Publish frozen OpenJeff pilot adapter and reproducibility card

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

NOTICE

@@ -0,0 +1,18 @@
+OpenJeff
+Copyright 2026 OpenJeff contributors
+
+Original OpenJeff code is licensed under Apache License 2.0.
+
+research/snapshots contains separately attributed, unmodified research reference
+material. JevBench material retains its MIT license and third-party notices;
+djev reference material retains its Apache-2.0 license and NOTICE. Model cards,
+configuration metadata and foundation weights retain their upstream terms.
+research/vendor/djev contains the pinned Apache-2.0 Djev implementation with its
+LICENSE and NOTICE. OpenJeff LoRA weights and original synthetic adaptation data
+are provided under Apache-2.0; the Gemma base retains its upstream license.
+The source manifest records exact URLs and SHA-256 hashes. No foundation model
+weights are included in this repository.
+
+OpenJeff is independent of TypeSafe AI, Google, NVIDIA, Ai2, and the owners of
+22 Jump Street. References identify sources and inspiration, not endorsement.
+

README.md

@@ -0,0 +1,168 @@
+---
+license: apache-2.0
+base_model: google/gemma-4-12B-it
+base_model_relation: adapter
+library_name: peft
+language:
+- en
+tags:
+- lora
+- peft
+- gemma4
+- structured-decisions
+- research
+---
+
+# OpenJeff — small answers, serious judgment
+
+An experimental LoRA adapter for evidence-conditioned, finite-choice decisions.
+This repository contains **adapter weights, not the foundation model**. Download
+the pinned Gemma foundation separately under its upstream terms. The included
+Apache-2.0 license covers OpenJeff's original artifacts.
+
+[Code and reproducible runs](https://github.com/greyaperez/openjeff) ·
+[Optional support](https://github.com/sponsors/greyaperez) ·
+[Evaluator handoff](https://github.com/greyaperez/openjeff/blob/main/docs/jevbench-submission.md)
+
+## Download
+
+```python
+from huggingface_hub import snapshot_download
+path = snapshot_download("greyecho/openjeff-pilot-v1")
+```
+
+For reproducible use, pin the Hub commit returned with this release. The files
+`adapter_config.json` and `adapter_model.safetensors` are standard PEFT artifacts.
+The original adapter config is unchanged so the frozen digest remains valid.
+
+## Run the decision model
+
+Use the [tested runtime and launch instructions](https://github.com/greyaperez/openjeff/blob/main/docs/using-openjeff.md).
+The GitHub release includes the same adapter plus the complete run directory
+required by `PilotScorer`. Generic text generation is not the evaluated task:
+OpenJeff compiles candidate labels to single-token codes and normalizes their
+logits with the frozen temperature. The calibrator is bound to the A100 runtime;
+loading weights on another device does not validate those probabilities.
+
+```bash
+git clone https://github.com/greyaperez/openjeff.git
+cd openjeff
+# In the documented PyTorch CUDA container on an A100 SXM 80 GB:
+python -m venv --system-site-packages .venv
+.venv/bin/python -m pip install -r configs/train-gpu-requirements.txt
+.venv/bin/python -m scripts.stage_weights
+.venv/bin/python -m openjeff.serve --run runs/pilot-v1 --port 8765
+```
+
+## Initial evidence
+
+On the same 231 public JevBench IDs, the initial OpenJeff pilot scored **90.04%**
+versus **86.58%** from Jev 1.13.0's published outcomes. Hard-subset accuracy was
+**80.18% vs. 72.97%**. Jev was not rerun here; prompts and runtimes differ.
+This is not an official leaderboard rank or a full benchmark comparison.
+The diffusion follow-up remains experimental; this release is AR-only.
+
+## Detailed model card
+
+OpenJeff is an experimental adapter for finite-choice, evidence-conditioned
+judgments. It returns candidate probabilities and supports explicit abstention.
+The trained adapter, original code, and original synthetic adaptation data are
+Apache-2.0. Foundation weights and third-party material retain their licenses
+and notices; see `NOTICE` and the pinned source snapshots.
+
+## Model and intended use
+
+- Foundation: `google/gemma-4-12B-it`, revision
+  `707f0a3b8a3c7ad586ed01e27eafbad8a27dd0f7`.
+- BF16 foundation; float32 LoRA parameters. No quantization.
+- Adapter: 21,331,968 trainable parameters; rank 16, alpha 32, dropout 0.05;
+  text attention q/k/v/o projections. Config-and-weight SHA-256:
+  `a1811874542eb3b9ca4235d79826dfabb847f0c5ad076bfd25b5e4b2f426ba2b`.
+- Intended use: reproducible research into structured decisions, policy-rule
+  interpretation, and probability readout. It does not perform actions itself.
+- Serving: local serial HTTP prototype, 2–26 candidates and 1,536 input tokens.
+  Confidence threshold 0.9 is an abstention policy, not an accuracy guarantee.
+
+Google's developer/base-weight lineage is accepted for this project. Neither
+Google's U.S. location nor this adaptation establishes U.S.-only pretraining data.
+Full foundation pretraining is not reproduced.
+
