asta-theorizer 0.1.0__tar.gz

asta_theorizer-0.1.0/.gitignore

@@ -0,0 +1,178 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Don't add the /prompts/ directory (which is a debug directory)
+prompts/
+
+# Large files that are preprocessed versions of conceptnet that shouldn't be committed
+
+# Don't commit anything with `donotcommit` in its name
+*donotcommit*
+
+# Don't commit the exclusion patterns that are automatically scanned for in commits (like API keys)
+EXCLUDE_PATTERNS.TXT
+
+# Runtime data, caches, and debug output
+data/
+ocr-cache/
+output/
+
+# OS files
+.DS_Store
+
+# Project data (VIP interneuron corpus + extraction output)
+vip-interneuron-project/
+
+# theorizer library: project directories and verbose logs
+theorizer-run/
+example-*-run/
+theorizer-verbose.log
+paperstore_log.txt
+paperstore_successfail_log.jsonl
+pf-check/
+vip-sweep-run/
+vip-sweep-html/
+sweep-html-export/
+vip-full-sweep/
+vip-full-sweep-html/
+vip-schema2-sweep/
+vip-sol-sweep/
+vip-*-sweep/
+vip-*-html/
+vip-*-html-*/
+vip-cache-test/
+vip-reflect-gauge/
+vip-2run-compare/
+vip-luna-test/
+
+# Theorizer run/project directories (any name), and their stores
+vip-s1-full/
+vip-s1-sol/
+theorystore.json
+store.json

