bayanat-labelbench 0.1.0__py3-none-any.whl

bayanat_labelbench-0.1.0.dist-info/METADATA

@@ -0,0 +1,266 @@
+Metadata-Version: 2.4
+Name: bayanat-labelbench
+Version: 0.1.0
+Summary: LabelBench by Bayanat Labs, a reproducible audit of automated Arabic data labeling.
+Author: Bayanat Labs Research
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://www.bayanatlabs.com/research/labelbench
+Project-URL: Repository, https://github.com/Bayanat-Labs/labelbench
+Project-URL: Issues, https://github.com/Bayanat-Labs/labelbench/issues
+Project-URL: Paper, https://www.bayanatlabs.com/research/labelbench-paper-v0.1.pdf
+Keywords: arabic,arabic-nlp,benchmark,data-labeling,annotation-quality,dialect-identification,toxicity-detection,llm-evaluation
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Natural Language :: Arabic
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Dynamic: license-file
+
+# LabelBench by Bayanat Labs
+
+**Arabic annotation is not binary.**
+
+LabelBench is a reproducible audit of automated Arabic data labeling from [Bayanat Labs](https://www.bayanatlabs.com). It measures how much of a labeling queue can be accepted at a declared quality floor, then breaks the answer down by taxonomy, task and Arabic variety.
+
+[Project page](https://www.bayanatlabs.com/research/labelbench) · [Technical report (PDF)](https://www.bayanatlabs.com/research/labelbench-paper-v0.1.pdf) · Code Apache-2.0 · Results CC BY 4.0 · Version 0.1.0
+
+## The v0.1 finding
+
+A local language model (Qwen 2.5 3B) scored 78% on binary Arabic toxicity. On the real seven-label taxonomy, exact-match accuracy fell to 25.3% on the fixed held-out manifest. Across five dialect regions it reached 22.4%, where chance is 20%. We call this the annotation complexity cliff.
+
+| Held-out task | Qwen 2.5 3B zero-shot | Fanar 1 9B zero-shot | Small supervised diagnostic |
+|---|---:|---:|---:|
+| Binary toxicity | 78.0% | 88.0% | 97.0% |
+| Seven-label toxicity (exact set) | 25.3% | 31.3% | 49.0% |
+| Five-region dialect ID | 22.4% | 47.8% | 69.8% |
+
+The toxicity rows use seeded AraTox samples of 100 and 300 items. The dialect row uses a balanced 500-item manifest of DART text from IADD, with 100 items for each region.
+
+The supervised systems are intentionally small character n-gram models. Their purpose is to establish that the held-out signal is learnable, not to claim state of the art. Arabic specialization helps, but the v0.1 generative runs still have 0% Safe Automation Coverage at a 95% quality target under their tied-confidence JSON protocol. That is a routing-diagnostic limitation, not proof that generative models cannot support selective automation when confidence is properly elicited and calibrated.
+
+Every model and baseline, the paired significance tests and per-region recall are in [RESULTS.md](RESULTS.md).
+
+## What is included
+
+- Checksummed ingestion for MASSIVE 1.1, AraTox, and IADD/DART
+- Leakage and conflicting-label audits
+- Binary, multi-label, intent, and dialect-region tasks
+- Character n-gram and one-vs-rest diagnostics
+- Local structured-output inference through Ollama
+- A dated OpenAI Responses API adapter with strict JSON Schema and `store=false`
+- Accuracy, exact-set, F1, calibration, bootstrap intervals, confusion matrices
+- Conservative Safe Automation Coverage using a Wilson lower bound
+- Resumable item-level logs with raw responses, model digests, usage, and hashes
+- A blinded offline RTL review app and three-rater aggregation
+- Paper-ready JSON, CSV, Markdown, and SVG release generation
