scientific-writer 2.1.1__py3-none-any.whl → 2.2.2__py3-none-any.whl

scientific_writer/.claude/skills/citation-management/assets/bibtex_template.bib

@@ -0,0 +1,264 @@
+% BibTeX Template File
+% Examples of properly formatted entries for all common types
+
+% =============================================================================
+% JOURNAL ARTICLES
+% =============================================================================
+
+@article{Jumper2021,
+  author  = {Jumper, John and Evans, Richard and Pritzel, Alexander and Green, Tim and Figurnov, Michael and Ronneberger, Olaf and Tunyasuvunakool, Kathryn and Bates, Russ and {\v{Z}}{\'\i}dek, Augustin and Potapenko, Anna and others},
+  title   = {Highly Accurate Protein Structure Prediction with {AlphaFold}},
+  journal = {Nature},
+  year    = {2021},
+  volume  = {596},
+  number  = {7873},
+  pages   = {583--589},
+  doi     = {10.1038/s41586-021-03819-2}
+}
+
+@article{Watson1953,
+  author  = {Watson, James D. and Crick, Francis H. C.},
+  title   = {Molecular Structure of Nucleic Acids: A Structure for Deoxyribose Nucleic Acid},
+  journal = {Nature},
+  year    = {1953},
+  volume  = {171},
+  number  = {4356},
+  pages   = {737--738},
+  doi     = {10.1038/171737a0}
+}
+
+@article{Doudna2014,
+  author  = {Doudna, Jennifer A. and Charpentier, Emmanuelle},
+  title   = {The New Frontier of Genome Engineering with {CRISPR-Cas9}},
+  journal = {Science},
+  year    = {2014},
+  volume  = {346},
+  number  = {6213},
+  pages   = {1258096},
+  doi     = {10.1126/science.1258096}
+}
+
+% =============================================================================
+% BOOKS
+% =============================================================================
+
+@book{Kumar2021,
+  author    = {Kumar, Vinay and Abbas, Abul K. and Aster, Jon C.},
+  title     = {Robbins and Cotran Pathologic Basis of Disease},
+  publisher = {Elsevier},
+  year      = {2021},
+  edition   = {10},
+  address   = {Philadelphia, PA},
+  isbn      = {978-0-323-53113-9}
+}
+
+@book{Alberts2014,
+  author    = {Alberts, Bruce and Johnson, Alexander and Lewis, Julian and Morgan, David and Raff, Martin and Roberts, Keith and Walter, Peter},
+  title     = {Molecular Biology of the Cell},
+  publisher = {Garland Science},
+  year      = {2014},
+  edition   = {6},
+  address   = {New York, NY},
+  isbn      = {978-0-815-34432-2}
+}
+
+% Book with editor instead of author
+@book{Sambrook2001,
+  editor    = {Sambrook, Joseph and Russell, David W.},
+  title     = {Molecular Cloning: A Laboratory Manual},
+  publisher = {Cold Spring Harbor Laboratory Press},
+  year      = {2001},
+  edition   = {3},
+  address   = {Cold Spring Harbor, NY},
+  isbn      = {978-0-879-69576-7}
+}
+
+% =============================================================================
+% CONFERENCE PAPERS (PROCEEDINGS)
+% =============================================================================
+
+@inproceedings{Vaswani2017,
+  author    = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, {\L}ukasz and Polosukhin, Illia},
+  title     = {Attention is All You Need},
+  booktitle = {Advances in Neural Information Processing Systems 30 (NeurIPS 2017)},
+  year      = {2017},
+  pages     = {5998--6008},
+  address   = {Long Beach, CA},
+  url       = {https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html}
+}
+
+@inproceedings{He2016,
+  author    = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  title     = {Deep Residual Learning for Image Recognition},
+  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year      = {2016},
+  pages     = {770--778},
+  address   = {Las Vegas, NV},
+  doi       = {10.1109/CVPR.2016.90}
+}
+
+% =============================================================================
+% BOOK CHAPTERS
+% =============================================================================
+
+@incollection{Brown2020,
+  author    = {Brown, Peter O. and Botstein, David},
+  title     = {Exploring the New World of the Genome with {DNA} Microarrays},
+  booktitle = {DNA Microarrays: A Molecular Cloning Manual},
+  editor    = {Eisen, Michael B. and Brown, Patrick O.},
+  publisher = {Cold Spring Harbor Laboratory Press},
+  year      = {2020},
+  pages     = {1--45},
+  address   = {Cold Spring Harbor, NY}
+}
+
+% =============================================================================
+% PHD THESES / DISSERTATIONS
+% =============================================================================
+
+@phdthesis{Johnson2023,
+  author  = {Johnson, Mary L.},
+  title   = {Novel Approaches to Cancer Immunotherapy Using {CRISPR} Technology},
+  school  = {Stanford University},
+  year    = {2023},
+  type    = {{PhD} dissertation},
+  address = {Stanford, CA}
+}
+
+% =============================================================================
