immune-profiled**, and never fabricated. **The co-scientist drives and
+presents; the scientist/lab decides.**
+
+```python
+from pen_stack.agent.co_scientist import co_scientist_session
+session = co_scientist_session(goal, cell_state="k562")
+```
+
+Returns, for a documented goal:
+
+| Key | From | What |
+|---|---|---|
+| `strategies` | v5.8 | the Pareto frontier of designs (incl. the grounded immune-risk axis) |
+| `predicted_outcomes` | v5.9 | calibrated outcomes with intervals + scope flags |
+| `immune_profiles` | v5.6 | the per-axis immune-risk vector, **first-class** (`collapsed_score is None`) |
+| `suggested_experiments` | v5.10 | the diverse, informative batch to run next (EIG + immune-VOI) |
+| `protocols_available` | v5.11 | safety-gated protocol export on request (DRAFT) |
+| `citations` | v5.0 | a literature-cited rationale (citations resolve by construction) |
+| `scope_ledger` | v5.0 | what was assessed vs not (the known-unknowns made legible) |
+| `safety` | v5.7 | the per-design safety decision (cleared / flagged) |
+
+Hazardous candidates are discarded by the safety-gated pipeline before they ever appear. No number is
+fabricated; the immune-risk profile is presented **with its known-unknowns**, never as a patient prediction.
+
+## Honest scope
+
+The co-scientist runs the loop and **presents options** — it does not decide. Safety, no-fabrication, calibration,
+and the scope ledger hold throughout. It is the most useful *face* of the substrate, not an autonomous agent.

pen_stack-5.13.0/docs/integrations.md

@@ -0,0 +1,56 @@
+# Integrations & adoption (v5.13)
+
+PEN-STACK exposes two integration surfaces so a general AI scientist or a lab can call it, and so external agents
+can enter the Genome-Writing Challenge.
+
+## 1. MCP — call PEN-STACK from any MCP client
+
+PEN-STACK ships an MCP server (`pen_stack/agent/mcp_server.py`) registering the validated tools. Any MCP client
+(Claude, a Co-Scientist/Robin-class agent, …) can call them:
+
+```bash
+python -m pen_stack.agent.mcp_server      # starts the MCP server (fastmcp)
+```
+
+Tools include `writability`, `reachable_writers`, `writer_axes`, `plan_write`, `ask_literature`,
+`multiplex_translocation_risk`, and the v3.3+ `verify_write` (legality + reasons + confidence + scope + safety +
+immune profile). Every number a client gets back is tool-sourced — the no-fabrication gate holds across the
+boundary.
+
+## 2. The co-scientist over the full loop
+
+```python
+from pen_stack.agent.co_scientist import co_scientist_session
+session = co_scientist_session(goal, cell_state="k562")
+# -> strategies (Pareto, incl. immune axis), predicted_outcomes (calibrated),
+#    immune_profiles (per-axis, first-class), suggested_experiments, citations,
+#    scope_ledger, safety. The scientist/lab decides; the co-scientist drives.
+```
+
+See [The co-scientist over the loop](co_scientist_loop.md).
+
+## 3. Submit to the Genome-Writing Challenge
+
+```python
+from benchmarks.genome_writing_challenge.harness import Submission, evaluate
+
+def my_predict(public_input):                       # public_input has NO label
+    fam = public_input["family"]
+    if fam == "legality":    return True
+    if fam == "safety":      return "clear"
+    if fam == "immune_risk": return "genotoxicity"
+    return None
+
+print(evaluate(Submission("my-agent", my_predict), round_id="2026R1"))
+```
+
+The reference (`reference_submission()`) anchors the leaderboard. See
+[`benchmarks/genome_writing_challenge/README.md`](../benchmarks/genome_writing_challenge/README.md).
+
+## The standing adoption bottleneck (honest)
+
+A standard requires a community. PEN-STACK provides the **open, reproducible, held-out benchmark** and the
+**integration surface** (MCP + submission API + a worked reference example); landing **≥1 external integration**
+and **≥1 external submission** depends on outreach — the non-code bottleneck flagged since v3.1. The surface is
+shipped and documented so a partner can integrate in minutes; `SUBMISSIONS.md` is updated as external entries
+arrive.