+- The LaTeX source of the technical report
+
+```text
+BENCHMARK.md              evaluation specification
+RESULTS.md                verified v0.1 findings
+DATA.md                   third-party sources, pinned revisions and licenses
+labelbench/               dependency-free benchmark package and CLI
+labelbench/templates/     blinded review template
+registry/                 data and model provenance gates
+adjudication/             offline human-review protocol
+paper/                    LaTeX source and figure script for the technical report
+tests/                    deterministic unit tests
+results/                  aggregate-only public releases
+```
+
+## Install
+
+LabelBench needs Python 3.10 or newer and has no third-party runtime dependencies.
+
+```bash
+pip install bayanat-labelbench
+labelbench --help
+```
+
+Or install from source:
+
+```bash
+git clone https://github.com/Bayanat-Labs/labelbench.git
+cd labelbench
+pip install -e .
+labelbench --help
+```
+
+From a checkout you can also run `python3 -m labelbench` without installing. Tested on Python 3.10 to 3.13.
+
+## Reproduce the core results
+
+Each command downloads its source from the original location at a pinned revision and checks its SHA-256 before use (see [DATA.md](DATA.md)). Downloads and normalized manifests go to `$LABELBENCH_CACHE_DIR` when it is set, and otherwise to `labelbench/` in your user cache directory (`~/.cache` on Linux, `~/Library/Caches` on macOS, `%LOCALAPPDATA%` on Windows). Every data command also accepts `--cache-dir`.
+
+The v0.1 runs kept downloads inside the checkout. To do the same, run these commands from the repository root:
+
+```bash
+export LABELBENCH_CACHE_DIR=data
+
+python3 -m unittest discover -s tests -v
+
+labelbench pilot-aratox \
+  --test-limit 100 --random-test \
+  --output runs/aratox-binary-sample100
+
+labelbench pilot-aratox-multilabel \
+  --test-limit 300 --random-test --tune-thresholds \
+  --output runs/aratox-multilabel-sample300
+
+labelbench pilot-ollama-aratox-multilabel \
+  --model qwen2.5:3b --test-limit 300 \
+  --output runs/ollama-aratox-multilabel-pilot-300
+
+labelbench pilot-ollama-aratox \
+  --model hf.co/yasserrmd/Fanar-1-9B-Instruct-gguf:Q4_K_M \
+  --test-limit 100 \
+  --output runs/ollama-aratox-random-pilot-100
+
+labelbench pilot-ollama-aratox \
+  --model qwen2.5:3b --test-limit 100 \
+  --output runs/ollama-aratox-random-pilot-100
+
+labelbench pilot-ollama-aratox-multilabel \
+  --model hf.co/yasserrmd/Fanar-1-9B-Instruct-gguf:Q4_K_M --test-limit 300 \
+  --output runs/ollama-aratox-multilabel-pilot-300
+
+labelbench pilot-ollama-iadd \
+  --model hf.co/yasserrmd/Fanar-1-9B-Instruct-gguf:Q4_K_M --per-region 100 \
+  --output runs/ollama-iadd-region-pilot-500
+
+labelbench pilot-iadd-supervised \
+  --train-per-region 100 --test-per-region 100 \
+  --output runs/iadd-supervised-diagnostic
+
+labelbench pilot-ollama-iadd \
+  --model qwen2.5:3b --per-region 100 \
+  --output runs/ollama-iadd-region-pilot-500
+```
+
+`data/` and `runs/` are created locally by these commands. Both are listed in `.gitignore` and are not part of this repository.
+
+The Ollama commands need a local [Ollama](https://ollama.com) server with the model already pulled, for example `ollama pull qwen2.5:3b`.
+
+All inference commands resume safely. A cached prediction is accepted only when its stable ID and gold label match the current manifest.
+