+% MASTER'S THESES
+% =============================================================================
+
+@mastersthesis{Smith2022,
+  author  = {Smith, Robert J.},
+  title   = {Machine Learning Methods for Protein Structure Prediction},
+  school  = {Massachusetts Institute of Technology},
+  year    = {2022},
+  type    = {{Master's} thesis},
+  address = {Cambridge, MA}
+}
+
+% =============================================================================
+% TECHNICAL REPORTS
+% =============================================================================
+
+@techreport{WHO2020,
+  author      = {{World Health Organization}},
+  title       = {Clinical Management of {COVID-19}: Interim Guidance},
+  institution = {World Health Organization},
+  year        = {2020},
+  type        = {Technical Report},
+  number      = {WHO/2019-nCoV/clinical/2020.5},
+  address     = {Geneva, Switzerland}
+}
+
+% =============================================================================
+% PREPRINTS
+% =============================================================================
+
+% bioRxiv preprint
+@misc{Zhang2024preprint,
+  author       = {Zhang, Yi and Chen, Li and Wang, Hui and Liu, Xin},
+  title        = {Novel Therapeutic Targets in {Alzheimer}'s Disease},
+  year         = {2024},
+  howpublished = {bioRxiv},
+  doi          = {10.1101/2024.01.15.575432},
+  note         = {Preprint}
+}
+
+% arXiv preprint
+@misc{Brown2024arxiv,
+  author       = {Brown, Alice and Green, Bob},
+  title        = {Advances in Quantum Computing},
+  year         = {2024},
+  howpublished = {arXiv},
+  note         = {arXiv:2401.12345}
+}
+
+% =============================================================================
+% DATASETS
+% =============================================================================
+
+@misc{AlphaFoldDB2021,
+  author       = {{DeepMind} and {EMBL-EBI}},
+  title        = {{AlphaFold} Protein Structure Database},
+  year         = {2021},
+  howpublished = {Database},
+  url          = {https://alphafold.ebi.ac.uk/},
+  doi          = {10.1093/nar/gkab1061},
+  note         = {Version 4}
+}
+
+% =============================================================================
+% SOFTWARE / CODE
+% =============================================================================
+
+@misc{McKinney2010pandas,
+  author       = {McKinney, Wes},
+  title        = {pandas: A Foundational {Python} Library for Data Analysis and Statistics},
+  year         = {2010},
+  howpublished = {Software},
+  url          = {https://pandas.pydata.org/},
+  note         = {Python Data Analysis Library}
+}
+
+% =============================================================================
+% WEBSITES / ONLINE RESOURCES
+% =============================================================================
+
+@misc{NCBI2024,
+  author       = {{National Center for Biotechnology Information}},
+  title        = {{PubMed}: Database of Biomedical Literature},
+  year         = {2024},
+  howpublished = {Website},
+  url          = {https://pubmed.ncbi.nlm.nih.gov/},
+  note         = {Accessed: 2024-01-15}
+}
+
+% =============================================================================
+% SPECIAL CASES
+% =============================================================================
+
+% Article with organization as author
+@article{NatureEditorial2023,
+  author  = {{Nature Editorial Board}},
+  title   = {The Future of {AI} in Scientific Research},
+  journal = {Nature},
+  year    = {2023},
+  volume  = {615},
+  pages   = {1--2},
+  doi     = {10.1038/d41586-023-00001-1}
+}
+
+% Article with no volume number (some journals)
+@article{OpenAccess2024,
+  author  = {Williams, Sarah and Thomas, Michael},
+  title   = {Open Access Publishing in the 21st Century},
+  journal = {Journal of Scholarly Communication},
+  year    = {2024},
+  pages   = {e123456},
+  doi     = {10.1234/jsc.2024.123456}
+}
+
+% Conference paper with DOI
+@inproceedings{Garcia2023,
+  author    = {Garc{\'i}a-Mart{\'i}nez, Jos{\'e} and M{\"u}ller, Hans},
+  title     = {International Collaboration in Science},
+  booktitle = {Proceedings of the International Conference on Academic Publishing},
+  year      = {2023},
+  pages     = {45--52},
+  doi       = {10.1109/ICAP.2023.123456}
+}
+
+% Article with PMID but no DOI (older papers)
+@article{OldPaper1995,
+  author  = {Anderson, Philip W.},
+  title   = {Through the Glass Lightly},
+  journal = {Science},
+  year    = {1995},
+  volume  = {267},
+  number  = {5204},
+  pages   = {1615--1616},
+  note    = {PMID: 17808148}
+}
+

scientific_writer/.claude/skills/citation-management/assets/citation_checklist.md

@@ -0,0 +1,386 @@
+# Citation Quality Checklist
+
+Use this checklist to ensure your citations are accurate, complete, and properly formatted before final submission.