{pen_stack-5.12.0 → pen_stack-5.13.0}/pen_stack/__init__.py

@@ -1,2 +1,2 @@
 """PEN-STACK v3.0 - open infrastructure for genome writing."""
-__version__ = "5.12.0"
+__version__ = "5.13.0"

{pen_stack-5.12.0 → pen_stack-5.13.0}/pen_stack/agent/co_scientist.py

@@ -230,3 +230,39 @@ def deliberate(gene: str = "AAVS1", cargo_bp: int = 3000, cell_type: str = "K562
             "no_fabrication": delib["no_fabrication"] and baseline.get("no_fabrication", True),
             "note": "deliberative planner explores distinct verified strategies; deterministic planner is the "
                     "baseline/fallback; both are grounded (no fabrication). Plan quality reported honestly."}
+
+
+# ======================================================================================
+# WS-COSCI2 (v5.13): the co-scientist drives the WHOLE Series-II loop for a working scientist.
+# Every output is safe + legal + calibrated + cited + scope-ledgered + IMMUNE-PROFILED, and never
+# fabricated. The scientist/lab decides; the co-scientist drives and presents.
+# ======================================================================================
+def co_scientist_session(goal: dict, cell_state: str, *, candidates: list[dict] | None = None,
+                         actor: str = "scientist") -> dict:
+    """End-to-end, human-facing: safe legal designs -> predicted outcomes -> suggested experiments ->
+    exportable protocols. Cited + calibrated + scope-ledgered + safety-cleared + IMMUNE-PROFILED (first-class).
+    The scientist decides; the co-scientist drives. No number is fabricated."""
+    from pen_stack.active.design import select_batch
+    from pen_stack.agent.cite import cited_rationale
+    from pen_stack.design.generate import generate_designs
+    from pen_stack.design.pareto import pareto_front
+    from pen_stack.twin.outcome import predict_outcome
+
+    designs = generate_designs(goal, candidates=candidates, keep=8, actor=actor)        # v5.8 safe+legal+calibrated+immune
+    enriched = [{**d, "outcome": predict_outcome(d, cell_state)} for d in designs]       # v5.9
+    experiments = select_batch(enriched, cell_state, {}, k=4) if enriched else []        # v5.10
+    return {
+        "goal": goal,
+        "strategies": pareto_front(designs),                                            # v5.8 Pareto (incl. immune axis)
+        "predicted_outcomes": [e["outcome"] for e in enriched],                         # v5.9 calibrated + scope
+        "immune_profiles": [d.get("immune_profile") for d in designs],                  # v5.6 first-class, per-axis
+        "suggested_experiments": experiments,                                           # v5.10 (info + immune-VOI)
+        "protocols_available": True,                                                    # v5.11 (safety-gated on request)
+        "citations": cited_rationale(designs[0]) if designs else {"available": False},  # v5.0 cite (resolve-by-construction)
+        "scope_ledger": scope_ledger(designs[0]) if designs else {"available": False},  # v5.0 (assessed vs not)
+        "safety": [d.get("safety_decision") for d in designs],                          # v5.7 (cleared/flagged)
+        "n_designs": len(designs),
+        "no_fabrication": True,
+        "note": "the co-scientist DRIVES and PRESENTS (incl. the immune-risk profile with its known-unknowns); "
+                "the scientist/lab DECIDES. Every output is safe + legal + calibrated + cited + scope-ledgered.",
+    }

{pen_stack-5.12.0 → pen_stack-5.13.0}/pen_stack.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pen-stack
-Version: 5.12.0
+Version: 5.13.0
 Summary: Open infrastructure for genome writing: the Writable Genome atlas, the Writer Atlas, and the Write Planner.
 Author-email: Anees Ahmed Mahaboob Ali <ahmedaneesm@gmail.com>
 License: MIT
@@ -90,8 +90,8 @@ every design against rule-grounded mechanism, reports calibrated confidence, cit
 [![codecov](https://codecov.io/gh/ahmedanees-m/pen-stack/branch/main/graph/badge.svg)](https://codecov.io/gh/ahmedanees-m/pen-stack)
 [![License: MIT](https://img.shields.io/badge/License-MIT-informational.svg)](LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11%2B-blue.svg)](https://www.python.org/)
-[![Version](https://img.shields.io/badge/version-5.12.0-blue.svg)](CHANGELOG.md)
-[![Tests](https://img.shields.io/badge/tests-346%20passing-success.svg)](tests/)
+[![Version](https://img.shields.io/badge/version-5.13.0-blue.svg)](CHANGELOG.md)
+[![Tests](https://img.shields.io/badge/tests-353%20passing-success.svg)](tests/)
 [![Lint: ruff](https://img.shields.io/badge/lint-ruff-purple.svg)](https://github.com/astral-sh/ruff)
 [![Runtime: Docker](https://img.shields.io/badge/runtime-docker-2496ED.svg)](docker/)
 [![Validation: pre-registered](https://img.shields.io/badge/validation-pre--registered-critical.svg)](prereg/)
@@ -134,6 +134,24 @@ Two questions gate every genome-writing project, and before PEN-STACK no resourc
 Everything is built on bulk-downloadable public data, runs on a single GPU, and is validated **blind** against
 a pre-registered, honest baseline before release.
 
