docs: publish KHIPU-R2 card from szl-forge@72544fd0be1c8a312660c57d8460648c87df2d47

Exact-source KHIPU-R2 card publication. The measured 3/6 abstention result remains explicitly not a pass; publication_eligible and autonomy_eligible remain false. No weights, adapter, configs, evals, visibility, hardware, or runtime state changed.

README.md

@@ -1,5 +1,5 @@
 ---
-thumbnail: https://huggingface.co/SZLHOLDINGS/KHIPU-R2/resolve/main/og-card.png
+thumbnail: https://huggingface.co/SZLHOLDINGS/KHIPU-R2/resolve/9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52/og-card.png
 license: apache-2.0
 language:
   - en
@@ -32,113 +32,105 @@ szl:
   gpu: UNAVAILABLE
 ---
 
-<p align="center">
-  <img src="holo-banner.svg" alt="KHIPU-R2 — holographic step-up banner" width="100%"/>
-</p>
+# KHIPU-R2
 
-<h1 align="center">K H I P U — R 2</h1>
+**Research-only · historical abstention 3/6 · publication and autonomy gates closed**
 
-<p align="center"><em>Failure is an artifact, not a footnote.</em></p>
+Adapters are on this repo. Abstain is MEASURED 3/6, not a pass.
+That statement describes the dated owner-run records below, rather than
+a new evaluation or current model qualification. This is a separate
+abstention-retraining SKU. Not a replacement for `SZL-Khipu-1.5B`.
 
-<p align="center">
-  <img alt="Base: Qwen2.5-1.5B-Instruct" src="https://img.shields.io/badge/base-Qwen2.5--1.5B--Instruct-334155?style=flat-square"/>
-  <img alt="Downloads" src="https://img.shields.io/huggingface/dt/SZLHOLDINGS/KHIPU-R2?style=flat-square&color=3af4c8&label=downloads"/>
-  <img alt="Artifact: QLoRA adapter r=32 a=64" src="https://img.shields.io/badge/artifact-QLoRA%20adapter%20r32%20a64-0d9488?style=flat-square"/>
-  <img alt="Abstain: MEASURED 3/6, was 2/6 — not a pass" src="https://img.shields.io/badge/abstain-3%2F6%20was%202%2F6%20%C2%B7%20not%20a%20pass-b45309?style=flat-square"/>
-  <img alt="Plan-valid 11/11" src="https://img.shields.io/badge/plan--valid-11%2F11-16a34a?style=flat-square"/>
-  <img alt="Hallucinated citations: 0" src="https://img.shields.io/badge/hallucinated%20citations-0-16a34a?style=flat-square"/>
-  <img alt="Lifecycle: research-only" src="https://img.shields.io/badge/lifecycle-research--only-7e8aa3?style=flat-square"/>
-</p>
+Card and metadata review snapshot: [9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52](https://huggingface.co/SZLHOLDINGS/KHIPU-R2/tree/9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52).
+No weights were downloaded, no model was loaded, and no evaluation or
+signature verification was rerun in this review.
 
-<p align="center">
-  <code>KANCHAY</code> · Doctrine v11 · Lean <code>749/14/163</code> · Λ = Conjecture 1 (advisory) · <a href="https://a-11-oy.com">a-11-oy.com</a>
-</p>
+## Distributed forms
 