+
+## Pre-Submission Checklist
+
+### ✓ Metadata Accuracy
+
+- [ ] All author names are correct and properly formatted
+- [ ] Article titles match the actual publication
+- [ ] Journal/conference names are complete (not abbreviated unless required)
+- [ ] Publication years are accurate
+- [ ] Volume and issue numbers are correct
+- [ ] Page ranges are accurate
+
+### ✓ Required Fields
+
+- [ ] All @article entries have: author, title, journal, year
+- [ ] All @book entries have: author/editor, title, publisher, year
+- [ ] All @inproceedings entries have: author, title, booktitle, year
+- [ ] Modern papers (2000+) include DOI when available
+- [ ] All entries have unique citation keys
+
+### ✓ DOI Verification
+
+- [ ] All DOIs are properly formatted (10.XXXX/...)
+- [ ] DOIs resolve correctly to the article
+- [ ] No DOI prefix in the BibTeX field (no "doi:" or "https://doi.org/")
+- [ ] Metadata from CrossRef matches your BibTeX entry
+- [ ] Run: `python scripts/validate_citations.py references.bib --check-dois`
+
+### ✓ Formatting Consistency
+
+- [ ] Page ranges use double hyphen (--) not single (-)
+- [ ] No "pp." prefix in pages field
+- [ ] Author names use "and" separator (not semicolon or ampersand)
+- [ ] Capitalization protected in titles ({AlphaFold}, {CRISPR}, etc.)
+- [ ] Month names use standard abbreviations if included
+- [ ] Citation keys follow consistent format
+
+### ✓ Duplicate Detection
+
+- [ ] No duplicate DOIs in bibliography
+- [ ] No duplicate citation keys
+- [ ] No near-duplicate titles
+- [ ] Preprints updated to published versions when available
+- [ ] Run: `python scripts/validate_citations.py references.bib`
+
+### ✓ Special Characters
+
+- [ ] Accented characters properly formatted (e.g., {\"u} for ü)
+- [ ] Mathematical symbols use LaTeX commands
+- [ ] Chemical formulas properly formatted
+- [ ] No unescaped special characters (%, &, $, #, etc.)
+
+### ✓ BibTeX Syntax
+
+- [ ] All entries have balanced braces {}
+- [ ] Fields separated by commas
+- [ ] No comma after last field in each entry
+- [ ] Valid entry types (@article, @book, etc.)
+- [ ] Run: `python scripts/validate_citations.py references.bib`
+
+### ✓ File Organization
+
+- [ ] Bibliography sorted in logical order (by year, author, or key)
+- [ ] Consistent formatting throughout
+- [ ] No formatting inconsistencies between entries
+- [ ] Run: `python scripts/format_bibtex.py references.bib --sort year`
+
+## Automated Validation
+
+### Step 1: Format and Clean
+
+```bash
+python scripts/format_bibtex.py references.bib \
+  --deduplicate \
+  --sort year \
+  --descending \
+  --output clean_references.bib
+```
+
+**What this does**:
+- Removes duplicates
+- Standardizes formatting
+- Fixes common issues (page ranges, DOI format, etc.)
