codebook-lab 1.1.0__tar.gz → 1.1.1__tar.gz

{codebook_lab-1.1.0 → codebook_lab-1.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codebook-lab
-Version: 1.1.0
+Version: 1.1.1
 Summary: An LLM annotation experiment pipeline for computational social science.
 Author: Lorcan McLaren
 License-Expression: AGPL-3.0-only
@@ -45,7 +45,7 @@ Dynamic: license-file
 
 # CodeBook Lab
 
-[![DOI](https://zenodo.org/badge/1186234207.svg)](https://doi.org/10.5281/zenodo.19185921)
+[![DOI](https://zenodo.org/badge/1186234207.svg)](https://doi.org/10.5281/zenodo.19185921) [![PyPI](https://img.shields.io/pypi/v/codebook-lab)](https://pypi.org/project/codebook-lab/) [![Python](https://img.shields.io/pypi/pyversions/codebook-lab)](https://pypi.org/project/codebook-lab/) [![License](https://img.shields.io/pypi/l/codebook-lab)](https://pypi.org/project/codebook-lab/)
 
 CodeBook Lab is an LLM annotation experiment pipeline for computational social science. It takes a codebook and labelled dataset from [CodeBook Studio](https://codebook.streamlit.app/) ([source](https://github.com/LorcanMcLaren/codebook-studio)) and runs structured experiments across the dimensions that matter for text-as-data research: model choice, model size, prompt style, zero-shot versus few-shot learning, and sampling hyperparameters — all benchmarked against human labels.
 
@@ -297,7 +297,7 @@ This project is licensed under the [GNU Affero General Public License v3.0](http
 If you use CodeBook Lab in research, please cite both:
 
 - this software package
-- the associated preprint
+- the associated arXiv preprint
 
 Citation metadata is also available in the project's [`CITATION.cff`](https://github.com/LorcanMcLaren/codebook-lab/blob/main/CITATION.cff).
 
@@ -324,7 +324,7 @@ BibTeX:
 
 APSR style:
 
-McLaren, Lorcan, James P. Cross, Zuzanna Krakowska, Robin Rauner, and Martijn Schoonvelde. 2026. *Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation*. Preprint.
+McLaren, Lorcan, James P. Cross, Zuzanna Krakowska, Robin Rauner, and Martijn Schoonvelde. 2026. *Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation*. arXiv preprint arXiv:2603.26898. [https://arxiv.org/abs/2603.26898](https://arxiv.org/abs/2603.26898).
 
 BibTeX:
 
@@ -333,6 +333,10 @@ BibTeX:
   author = {McLaren, Lorcan and Cross, James P. and Krakowska, Zuzanna and Rauner, Robin and Schoonvelde, Martijn},
   title = {Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation},
   year = {2026},
-  note = {Preprint}
+  eprint = {2603.26898},
+  archivePrefix = {arXiv},
+  primaryClass = {cs.CL},
+  doi = {10.48550/arXiv.2603.26898},
+  url = {https://arxiv.org/abs/2603.26898}
 }
 ```

{codebook_lab-1.1.0 → codebook_lab-1.1.1}/README.md

@@ -1,6 +1,6 @@
 # CodeBook Lab
 
-[![DOI](https://zenodo.org/badge/1186234207.svg)](https://doi.org/10.5281/zenodo.19185921)
+[![DOI](https://zenodo.org/badge/1186234207.svg)](https://doi.org/10.5281/zenodo.19185921) [![PyPI](https://img.shields.io/pypi/v/codebook-lab)](https://pypi.org/project/codebook-lab/) [![Python](https://img.shields.io/pypi/pyversions/codebook-lab)](https://pypi.org/project/codebook-lab/) [![License](https://img.shields.io/pypi/l/codebook-lab)](https://pypi.org/project/codebook-lab/)
 
 CodeBook Lab is an LLM annotation experiment pipeline for computational social science. It takes a codebook and labelled dataset from [CodeBook Studio](https://codebook.streamlit.app/) ([source](https://github.com/LorcanMcLaren/codebook-studio)) and runs structured experiments across the dimensions that matter for text-as-data research: model choice, model size, prompt style, zero-shot versus few-shot learning, and sampling hyperparameters — all benchmarked against human labels.
 
@@ -252,7 +252,7 @@ This project is licensed under the [GNU Affero General Public License v3.0](http
 If you use CodeBook Lab in research, please cite both:
 
 - this software package
-- the associated preprint
+- the associated arXiv preprint
 
 Citation metadata is also available in the project's [`CITATION.cff`](https://github.com/LorcanMcLaren/codebook-lab/blob/main/CITATION.cff).
 
@@ -279,7 +279,7 @@ BibTeX:
 
 APSR style:
 
-McLaren, Lorcan, James P. Cross, Zuzanna Krakowska, Robin Rauner, and Martijn Schoonvelde. 2026. *Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation*. Preprint.
+McLaren, Lorcan, James P. Cross, Zuzanna Krakowska, Robin Rauner, and Martijn Schoonvelde. 2026. *Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation*. arXiv preprint arXiv:2603.26898. [https://arxiv.org/abs/2603.26898](https://arxiv.org/abs/2603.26898).
 
 BibTeX:
 
@@ -288,6 +288,10 @@ BibTeX:
   author = {McLaren, Lorcan and Cross, James P. and Krakowska, Zuzanna and Rauner, Robin and Schoonvelde, Martijn},
   title = {Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation},
   year = {2026},
-  note = {Preprint}
+  eprint = {2603.26898},
+  archivePrefix = {arXiv},
+  primaryClass = {cs.CL},
+  doi = {10.48550/arXiv.2603.26898},
+  url = {https://arxiv.org/abs/2603.26898}
 }
 ```