-Adapters are on this repo. Abstain is MEASURED 3/6, not a pass. This card-only release does not modify adapter files and does not open the publication or autonomy gates.
-
-QLoRA adapter on disclosed [`Qwen/Qwen2.5-1.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) (runtime `unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit`). Proposal-only brain navigator / abstain retrain. Doctrine v11 LOCKED. Λ = Conjecture 1 (advisory, never a theorem).
-
-<!-- SZL-ATELIER-CUT:v1:START -->
-## The cut
-
-Leaders ship v1 and changelog the rest. We name the retraining of silence as its own model. Failure is an artifact, not a footnote.
-
-A public retrain whose only job is to improve one metric: honest abstain under adversarial handles.
-
-### Silhouette → leave → SZL
-
-| Leader | Take, then tweak |
-|---|---|
-| Anthropic | Red-team → constitution update. We red-team → adapter. |
-| NVIDIA | Recipe re-run with a new seed and a bounded delta. |
-| Unsloth | Same FastLanguageModel loop, new curriculum, new evidence record. |
-
-This card makes the combination inspectable: a separate abstain-retraining SKU, bounded small-sample results, and an exact-source documentation publisher that cannot modify weights or promotion state.
-
-## Intended use
-
-Continue the abstain-retrain loop. Keep publication and autonomy gates closed until independently verifiable evaluation evidence satisfies the governed release criteria.
-
-## Limitations
-
-- research-only
-- No signed R2 eval receipt in this atelier.
-- Publishing this card is a documentation update, not model promotion or autonomy approval.
-
-Canonical GitHub: [`szl-holdings/szl-forge/khipu_r2`](https://github.com/szl-holdings/szl-forge/tree/main/khipu_r2)
-<!-- SZL-ATELIER-CUT:v1:END -->
-
-## Specification
-
-| | |
-|---|---|
-| **Artifact** | `adapter_model.safetensors` (147.8M) + `adapter_config.json` **AVAILABLE** |
-| **Job** | [`6a91bf11984507d9db4ea104`](https://huggingface.co/jobs/SZLHOLDINGS/6a91bf11984507d9db4ea104) **COMPLETED** |
-| **Does NOT overwrite** | signed [`SZL-Khipu-1.5B`](https://huggingface.co/SZLHOLDINGS/SZL-Khipu-1.5B) |
-| **Prior job** | [`6a91ba2c`](https://huggingface.co/jobs/SZLHOLDINGS/6a91ba2c45686a1580c12020) **ERROR** Trackio 404 |
-| **Card publication** | Exact-source README + local SVG + source binding only; weights, adapter, configs, evals, visibility, hardware, and runtime unchanged |
-| **Lab** | Forbidden. Pin stays Khipu GGUF. GPU **UNAVAILABLE**. |
-| **License** | Apache-2.0 |
-| **Autonomy** | false |
-
-## Evaluation (MEASURED this job)
-
-Method: in-process Unsloth generate, scoring ported from `eval_khipu.py`, temperature 0, held-out never in gradients. Host job worker. Date 2026-08-28 17:20 UTC. File: `eval_measured.json`.
-
-| split | k/n | what-NOT |
+| Form | Files | Scope |
 |---|---|---|
-| plan-valid | **11 / 11** | not a public leaderboard |
-| grounding (`eval.jsonl` navigate) | **5 / 5** | n=5 |
-| abstain (`adversarial.jsonl`) | **3 / 6** | not 5/5, not 6/6 |
-| hallucinated citations | **0** | this job only |
+| QLoRA adapter | `adapter_model.safetensors`, `adapter_config.json` | The PEFT example below explicitly selects this adapter form. |
+| Separate fp32 merged checkpoint | Root `model.safetensors`, `config.json`, `merge_receipt.json` | A distinct runtime form; selecting the adapter does not load this merged checkpoint. |
 
-Prior published original `SZL-Khipu-1.5B` MEASURED abstain was **2/6**. This run is **3/6**. Small n. Do not derive a world-rank score from k/n on n=11.
+Current artifact bytes and their equality to historical evaluated bytes
+were not independently rehashed. The merge receipt's base revision is
+`main@merge-time`, which is not an immutable base identity.
 
-## Training (MEASURED / REPORTED)
+## Dated evaluation records
 
-- Unsloth QLoRA, seed 11, lr 2e-4, LoRA r=32 α=64, 45 epochs
-- Train: 15 navigate + 8 abstain rows × oversample 4 (in-memory 32)
-- Held-out: 5 + 6, `held_out_in_gradients: false`
-- `training_loss` MEASURED `0.017188…` is a train metric, not an eval
-- adapter sha256 `e44d53f29f2d443598e06d6c0441557fd3a5010888c7aa97b56ec3c0e050d349`
+The [2026-08-28 owner-run job record](https://huggingface.co/SZLHOLDINGS/KHIPU-R2/blob/9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52/eval_measured.json)
+reports in-process Unsloth generation at temperature 0 with scoring ported
+from `eval_khipu.py`. It reports `held_out_in_gradients: false`.
 