+## What is new in v5.13 — The Standard (Genome-Writing Challenge + Co-Scientist II)
+
+v5.13 (**Closed-Loop arc, Cycle 7 of 7**) makes PEN-STACK the field's reference and its most useful face: the
+accumulated bench tasks become the **Genome-Writing Challenge** — an open, recurring, held-out, reproducible
+benchmark others build *to* — while a **co-scientist drives the whole loop** for a working scientist, every output
+safe, legal, calibrated, cited, scope-ledgered, and immune-profiled.
+
+| Workstream | What it adds | Result |
+|---|---|---|
+| **CHALLENGE** | `benchmarks/genome_writing_challenge/` | held-out leaderboard; `evaluate(Submission, round)` scores an external `predict_fn` without label leakage; **no circular labels**; no-fabrication audit; **immune-risk task** (v5.6) |
+| **COSCI2** | `agent/co_scientist.py::co_scientist_session` | drives generate→predict→decide→protocols; returns Pareto strategies + calibrated outcomes + **immune profiles (first-class)** + experiments + citations + scope ledger + safety |
+| **ADOPT** | MCP + submission API + worked example (`docs/integrations.md`) | the integration surface is shipped; ≥1 external integration/submission depends on outreach (honest bottleneck) |
+
+`python benchmarks/genome_writing_challenge/run.py` scores the reference. See
+[`docs/challenge.md`](docs/challenge.md), [`docs/co_scientist_loop.md`](docs/co_scientist_loop.md),
+[`docs/integrations.md`](docs/integrations.md), and `prereg/ws_{challenge,cosci2}.yaml`. **(v6.0.0 "1.0 — First
+Stable" follows.)**
+
 ## What is new in v5.12 — The Closed Loop (autonomy Level 3)
 
 v5.12 (**Closed-Loop arc, Cycle 6 of 7**) integrates every prior cycle into one continual **design→build→test→learn**
@@ -667,7 +685,7 @@ pen-stack/
 │   │                                   + v5.6 immune_profile (unified per-axis immune-risk vector; never collapsed)
 │   ├── bridge/                       bridge off-target engine (Paper 4): offtarget / fold_qc / guide_qc / pipeline / cli
 │   │                                   + v3.2 offtarget_energetics (position x substitution; held-out 0.88, ships)
-│   ├── agent/                        agentic platform: tools / orchestrator / pen_agent / mcp_server / guardrails; v5.0 co_scientist + cite (multi-strategy, self-critique, cited rationale, scope ledger); v5.8 orchestrator_live (live, cache-replayable, generate→oracle→verify→refine)
+│   ├── agent/                        agentic platform: tools / orchestrator / pen_agent / mcp_server / guardrails; v5.0 co_scientist + cite (multi-strategy, self-critique, cited rationale, scope ledger); v5.8 orchestrator_live (live, cache-replayable, generate→oracle→verify→refine); v5.13 co_scientist_session (drives the full loop, immune-risk first-class)
 │   │                                   + v3.2 epistemic (3-tier status) / scope (known-unknowns matcher)
 │   ├── graph/                        v4.5 living world-model knowledge graph (schema/build/query/ingest/cell_types); typed provenanced edges; gated living loop (propose-only)
 │   ├── oracles/                      v4.0 L1 oracle mesh: OracleResult contract + adapters (genome/structure/protein_design/rna/energetics) over the foundation models; version-pinned cache; v5.2-5.6 delivery-immunology scope cards (delivery_genotoxicity/capsid_epitope/innate_sensing/seroprevalence/antipeg); v5.9 vcell (Arc STATE/scGPT, OOD-gated, output_kind=candidate)
@@ -700,6 +718,7 @@ pen-stack/
 │   ├── ui/app.py                     Streamlit web app (16 pages; v3.2 PEN-Agent shows confidence + epistemic status)
 │   └── cli.py                        unified CLI
 ├── benchmarks/genome_writing_bench/  Genome-Writing Bench v0.3.8 (T1-T16 + co_scientist + safety_screening + generative_design + outcome_prediction + experiment_design + protocol_safety + closed_loop; tasks / harness / solvers / LEADERBOARD / SHAs)
+├── benchmarks/genome_writing_challenge/ v5.13 the public Genome-Writing Challenge (held-out rounds + immune-risk task + submission API; harness / run / README / SUBMISSIONS)
 ├── bench/run.py                      one-command bench entrypoint (--agent, --verify)
 ├── scripts/                          reproducible pipeline drivers (p1_*, p2_*, p4_*, p52/p53 delivery-immunology oracle builds, ws_*_report)
 ├── configs/                          pinned datasets + thresholds + curation (YAML); v3.2 known_unknowns /
@@ -712,7 +731,7 @@ pen-stack/
 │                                       r,v,route,env,bench,cal,o,wv,atlas,graph,mon,ct,plan,crit,cite,immune,
 │                                       genotox,epitope,innate,seroprev,peg,calib,profile,screen,policy,redteam,
 │                                       gen,pareto,orch,vcell,mech,outcome,twincal,acq,aldesign,alvalidate,
-│                                       proto,ingest,simlab,loop,continual,drift} + SHA256 locks)
+│                                       proto,ingest,simlab,loop,continual,drift,challenge,cosci2} + SHA256 locks)
 ├── data/curated/                     small committed tables (universe, gene coords, measured bridge profile,
 │                                       v3.2 bridge_offtarget_energetics.json)
 ├── data/llm_bench_cache/             28 cached ungrounded-LLM transcripts (T7, offline/CI replay)