{codebook_lab-1.1.0 → codebook_lab-1.1.1}/codebook_lab/annotate.py

@@ -205,7 +205,9 @@ def generate_response(chain, prompt, char_counts, timing_data, row_num=None, ann
 
         structured_chain = (
             _PROMPT_TEMPLATE
-            | chain.with_structured_output(AnnotationResponse, include_raw=True)
+            | chain.with_structured_output(
+                AnnotationResponse, method="json_schema", include_raw=True
+            )
         )
 
         start_time = time.time()

{codebook_lab-1.1.0 → codebook_lab-1.1.1}/codebook_lab.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codebook-lab
-Version: 1.1.0
+Version: 1.1.1
 Summary: An LLM annotation experiment pipeline for computational social science.
 Author: Lorcan McLaren
 License-Expression: AGPL-3.0-only
@@ -45,7 +45,7 @@ Dynamic: license-file
 
 # CodeBook Lab
 
-[![DOI](https://zenodo.org/badge/1186234207.svg)](https://doi.org/10.5281/zenodo.19185921)
+[![DOI](https://zenodo.org/badge/1186234207.svg)](https://doi.org/10.5281/zenodo.19185921) [![PyPI](https://img.shields.io/pypi/v/codebook-lab)](https://pypi.org/project/codebook-lab/) [![Python](https://img.shields.io/pypi/pyversions/codebook-lab)](https://pypi.org/project/codebook-lab/) [![License](https://img.shields.io/pypi/l/codebook-lab)](https://pypi.org/project/codebook-lab/)
 
 CodeBook Lab is an LLM annotation experiment pipeline for computational social science. It takes a codebook and labelled dataset from [CodeBook Studio](https://codebook.streamlit.app/) ([source](https://github.com/LorcanMcLaren/codebook-studio)) and runs structured experiments across the dimensions that matter for text-as-data research: model choice, model size, prompt style, zero-shot versus few-shot learning, and sampling hyperparameters — all benchmarked against human labels.
 
@@ -297,7 +297,7 @@ This project is licensed under the [GNU Affero General Public License v3.0](http
 If you use CodeBook Lab in research, please cite both:
 
 - this software package
-- the associated preprint
+- the associated arXiv preprint
 
 Citation metadata is also available in the project's [`CITATION.cff`](https://github.com/LorcanMcLaren/codebook-lab/blob/main/CITATION.cff).
 
@@ -324,7 +324,7 @@ BibTeX:
 
 APSR style:
 
-McLaren, Lorcan, James P. Cross, Zuzanna Krakowska, Robin Rauner, and Martijn Schoonvelde. 2026. *Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation*. Preprint.
+McLaren, Lorcan, James P. Cross, Zuzanna Krakowska, Robin Rauner, and Martijn Schoonvelde. 2026. *Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation*. arXiv preprint arXiv:2603.26898. [https://arxiv.org/abs/2603.26898](https://arxiv.org/abs/2603.26898).
 