+## Training and selection
+
+8,000 original synthetic examples from 20 rule-grounded families, generated by
+`openjeff/curriculum.py`. Labels come from executable reference logic; no external
+teacher, private record, Jev API, or JevBench task supplies training examples.
+One epoch: 500 AdamW optimizer steps, microbatch 4, accumulation 4, learning rate
+1e-4 with warmup/cosine decay, candidate-only cross entropy, seed in the run recipe.
+
+Development (400 rows) alone selected step 500 and then the adapter over the base.
+Selection froze at 2026-09-23T04:34:38Z before calibration and final scoring.
+Separate partitions: calibration-fit 600, calibration-check 400, final 600,
+adversarial 200, and production-simulation 200. Exact request/group hashes include unique case IDs. Removing decorative IDs
+reveals 197/600 final states matching training states. On the remaining 403,
+OpenJeff scores 96.28% versus 75.93% for the base. Calibration-fit states also
+recur in evaluation. See `reports/curriculum-overlap.json`. Templates and logical
+patterns are shared; this is
+not a natural-language domain holdout or semantic deduplication guarantee.
+
+## Evaluation and calibration
+
+| Measure | Base | OpenJeff |
+|---|---:|---:|
+| Synthetic final accuracy (600) | 79.67% | 97.50% |
+| Synthetic final calibrated ECE (15 bins) | 0.0554 | 0.0137 |
+| Candidate-order disagreement on final scenarios | 22.00% | 1.83% |
+| Public JevBench accuracy (231) | 70.13% | 90.04% |
+| Public JevBench hard accuracy (111) | 42.34% | 80.18% |
+| Public hard ECE (10 bins) | 0.2756 | 0.1417 |
+
+Synthetic final accuracy gain is 17.83 percentage points, paired row-bootstrap
+95% interval [14.67, 20.83]. This interval concerns the sampled synthetic generator
+distribution. Related candidate reversals are excluded from the independent-row
+bootstrap. The rule-grounded tasks are also solvable with deterministic programs;
+the result validates adaptation, not a need to replace those programs with an LLM.
+
+Each frozen backend has its own positive temperature fitted on the 600-example
+fit set: base 2.7638, adapter 1.0207. Calibration artifacts bind scorer settings,
+weights, prompt, package versions, and GPU model. Changing that environment requires
+new calibration rather than reusing an unsupported probability claim.
+
+JevBench uses only the 231 public tasks, the pinned upstream scoring function,
+and unchanged temperatures; no checkpoint was altered afterward. Only state,
+question, and options enter prompts. Gold answers, rationales, author metadata,
+and gold probabilities are excluded. The diagnostic raises the context guard to
+8,192 tokens; longest prompt 4,071. It is not the official 534-item ranking.
+See [complete results](https://github.com/greyaperez/openjeff/blob/main/reports/RESULTS.md) for slices and publisher comparisons.
+
+## Runtime and reproducibility
+
+Tested on NVIDIA A100 SXM 80 GB, Linux/Python 3.12.3, PyTorch 2.8.0+cu128,
+Transformers 5.17.0, PEFT 0.21.0, and SDPA. Training/evaluation script elapsed
+28.65 minutes with 44.57 GiB peak allocated memory. Public-benchmark local serial
+adapter scoring: median 72.3 ms, p95 553.3 ms. These exclude cold load, network,
+queues, and concurrency; they establish no deployment SLA.
+
+The saved adapter passed offline reload and HTTP probability parity checks.
+Release validation recomputed 2,800 held-out score rows and both temperature fits.
+Weight/tokenizer hashes, recipe, raw scores, selection, calibration, and runtime
+are under `runs/pilot-v1/`. Source and data manifests accompany the release.
+The container tag was recorded but its OCI digest was not; bitwise retraining
+reproducibility is not claimed. [Usage guide](https://github.com/greyaperez/openjeff/blob/main/docs/using-openjeff.md).
+
+## Limitations
+
+This pilot does not establish fairness, robustness to natural-language policy
+ambiguity or prompt injection, employment suitability, medical/legal reliability,
+privacy compliance, or production throughput. A narrow synthetic curriculum and
+public benchmark can understate distribution shift. Candidate-order sensitivity
+was reduced, not eliminated. Hard-task probability calibration remains imperfect.
+Foundation pretraining may contain public benchmark material; its contamination
+status is unknown even though OpenJeff adaptation excludes benchmark examples.
+
+No full Jev API comparison, learned hybrid bridge, scalar continuous-output head,
+production authentication, or validated enterprise deployment is included.
+At the time of the original pilot archive, the optional diffusion control had
+failed during startup before model evaluation. A subsequent
+[completed diffusion study](https://github.com/greyaperez/openjeff/blob/main/reports/HYBRID-RESULTS.md) tested structured guidance
+and controls without changing this adapter. It found mixed gains and leaves AR
+as the default. Its H200 calibrators do not replace this pilot's A100 calibrators.