-## What this is NOT
+| Metric | Historical result | Limit |
+|---|---|---|
+| plan-valid | **11 / 11** | Small owner-run synthetic protocol |
+| grounding (`eval.jsonl` navigate) | **5 / 5** | Five navigation cases |
+| abstain (`adversarial.jsonl`) | **3 / 6** | Visible release blocker; not a pass |
+| hallucinated citations | **0** | These cases only |
+
+The [2026-09-13 corrected-harness CPU re-verification](https://huggingface.co/SZLHOLDINGS/KHIPU-R2/blob/9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52/eval_verified_2026-09-13.json)
+reports **11/11 plan-valid, 5/5 grounding, and 3/6 abstention** on rebuilt
+fp16 merges and the published fp32 merge. The owner fixed a decoding
+harness that returned prompt characters instead of generated output;
+**all prior fp16 scores produced by that buggy harness are void**.
+The corrected runs are separate owner records and do not promote the model.
+
+No signed R2 eval receipt in this atelier. The linked owner-run records
+are not an independent evaluation or public leaderboard. GPU **UNAVAILABLE**
+describes the CPU-only re-verification record and the earlier card state;
+no current hardware availability was tested. Publication and autonomy
+eligibility remain **false**.
+
+The original Khipu **2/6** abstention record and R2's **3/6** record remain
+separate. No broad quality score or general safety guarantee follows.
+
+## Historical training
+
+The prior card and [training receipt](https://huggingface.co/SZLHOLDINGS/KHIPU-R2/blob/9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52/training_receipt.json)
+describe QLoRA r=32, α=64, seed 11, learning rate 2e-4 and 45 epochs,
+on 15 navigation rows plus 8 abstention rows oversampled four times.
+The reported train loss **0.017188…** is a training metric, not evaluation.
+The historical adapter digest is
+`e44d53f29f2d443598e06d6c0441557fd3a5010888c7aa97b56ec3c0e050d349`;
+it was not recomputed here. The earlier card records successful job
+`6a91bf11984507d9db4ea104` and prior error `6a91ba2c45686a1580c12020`
+(Trackio 404). This review did not query those jobs or rerun training.
+
+## Adapter usage
+
+This example is **untested in this review**. An owner-verified immutable
+base revision is required; none is invented here. The blank base revision
+fails before imports or remote loading. The adapter repository is pinned
+to the reviewed documentation and metadata snapshot; this is not an
+evaluation binding or release approval.
 
-- Not a replacement for `SZL-Khipu-1.5B`
-- Not Chaski (Qwen3.5 lock)
-- Not an autonomous agent
-- Not a GGUF. Mini GGUFs exist on [`A11OY-MINI`](https://huggingface.co/SZLHOLDINGS/A11OY-MINI); Mini evals none-this-run; Mini does **not** inherit this 3/6
+```python
+import re
 
-## Load
+BASE_REVISION = ""  # Supply an owner-verified immutable base commit.
+if not re.fullmatch(r"[0-9a-f]{40}", BASE_REVISION):
+    raise ValueError("An owner-verified immutable base revision is required")
 
-```python
 from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 base_id = "Qwen/Qwen2.5-1.5B-Instruct"
-tok = AutoTokenizer.from_pretrained(base_id)
-base = AutoModelForCausalLM.from_pretrained(base_id)
-model = PeftModel.from_pretrained(base, "SZLHOLDINGS/KHIPU-R2")
+adapter_id = "SZLHOLDINGS/KHIPU-R2"
+adapter_revision = "9fc2f7bebeaf4b3d6d26f7a2a1788a27f8c9ed52"
+tok = AutoTokenizer.from_pretrained(base_id, revision=BASE_REVISION)
+base = AutoModelForCausalLM.from_pretrained(base_id, revision=BASE_REVISION)
+model = PeftModel.from_pretrained(base, adapter_id, revision=adapter_revision)
 ```
 
-Owner: Stephen Lutar / SZL Holdings.
+Outputs are proposals requiring external validation and approval. Lab load
+remains forbidden. [A11OY-MINI](https://huggingface.co/SZLHOLDINGS/A11OY-MINI)
+contains separately scoped legacy and R2 evidence and inherits no KHIPU-R2
+score or qualification.
+
+Apache-2.0 is declared in metadata. No standalone `LICENSE` is listed at
+the reviewed revision; artifact license coverage was not independently
+verified. A license addition requires source-owner review of that coverage.
+
+Canonical card authoring source: [khipu-r2/card/README.md](https://github.com/szl-holdings/szl-forge/blob/6f4ac90ff503265cec9c0436587f086e52d6124e/khipu-r2/card/README.md).
+Doctrine v11 LOCKED 749/14/163. Λ = Conjecture 1, advisory, never a theorem.

szl-source-binding.json

@@ -18,8 +18,8 @@
   "source": {
     "assets": {
       "README.md": {
-        "bytes": 6292,
-        "sha256": "cbd25e918a0e955a49440fcdddddb0ccbe94eb996ccfd2eb97a1815d3930a85e"
+        "bytes": 6157,
+        "sha256": "2d65c2346bfefbad4dd843c334624935ee3fd5fbd28844fa09e8dbf9c7a4da50"
       },
       "holo-banner.svg": {
         "bytes": 1516,
@@ -27,7 +27,7 @@
       }
     },
     "repository": "szl-holdings/szl-forge",
-    "revision": "a2480040b37e0ee2cc036eda175ccd096aefb93f"
+    "revision": "72544fd0be1c8a312660c57d8460648c87df2d47"
   },
   "target": {
     "controlled_paths": [