+The exact v0.1 generative results used categorical JSON confidence. For the next confidence-enabled experiment matrix, add `--confidence-mode verbalized` to the Ollama commands. Those runs are intentionally new model IDs rather than exact reproductions of the v0.1 reports.
+
+### Build a public release
+
+Pass the exact reports intended for publication:
+
+```bash
+labelbench build-release \
+  --release-id labelbench-v0.1 \
+  --output runs/release-v0.1 \
+  --reports \
+    runs/aratox-binary-sample100/char_ngram_nb/report.json \
+    runs/ollama-aratox-random-pilot-100/ollama_qwen2.5_3b_zero_shot/report.json \
+    runs/ollama-aratox-random-pilot-100/ollama_hf.co_yasserrmd_Fanar-1-9B-Instruct-gguf_Q4_K_M_zero_shot/report.json \
+    runs/aratox-multilabel-sample300/char_ngram_nb_ovr_tuned/report.json \
+    runs/ollama-aratox-multilabel-pilot-300/ollama_qwen2.5_3b_multilabel_zero_shot/report.json \
+    runs/ollama-aratox-multilabel-pilot-300/ollama_hf.co_yasserrmd_Fanar-1-9B-Instruct-gguf_Q4_K_M_multilabel_zero_shot/report.json \
+    runs/iadd-supervised-diagnostic/char_ngram_nb/report.json \
+    runs/ollama-iadd-region-pilot-500/ollama_qwen2.5_3b_dialect_region_zero_shot/report.json \
+    runs/ollama-iadd-region-pilot-500/ollama_hf.co_yasserrmd_Fanar-1-9B-Instruct-gguf_Q4_K_M_dialect_region_zero_shot/report.json
+```
+
+The published `results/v0.1` also includes the Qwen 2 7B, Llama 3 8B and MASSIVE intent reports, plus eight `compare-runs` outputs passed with `--comparisons`. Write test builds outside `results/` so the published files stay unchanged.
+
+The output includes `summary.json`, `leaderboard.csv`, a human-readable table, a task chart, and a dialect confusion heatmap. No source text is copied into the release.
+
+### Human adjudication
+
+Create a blinded review bundle (the examples path assumes `LABELBENCH_CACHE_DIR=data`, as above):
+
+```bash
+labelbench make-review-bundle \
+  --examples data/normalized/aratox_multilabel_test_sample300_seed42.jsonl \
+  --manifest adjudication/bundles/aratox-review-manifest.json \
+  --bundle adjudication/bundles/aratox-review.html
+```
+
+The review template ships with the package. Pass `--template` to use your own. Reviewers work offline. Model predictions are never shown. The application enforces the exclusive `not` label, stores progress locally, and exports a pseudonymous JSON submission. See [adjudication/README.md](adjudication/README.md).
+
+### Frontier API adapter
+
+The OpenAI adapter follows the current Responses API structured-output shape:
+
+- <https://developers.openai.com/api/docs/guides/structured-outputs>
+- <https://developers.openai.com/api/reference/resources/responses/methods/create>
+
+Copy `.env.example`, export `OPENAI_API_KEY`, and use a dated model snapshot:
+
+```bash
+labelbench pilot-openai-iadd \
+  --model gpt-5.4-mini-2026-03-17 \
+  --per-region 100 \
+  --confidence-mode verbalized \
+  --output runs/openai-iadd-region-pilot-500
+```
+
+Credentials are never read from files or written to run artifacts.
+
+Do not paste API keys into chats, issues, or notebooks. Export them in the shell environment for the single run and rotate any key that was ever shared in plain text.
+
+## Data sources and licenses
+
+- Code: Apache License 2.0. See [LICENSE](LICENSE) and [NOTICE](NOTICE).
+- Results, registry, specification and paper source written by Bayanat Labs: CC BY 4.0. See [LICENSE-data](LICENSE-data).
+- Third-party data is not stored in this repository. The commands download each source from its original location and check its SHA-256. Each source keeps its own license. See [DATA.md](DATA.md).