SHA256SUMS.json

@@ -0,0 +1,10 @@
+{
+  "NOTICE": "458290bbbf9d086de13ca888543cb332c13af88815be57b9bbbcbf02dbb00c4b",
+  "adapter_model.safetensors": "16069594ba62c231aa98fdbf99fbcadbcf20e8b4e087786e0f817401d56a1a85",
+  "freeze.json": "22db492b397ca8a187890cdc20d70b04141641134ab688adbf8ecbc7cb003779",
+  "LICENSE": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
+  "adapter_config.json": "719fc3ef108d34e08619ac4fa77115f0c3d2461e92c1b270bad9676a73f4e6bb",
+  "release.json": "82e62e7aeb6bd3912698eee6c1c506178547674dcf39863f5fd718843b782d24",
+  "adapter-calibration.json": "34b87c561312b1116175b8bbcd8692136890f7e7a3a68cd5fa6ea47412c44bdf",
+  "README.md": "abd8c0437bf4380cf046aebc6923c5fa2b0122207ba895ab9d3f3c54dadc3be2"
+}

adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma4UnifiedForConditionalGeneration",
+    "parent_library": "transformers.models.gemma4_unified.modeling_gemma4_unified"
+  },
+  "base_model_name_or_path": "google/gemma-4-12B-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "707f0a3b8a3c7ad586ed01e27eafbad8a27dd0f7",
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16069594ba62c231aa98fdbf99fbcadbcf20e8b4e087786e0f817401d56a1a85
+size 85382928

freeze.json

@@ -0,0 +1,8 @@
+{
+  "adapter_sha256": "a1811874542eb3b9ca4235d79826dfabb847f0c5ad076bfd25b5e4b2f426ba2b",
+  "best_step": 500,
+  "release_choice": "adapter",
+  "rule": "development accuracy then NLL against base",
+  "final_unopened": true,
+  "frozen_utc": "2026-09-23T04:34:38Z"
+}

release.json

@@ -0,0 +1,11 @@
+{
+  "model": "google/gemma-4-12B-it",
+  "revision": "707f0a3b8a3c7ad586ed01e27eafbad8a27dd0f7",
+  "selected_backend": "adapter",
+  "evaluation_adapter_sha256": "a1811874542eb3b9ca4235d79826dfabb847f0c5ad076bfd25b5e4b2f426ba2b",
+  "package_adapter_sha256": "a1811874542eb3b9ca4235d79826dfabb847f0c5ad076bfd25b5e4b2f426ba2b",
+  "adapter_weights_sha256": "16069594ba62c231aa98fdbf99fbcadbcf20e8b4e087786e0f817401d56a1a85",
+  "scope": "experimental synthetic structured decisions",
+  "cloud_terminated": true,
+  "cleanup_evidence": "A100 stop succeeded, console showed 0 USD/hour, then pod was terminated. See reports/spending.json."
+}