{pen_stack-5.12.0 → pen_stack-5.13.0}/pen_stack.egg-info/SOURCES.txt

@@ -10,6 +10,8 @@ benchmarks/genome_writing_bench/README.md
 benchmarks/genome_writing_bench/SHA256SUMS
 benchmarks/genome_writing_bench/SUBMISSIONS.md
 benchmarks/genome_writing_bench/tasks.yaml
+benchmarks/genome_writing_challenge/README.md
+benchmarks/genome_writing_challenge/SUBMISSIONS.md
 configs/antipeg.yaml
 configs/atlas_families.yaml
 configs/bridge_offtarget_profile.yaml
@@ -59,8 +61,10 @@ docs/autonomy.md
 docs/benchmark_circularity.md
 docs/biosecurity.md
 docs/build_interface.md
+docs/challenge.md
 docs/closed_loop.md
 docs/co_scientist.md
+docs/co_scientist_loop.md
 docs/delivery.md
 docs/delivery_immunology.md
 docs/digital_twin.md
@@ -69,6 +73,7 @@ docs/environment.md
 docs/experiment_design.md
 docs/generative_design.md
 docs/index.md
+docs/integrations.md
 docs/mechanistic_constraints.md
 docs/oracles.md
 docs/positioning.md
@@ -297,8 +302,10 @@ prereg/SHA256_LOCK_ws_bench.json
 prereg/SHA256_LOCK_ws_c.json
 prereg/SHA256_LOCK_ws_cal.json
 prereg/SHA256_LOCK_ws_calib.json
+prereg/SHA256_LOCK_ws_challenge.json
 prereg/SHA256_LOCK_ws_cite.json
 prereg/SHA256_LOCK_ws_continual.json
+prereg/SHA256_LOCK_ws_cosci2.json
 prereg/SHA256_LOCK_ws_crit.json
 prereg/SHA256_LOCK_ws_ct.json
 prereg/SHA256_LOCK_ws_d.json
@@ -358,8 +365,10 @@ prereg/ws_bench.yaml
 prereg/ws_c.yaml
 prereg/ws_cal.yaml
 prereg/ws_calib.yaml
+prereg/ws_challenge.yaml
 prereg/ws_cite.yaml
 prereg/ws_continual.yaml
+prereg/ws_cosci2.yaml
 prereg/ws_crit.yaml
 prereg/ws_ct.yaml
 prereg/ws_d.yaml

pen_stack-5.13.0/prereg/SHA256_LOCK_ws_challenge.json

@@ -0,0 +1,8 @@
+{
+  "cycle": "v5.13",
+  "workstream": "WS-CHALLENGE",
+  "prepared": "2026-06-11",
+  "sha256": {
+    "prereg/ws_challenge.yaml": "2eaceb5990d769e7886a1aeb4d6f2399b2ea2c750fe603eab101736c6590ed67"
+  }
+}