+- The Bayanat Labs name and logo are not licensed.
+
+MASSIVE and AraTox are pinned CC BY 4.0 sources. IADD/DART text is treated as evaluation-only because the repository does not include an explicit data license, even though the accompanying Data in Brief article is CC BY. Public releases contain aggregate results and cryptographic identifiers only.
+
+Raw data, normalized text, review submissions, and model outputs are ignored by Git. Do not publish those directories without a separate source and privacy review.
+
+## Results and paper
+
+- [results/v0.1/](results/v0.1/) holds `summary.json`, `leaderboard.csv`, eight paired comparison files and two charts. `summary.json` and `leaderboard.csv` match the downloads on the project page byte for byte.
+- [RESULTS.md](RESULTS.md) has the verified v0.1 findings, and [BENCHMARK.md](BENCHMARK.md) the evaluation specification.
+- The technical report is on the [project page](https://www.bayanatlabs.com/research/labelbench) as a [PDF](https://www.bayanatlabs.com/research/labelbench-paper-v0.1.pdf). Its LaTeX source is in [paper/](paper/). `paper/make_figures.py` needs `reportlab`, which LabelBench itself does not use.
+
+## Limitations
+
+- **Small local models.** The v0.1 generative results come from four-bit quantized local models of 3B to 9B parameters, run through Ollama. They do not describe frontier or API models. v0.1 contains no frontier API results and no human adjudication results. The API adapter and review bundles are ready for the next release.
+- **Tied-confidence protocol.** The v0.1 generative runs emit categorical JSON confidence, not calibrated confidence. Their 0% Safe Automation Coverage is a limitation of this harness setup, not evidence that selective automation is impossible.
+- **v0.1 scope.** v0.1 covers four task families on fixed samples of 100 to 2,974 items. The dialect task uses five coarse regions from one source (DART) and cannot establish country-level performance. MASSIVE is localized from English and serves only as an engineering control. AraTox rows carry no per-item dialect labels.
+
+## Cite
+
+If you use LabelBench, please cite the technical report. GitHub's "Cite this repository" button reads [CITATION.cff](CITATION.cff). A Zenodo DOI will be added with the first GitHub release.
+
+```bibtex
+@techreport{bayanat2026labelbench,
+  title       = {Arabic Annotation Is Not Binary: LabelBench, a Reproducible Audit of Automated Data Labeling},
+  author      = {{Bayanat Labs Research}},
+  institution = {Bayanat Labs},
+  year        = {2026},
+  month       = jul,
+  number      = {v0.1},
+  url         = {https://www.bayanatlabs.com/research/labelbench}
+}
+```
+
+## Contributing
+
+Issues and pull requests are welcome. Please read the [contributing guide](https://github.com/Bayanat-Labs/.github/blob/main/CONTRIBUTING.md) and open an issue before larger changes. For questions about the data, email [hello@bayanatlabs.com](mailto:hello@bayanatlabs.com).
+
+---
+
+### About Bayanat Labs
+
+[Bayanat Labs](https://www.bayanatlabs.com) is a Riyadh-based Arabic data company for AI. We work only on data, from sourcing and annotation to alignment and evaluation, across 25+ Arabic varieties, with vetted native speakers, linguists and licensed domain professionals.
+
+[Run a pilot](https://www.bayanatlabs.com/pilot) · [Datasets](https://www.bayanatlabs.com/products) · [LinkedIn](https://www.linkedin.com/company/bayanat-labs/) · [hello@bayanatlabs.com](mailto:hello@bayanatlabs.com)