asta_theorizer-0.1.0/CLI.md

@@ -0,0 +1,160 @@
+# Theorizer CLI
+
+## Install and check
+
+```bash
+pip install asta-theorizer
+export OPENAI_API_KEY=...                  # the default models are gpt-5.2 and gpt-5-mini
+export S2_API_KEY=...                      # optional: faster paper fetching
+export MISTRAL_API_KEY=...                 # optional: Mistral OCR for PDFs instead of local conversion
+
+theorize doctor
+theorize -p vip/ init --model gpt-5-mini --extraction-model gpt-5-mini
+theorize --help
+theorize papers --help
+```
+
+## Papers from PaperFinder
+
+```bash
+theorize -p vip/ papers search "VIP interneurons visual cortex gain"
+theorize -p vip/ papers fetch --top 1                    # fetches the full text of the top candidate into the project
+theorize -p vip/ papers fetch 225095372 244348308        # or of these corpus ids
+theorize -p vip/ show papers
+theorize -p vip/ show papers --status metadata-only
+theorize -p vip/ show candidates
+```
+
+## Papers from your own files or a store
+
+```bash
+theorize -p vip/ papers import tests/fixtures/one-paper.md
+theorize -p vip/ papers import my-papers/*.pdf                          # local conversion
+theorize -p vip/ papers import my-papers/*.pdf --ocr mistral            # Mistral OCR
+theorize -p vip/ papers import my-papers/ --no-metadata                 # skip the metadata call
+
+asta-papers search "VIP interneurons visual cortex" --limit 1 | asta-papers store > store.json
+theorize -p vip/ papers import store.json
+theorize -p vip/ show papers
+```
+
+## The whole run in one command
+
+```bash
+theorize -p vip/ run "Build a theory of how VIP interneurons control response gain in mouse V1" --max-papers 1
+theorize -p vip/ export html
+open vip/html/index.html
+```
+
+## Stage by stage
+
+```bash
+theorize -p vip/ plan "Build a theory of how VIP interneurons control response gain in mouse V1"
+theorize -p vip/ show plan
+theorize -p vip/ show plan --full
+theorize -p vip/ extract --max-papers 1
+theorize -p vip/ extract
+theorize -p vip/ show extraction
+theorize -p vip/ theories generate
+theorize -p vip/ show theories
+theorize -p vip/ export html
+```
+
+## Refine the schema from what came out
+
+```bash
+theorize -p vip/ report
+theorize -p vip/ show variable-report
+theorize -p vip/ schemas extend
+theorize -p vip/ schemas extend --max-suggestions 5 --save-as schema-wide
+theorize -p vip/ show schema-extended
+theorize -p vip/ extract --schema schema-extended --save-as extraction-extended
+theorize -p vip/ theories generate --extraction extraction-extended
+```
+
+## Let the papers propose the schema
+
+```bash
+theorize -p vip/ discover
+theorize -p vip/ schemas from-discovery
+theorize -p vip/ show schemas#0
+theorize -p vip/ extract --schema schemas#0 --save-as extraction-discovered
+theorize -p vip/ theories generate --extraction extraction-discovered
+```
+
+## Other theory generators
+
+```bash
+theorize -p vip/ theories generate --objective novelty --save-as theories-novelty
+theorize -p vip/ theories generate --no-reflection --max-laws 2 --model gpt-5.2
+theorize -p vip/ theories generate --suggestions variable-report
+theorize -p vip/ theories sweep --debug-limit 2
+theorize -p vip/ theories sweep --output-types "MECHANISTIC EXPLANATION" --inference-types none
+theorize -p vip/ show theories
+```
+
+## Symbolic laws
+
+```bash
+theorize -p vip/ schemas symbolic
+theorize -p vip/ show symbolic-schema
+theorize -p vip/ extract --schema symbolic-schema --save-as extraction-symbolic
+theorize -p vip/ symbolic table
+theorize -p vip/ symbolic solve
+theorize -p vip/ symbolic solve --skip pysr_symbolic --skip gplearn_symbolic --timeout 60
+theorize -p vip/ symbolic laws
+theorize -p vip/ symbolic report symbolic-report
+theorize -p vip/ symbolic report symbolic-report --out vip/laws.md
+```
+
+## Evaluate the theories
+
+```bash
+theorize -p vip/ evaluate judge
+theorize -p vip/ evaluate judge --only-novel --model gpt-5.2
+theorize -p vip/ evaluate belief --samples 2 --limit 1
+theorize -p vip/ evaluate novelty --limit 1
+theorize -p vip/ show evaluation-novelty
+theorize -p vip/ evaluate predictive --evidence-from 2024-01 --limit 1 --max-papers 1
+theorize -p vip/ export html
+```
+
+## Inspect and pipe
+
+```bash
+theorize -p vip/ show
+theorize -p vip/ show 3
+theorize -p vip/ load plan
+theorize -p vip/ load plan --key output.paper_search_query
+theorize -p vip/ load extraction > extraction.json
+theorize -p vip/ --json show | jq '.data.items[].name'
+theorize -p vip/ --json theories generate --no-reflection | jq '.data.theory_ids'
+theorize -p vip/ -q show theories
+```
+
+## Models and keys
+
+```bash
+theorize -p vip/ init --model gpt-5.2 --extraction-model gpt-5-mini
+THEORIZER_MODEL=gpt-5.2 theorize -p vip/ theories generate
+theorize -p vip/ theories generate --model gpt-5.2
+LITELLM_BASE_URL=https://proxy.example/v1 LITELLM_USER_KEY=... theorize -p vip/ doctor
+THEORIZER_PAPERFINDER_URL=http://localhost:8000 theorize -p vip/ papers search "VIP interneurons"
+```
+
+## Resume and retry
+
+```bash
+theorize -p vip/ extract                       # reruns pick up where the last one stopped
+theorize -p vip/ papers fetch 225095372        # a failed paper is fetched again
+theorize -p vip/ theories sweep --debug-limit 2 --debug-seed 1
+```
+
+## Exit codes
+
+```
+0  done
+1  a stage ran and failed (no theories, nothing extracted, solver error)
+2  usage (missing input, unknown reference, no papers)
+3  preflight (another command holds the project, doctor found a problem)
+```