 BibTeX:
 
@@ -333,6 +333,10 @@ BibTeX:
   author = {McLaren, Lorcan and Cross, James P. and Krakowska, Zuzanna and Rauner, Robin and Schoonvelde, Martijn},
   title = {Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation},
   year = {2026},
-  note = {Preprint}
+  eprint = {2603.26898},
+  archivePrefix = {arXiv},
+  primaryClass = {cs.CL},
+  doi = {10.48550/arXiv.2603.26898},
+  url = {https://arxiv.org/abs/2603.26898}
 }
 ```

{codebook_lab-1.1.0 → codebook_lab-1.1.1}/codebook_lab.egg-info/SOURCES.txt

@@ -19,10 +19,6 @@ codebook_lab.egg-info/top_level.txt
 codebook_lab/tasks/__init__.py
 codebook_lab/tasks/policy-sentiment/codebook.json
 codebook_lab/tasks/policy-sentiment/ground-truth.csv
-scripts/multi_run_example.py
-scripts/single_run_example.py
-tests/__init__.py
-tests/conftest.py
 tests/test_conditions.py
 tests/test_examples.py
 tests/test_experiments.py

{codebook_lab-1.1.0 → codebook_lab-1.1.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "codebook-lab"
-version = "1.1.0"
+version = "1.1.1"
 description = "An LLM annotation experiment pipeline for computational social science."
 readme = "README.md"
 requires-python = ">=3.10"

codebook_lab-1.1.0/scripts/multi_run_example.py

@@ -1,41 +0,0 @@
-"""Run a small multi-experiment sweep with CodeBook Lab.
-
-This script is intentionally small so users can test the package quickly.
-Edit the grid below to explore more combinations once the basic workflow is
-working in your environment. The package will try to start a local Ollama
-server if needed and will pull any missing models automatically.
-"""
-
-from pathlib import Path
-
-from codebook_lab import run_experiment_grid
-
-
-OUTPUT_ROOT = Path("outputs")
-
-PARAM_GRID = {
-    "country_iso_code": "IRL",
-    "tasks": ["policy-sentiment"],
-    "models": ["gemma3:270m"],
-    "use_examples": [False, True],
-    "prompt_types": ["standard"],
-    "temperatures": [None],
-    "top_ps": [None],
-    "process_textboxes": [True],
-}
-
-
-def main() -> None:
-    """Run a small sweep and print a short summary of the completed runs."""
-    results = run_experiment_grid(
-        param_grid=PARAM_GRID,
-        output_root=OUTPUT_ROOT,
-    )
-
-    print(f"Completed {len(results)} experiment runs.")
-    for result in results:
-        print(f"- {result.model_id}: {result.experiment_directory}")
-
-
-if __name__ == "__main__":
-    main()

codebook_lab-1.1.0/scripts/single_run_example.py

@@ -1,48 +0,0 @@
-"""Run one bundled-example experiment with CodeBook Lab.
-
-Edit the constants below if you want to change the model, task, or output
-location. This script assumes:
-
-1. CodeBook Lab has been installed in the current environment, for example
-   with ``python -m pip install codebook-lab``.
-2. Ollama is installed and available on PATH.
-
-The package will try to start a local Ollama server if needed and will pull the
-requested model automatically before running the experiment.
-"""
-
-from pathlib import Path
-
-from codebook_lab import ExperimentSpec, run_experiment
-
-
-TASK = "policy-sentiment"
-MODEL = "gemma3:270m"
-COUNTRY_ISO_CODE = "IRL"
-OUTPUT_ROOT = Path("outputs")
-
-
-def main() -> None:
-    """Run a single experiment and print the key output locations."""
-    result = run_experiment(
-        ExperimentSpec(
-            task=TASK,
-            model=MODEL,
-            use_examples=False,
-            prompt_type="standard",
-            temperature=None,
-            top_p=None,
-            process_textbox=True,
-            country_iso_code=COUNTRY_ISO_CODE,
-        ),
-        output_root=OUTPUT_ROOT,
-    )
-
-    print("Completed single experiment run.")
-    print(f"Experiment directory: {result.experiment_directory}")
-    print(f"Metrics CSV: {result.metrics.output_csv}")
-    print(f"Classification report: {result.metrics.report_file}")
-
-
-if __name__ == "__main__":
-    main()

codebook_lab-1.1.0/tests/conftest.py

@@ -1,13 +0,0 @@
-from __future__ import annotations
-
-from pathlib import Path
-
-import pytest
-
-
-@pytest.fixture()
-def bundled_task_dir() -> Path:
-    """Return the path to the bundled policy-sentiment example task."""
-    task_dir = Path(__file__).resolve().parent.parent / "codebook_lab" / "tasks" / "policy-sentiment"
-    assert task_dir.exists(), f"Bundled task directory not found: {task_dir}"
-    return task_dir