bayanat_labelbench-0.1.0.dist-info/RECORD

@@ -0,0 +1,24 @@
+bayanat_labelbench-0.1.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+bayanat_labelbench-0.1.0.dist-info/licenses/NOTICE,sha256=Ur9oQihpYB6wNC95jYYvtnZyRcymtN6MM-6KjTsxn-4,689
+labelbench/__init__.py,sha256=jIMs1iC2pCc5Af7rYZ9_BmsQOiUvou31uh2NxdOJRYE,113
+labelbench/__main__.py,sha256=MHKZ_ae3fSLGTLUUMOx15fWdeOnJSHhq-zslRP5F5Lc,79
+labelbench/adjudication.py,sha256=JX7ygVlqqICuWDX5Glodc4g6k_ICu_Y24CmUG-HeJqk,7742
+labelbench/audit.py,sha256=9raKoWGhEBoVPk0id3UvEhvIfAl7tVsou-GGt1LE86c,2912
+labelbench/cli.py,sha256=Zl7VV0NqlOYefuIcdf_RPbb27IiG3uKLT9Xwi8ADEL4,22262
+labelbench/comparisons.py,sha256=fLvGmmrfnPiQikORtZD7r46m45cBUfSo_T0lyfP43oU,3563
+labelbench/datasets.py,sha256=Jx-1Yn3Nw3PZDzpGZPcXXCfOvfhQEyP-pbtNPwubll8,20099
+labelbench/metrics.py,sha256=JOkl90DLqhMI-e1T2P81hiGhvua54vrItUnp8y-wNDQ,7915
+labelbench/models.py,sha256=iBv6Ex6YQkoueG3F7IZe_ZEeU6zqcdBEUHEOzUNqFxM,11093
+labelbench/multilabel_metrics.py,sha256=F0hKqDHkizhqSc5QA6T1cCKL7zbbhO7vnTWtuMiu4lA,3353
+labelbench/multilabel_runner.py,sha256=SiAQH-LfqlCW44js3EID_DEHNYIVrNX3EWycTh0RGyk,5775
+labelbench/ollama.py,sha256=I0_O2hS7-FMZGGQURN7v5RI2YJtVL_Y-lbSQtmct3eI,14987
+labelbench/openai_api.py,sha256=PGd-F5kzy1M3F9QVGdD6CZ2QE2mhd3INUQ7_CYLoaMY,6585
+labelbench/paths.py,sha256=4NmTCtgdo-iEqTwsIPvwaeeBSz5emUiC3QMxggY_56A,1280
+labelbench/reporting.py,sha256=TTdb69jDXekUswU_1Z1z1hvkd8ANp1RYx0zOqqzQZjQ,11243
+labelbench/runner.py,sha256=GuMNoOAb4EaVTVNyWer65abk22bFKy8osPffPww3Xqo,6952
+labelbench/templates/review_template.html,sha256=-rIk-WimkBjRoZqCxLOCaCMAxPM-eBQ1FHFqK0a-8JY,9535
+bayanat_labelbench-0.1.0.dist-info/METADATA,sha256=02EEXSxkUZfxCFy6yIQsPbu_ambOOh2A19wH4SscTNE,14407
+bayanat_labelbench-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+bayanat_labelbench-0.1.0.dist-info/entry_points.txt,sha256=FlN3j7NAN9xW01RyiZvCsw5n0JYJKK9wZBPnZoCJIQY,51
+bayanat_labelbench-0.1.0.dist-info/top_level.txt,sha256=BMM1C0Vy71aeVro-MTWDIVtMk-STEoJzGvUvaDHWWH0,11
+bayanat_labelbench-0.1.0.dist-info/RECORD,,

bayanat_labelbench-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

bayanat_labelbench-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+labelbench = labelbench.cli:main

bayanat_labelbench-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 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.

bayanat_labelbench-0.1.0.dist-info/licenses/NOTICE

@@ -0,0 +1,15 @@
+LabelBench by Bayanat Labs
+Copyright 2026 Bayanat Labs
+
+This product includes software developed by Bayanat Labs (https://www.bayanatlabs.com).
+
+The code in this repository is licensed under the Apache License 2.0 (LICENSE).
+The results, registry, specification and paper files listed in LICENSE-data
+are licensed under the Creative Commons Attribution 4.0 International License.
+
+No third-party dataset is included in this repository. The code downloads each
+source from its original location, and each source keeps its own license.
+See DATA.md.
+
+The Bayanat Labs name, logo and project branding are not licensed under the
+Apache License 2.0 or under any data license in this repository.

bayanat_labelbench-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+labelbench

labelbench/__init__.py

@@ -0,0 +1,3 @@
+"""LabelBench by Bayanat Labs: a reproducible audit of automated Arabic data labeling."""
+
+__version__ = "0.1.0"

labelbench/__main__.py

@@ -0,0 +1,4 @@
+from .cli import main
+
+if __name__ == "__main__":
+    raise SystemExit(main())