+- Sorts by year (newest first)
+
+### Step 2: Validate
+
+```bash
+python scripts/validate_citations.py clean_references.bib \
+  --check-dois \
+  --report validation_report.json \
+  --verbose
+```
+
+**What this does**:
+- Checks required fields
+- Verifies DOIs resolve
+- Detects duplicates
+- Validates syntax
+- Generates detailed report
+
+### Step 3: Review Report
+
+```bash
+cat validation_report.json
+```
+
+**Address any**:
+- **Errors**: Must fix (missing fields, broken DOIs, syntax errors)
+- **Warnings**: Should fix (missing recommended fields, formatting issues)
+- **Duplicates**: Remove or consolidate
+
+### Step 4: Final Check
+
+```bash
+python scripts/validate_citations.py clean_references.bib --verbose
+```
+
+**Goal**: Zero errors, minimal warnings
+
+## Manual Review Checklist
+
+### Critical Citations (Top 10-20 Most Important)
+
+For your most important citations, manually verify:
+
+- [ ] Visit DOI link and confirm it's the correct article
+- [ ] Check author names against the actual publication
+- [ ] Verify year matches publication date
+- [ ] Confirm journal/conference name is correct
+- [ ] Check that volume/pages match
+
+### Common Issues to Watch For
+
+**Missing Information**:
+- [ ] No DOI for papers published after 2000
+- [ ] Missing volume or page numbers for journal articles
+- [ ] Missing publisher for books
+- [ ] Missing conference location for proceedings
+
+**Formatting Errors**:
+- [ ] Single hyphen in page ranges (123-145 → 123--145)
+- [ ] Ampersands in author lists (Smith & Jones → Smith and Jones)
+- [ ] Unprotected acronyms in titles (DNA → {DNA})
+- [ ] DOI includes URL prefix (https://doi.org/10.xxx → 10.xxx)
+
+**Metadata Mismatches**:
+- [ ] Author names differ from publication
+- [ ] Year is online-first instead of print publication
+- [ ] Journal name abbreviated when it should be full
+- [ ] Volume/issue numbers swapped
+
+**Duplicates**:
+- [ ] Same paper cited with different citation keys
+- [ ] Preprint and published version both cited
+- [ ] Conference paper and journal version both cited
+
+## Field-Specific Checks
+
+### Biomedical Sciences
+
+- [ ] PubMed Central ID (PMCID) included when available
+- [ ] MeSH terms appropriate (if using)
+- [ ] Clinical trial registration number included (if applicable)
+- [ ] All references to treatments/drugs accurately cited
+
+### Computer Science
+
+- [ ] arXiv ID included for preprints
+- [ ] Conference proceedings properly cited (not just "NeurIPS")
+- [ ] Software/dataset citations include version numbers
+- [ ] GitHub links stable and permanent
+
+### General Sciences
+
+- [ ] Data availability statements properly cited
+- [ ] Retracted papers identified and removed
+- [ ] Preprints checked for published versions
+- [ ] Supplementary materials referenced if critical
+
+## Final Pre-Submission Steps
+
+### 1 Week Before Submission
+
+- [ ] Run full validation with DOI checking
+- [ ] Fix all errors and critical warnings
+- [ ] Manually verify top 10-20 most important citations
+- [ ] Check for any retracted papers
+
+### 3 Days Before Submission
+
+- [ ] Re-run validation after any manual edits
+- [ ] Ensure all in-text citations have corresponding bibliography entries
+- [ ] Ensure all bibliography entries are cited in text
+- [ ] Check citation style matches journal requirements
+
+### 1 Day Before Submission
+
+- [ ] Final validation check
+- [ ] LaTeX compilation successful with no warnings
+- [ ] PDF renders all citations correctly
+- [ ] Bibliography appears in correct format
+- [ ] No placeholder citations (Smith et al. XXXX)
+
+### Submission Day
+
+- [ ] One final validation run
+- [ ] No last-minute edits without re-validation
+- [ ] Bibliography file included in submission package
+- [ ] Figures/tables referenced in text match bibliography
+
+## Quality Metrics
+
+### Excellent Bibliography