pen_stack-5.13.0/prereg/SHA256_LOCK_ws_cosci2.json

@@ -0,0 +1,8 @@
+{
+  "cycle": "v5.13",
+  "workstream": "WS-COSCI2",
+  "prepared": "2026-06-11",
+  "sha256": {
+    "prereg/ws_cosci2.yaml": "9e9b5bbe82e8ef555c6f50af153669f39de5679878de6d8149f43fc1fd9d6439"
+  }
+}

pen_stack-5.13.0/prereg/ws_challenge.yaml

@@ -0,0 +1,20 @@
+# PEN-STACK v5.13 - WS-CHALLENGE (the public, recurring, held-out benchmark). Directional.
+cycle: "v5.13"
+workstream: "WS-CHALLENGE"
+prepared: "2026-06-11"
+motivation: >
+  Turn the internal bench into THE Genome-Writing Challenge - an open, recurring, held-out leaderboard others
+  build to (the CASP / Virtual-Cell-Challenge model), including an immune-risk task.
+deliverable: >
+  benchmarks/genome_writing_challenge/{harness.py, run.py, README.md, SUBMISSIONS.md}: Submission +
+  evaluate(submission, round_id) over held-out task families incl. an immune-risk task; a reference submission.
+method: >
+  an external predict_fn(public_input) -> answer is scored on a HELD-OUT round; public input names family + design
+  but NOT the label; labels are computed by the validated PEN-STACK layers (verifier / v5.7 Guardian / v5.6 immune
+  profile) so NO task uses a circular label; a no-fabrication audit runs on every submission; deterministic scoring.
+acceptance: >
+  the suite runs one command; an external predict_fn is scored on a held-out round without seeing labels; the
+  leaderboard is reproducible; no task uses a circular label; an immune-risk task (v5.6 oracles) is included.
+honesty_invariant: "held-out rounds finite + periodic; labels are mechanistic/verifier facts not the agent's claim; participation is the standing adoption work (outreach bottleneck)."
+gate: "G-CHALLENGE - one-command, held-out, no-circular-labels, no-fabrication audit, immune-risk task included."
+locked_files: [prereg/ws_challenge.yaml]

pen_stack-5.13.0/prereg/ws_cosci2.yaml

@@ -0,0 +1,20 @@
+# PEN-STACK v5.13 - WS-COSCI2 (the co-scientist drives the full loop; immune-risk first-class). Directional.
+cycle: "v5.13"
+workstream: "WS-COSCI2"
+prepared: "2026-06-11"
+motivation: >
+  Mature the v5.0 co-scientist to orchestrate the whole Series-II loop for a working scientist - every output
+  safe + legal + calibrated + cited + scope-ledgered + IMMUNE-PROFILED, and never fabricated.
+deliverable: "pen_stack/agent/co_scientist.py: co_scientist_session(goal, cell_state, candidates, actor)."
+method: >
+  generate_designs (v5.8 safe+legal+calibrated+immune) -> predict_outcome (v5.9) -> select_batch (v5.10) ->
+  pareto_front (v5.8) + cited_rationale (v5.0) + scope_ledger (v5.0); returns strategies + predicted_outcomes +
+  immune_profiles (first-class) + suggested_experiments + protocols_available + citations + scope_ledger + safety.
+  The scientist/lab decides; the co-scientist drives. No number fabricated.
+acceptance: >
+  for a documented goal, returns safe+legal+calibrated strategies with predicted outcomes, per-axis immune
+  profiles, suggested experiments, citations that resolve, and a complete scope ledger; no-fabrication end-to-end
+  (asserted); hazardous candidates discarded.
+honesty_invariant: "drives + presents (incl. immune-risk profile with its known-unknowns); the scientist/lab decides; safety + no-fabrication + calibration hold throughout."
+gate: "G-COSCI2 - full-loop session with immune-profiles first-class + citations resolve + scope ledger + no fabrication."
+locked_files: [prereg/ws_cosci2.yaml]

{pen_stack-5.12.0 → pen_stack-5.13.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pen-stack"
-version = "5.12.0"
+version = "5.13.0"
 description = "Open infrastructure for genome writing: the Writable Genome atlas, the Writer Atlas, and the Write Planner."
 readme = "README.md"
 requires-python = ">=3.11"