+
+- ✓ 100% of entries have DOIs (for modern papers)
+- ✓ Zero validation errors
+- ✓ Zero missing required fields
+- ✓ Zero broken DOIs
+- ✓ Zero duplicates
+- ✓ Consistent formatting throughout
+- ✓ All citations manually spot-checked
+
+### Acceptable Bibliography
+
+- ✓ 90%+ of modern entries have DOIs
+- ✓ Zero high-severity errors
+- ✓ Minor warnings only (e.g., missing recommended fields)
+- ✓ Key citations manually verified
+- ✓ Compilation succeeds without errors
+
+### Needs Improvement
+
+- ✗ Missing DOIs for recent papers
+- ✗ High-severity validation errors
+- ✗ Broken or incorrect DOIs
+- ✗ Duplicate entries
+- ✗ Inconsistent formatting
+- ✗ Compilation warnings or errors
+
+## Emergency Fixes
+
+If you discover issues at the last minute:
+
+### Broken DOI
+
+```bash
+# Find correct DOI
+# Option 1: Search CrossRef
+# https://www.crossref.org/
+
+# Option 2: Search on publisher website
+# Option 3: Google Scholar
+
+# Re-extract metadata
+python scripts/extract_metadata.py --doi CORRECT_DOI
+```
+
+### Missing Information
+
+```bash
+# Extract from DOI
+python scripts/extract_metadata.py --doi 10.xxxx/yyyy
+
+# Or from PMID (biomedical)
+python scripts/extract_metadata.py --pmid 12345678
+
+# Or from arXiv
+python scripts/extract_metadata.py --arxiv 2103.12345
+```
+
+### Duplicate Entries
+
+```bash
+# Auto-remove duplicates
+python scripts/format_bibtex.py references.bib \
+  --deduplicate \
+  --output fixed_references.bib
+```
+
+### Formatting Errors
+
+```bash
+# Auto-fix common issues
+python scripts/format_bibtex.py references.bib \
+  --output fixed_references.bib
+
+# Then validate
+python scripts/validate_citations.py fixed_references.bib
+```
+
+## Long-Term Best Practices
+
+### During Research
+
+- [ ] Add citations to bibliography file as you find them
+- [ ] Extract metadata immediately using DOI
+- [ ] Validate after every 10-20 additions
+- [ ] Keep bibliography file under version control
+
+### During Writing
+
+- [ ] Cite as you write
+- [ ] Use consistent citation keys
+- [ ] Don't delay adding references
+- [ ] Validate weekly
+
+### Before Submission
+
+- [ ] Allow 2-3 days for citation cleanup
+- [ ] Don't wait until the last day
+- [ ] Automate what you can
+- [ ] Manually verify critical citations
+
+## Tool Quick Reference
+
+### Extract Metadata
+
+```bash
+# From DOI
+python scripts/doi_to_bibtex.py 10.1038/nature12345
+
+# From multiple sources
+python scripts/extract_metadata.py \
+  --doi 10.1038/nature12345 \
+  --pmid 12345678 \
+  --arxiv 2103.12345 \
+  --output references.bib
+```
+
+### Validate
+
+```bash
+# Basic validation
+python scripts/validate_citations.py references.bib
+
+# With DOI checking (slow but thorough)
+python scripts/validate_citations.py references.bib --check-dois
+
+# Generate report
+python scripts/validate_citations.py references.bib \
+  --report validation.json \
+  --verbose
+```
+
+### Format and Clean
+
+```bash
+# Format and fix issues
+python scripts/format_bibtex.py references.bib
+
+# Remove duplicates and sort
+python scripts/format_bibtex.py references.bib \
+  --deduplicate \
+  --sort year \
+  --descending \
+  --output clean_refs.bib
+```
+
+## Summary
+
+**Minimum Requirements**:
+1. Run `format_bibtex.py --deduplicate`
+2. Run `validate_citations.py`
+3. Fix all errors
+4. Compile successfully
+
+**Recommended**:
+1. Format, deduplicate, and sort
+2. Validate with `--check-dois`
+3. Fix all errors and warnings
+4. Manually verify top citations
+5. Re-validate after fixes
+
+**Best Practice**:
+1. Validate throughout research process
+2. Use automated tools consistently
+3. Keep bibliography clean and organized
+4. Document any special cases
+5. Final validation 1-3 days before submission
+
+**Remember**: Citation errors reflect poorly on your scholarship. Taking time to ensure accuracy is worthwhile!
+