Skip to content

Release to main: JOSS paper rewrite and syllabus prompt fix (#460) - #461

Merged
phanindra-max merged 2 commits into
mainfrom
dev
Nov 7, 2026
Merged

phanindra-max merged 2 commits into
mainfrom
dev

Conversation

@phanindra-max

Copy link
Copy Markdown
Member

Brings #460 from dev to main. It was merged into dev in #460; this PR only promotes it. The JOSS paper is built from main, so the reviewer sees the revised paper only once this is merged.

What reaches main

  • eed165d docs(paper): rewrite remaining sections from JOSS paper review ([JOSS] Paper Feedback #447).
    • paper.md:
      • Statement of need, State of the field and Software design are rewritten.
      • The AI usage disclosure is rewritten to the JOSS AI policy.
      • Acknowledgments now state the funders' role.
    • paper.bib: the unused Autor2013 entry is removed.
    • laiser/services.py, laiser/config.py: syllabi now use the shared extraction prompt. Before this, they were sent to a placeholder prompt that contained no document text.
    • docs/usage.md: updated to match.
    • tests/test_syllabus_prompt.py: new tests for the fix.

Checks

🤖 Generated with Claude Code

phanindra-max and others added 2 commits November 7, 2026 04:10
Paper
- Statement of need: rewritten from the authors' answers on the problem,
  its cost and the response; existing-work claims are now cited.
- State of the field: esco-skill-extractor and ESCOX are the same tool and
  are now described once; the unsupported "lacks preprocessing" clause is
  removed; a new paragraph states what LAiSER adds, why it was built rather
  than extending Nesta's library, and that it has no published evaluation.
- Software design: rewritten as four paragraphs (pipeline, LLM vs NER,
  exact search, reproducibility and its limits), checked against the code.
- AI usage disclosure: names each tool and model version, what it was used
  for, and how this revision was produced, per the JOSS AI policy.
- Acknowledgments: states that the funders had no role.
- paper.bib: remove Autor2013, no longer cited. Body is 1,748 words.

Code
- Syllabi used a placeholder prompt (" Work in progress") that contained no
  document text. Every input type now uses the shared extraction prompt and
  reads every column in text_columns. Tests added; docs/usage.md updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
docs(paper): rewrite remaining sections from JOSS paper review (#447)
Copilot AI balanced review requested due to automatic review settings November 7, 2026 10:04

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot was unable to review this pull request because the user who requested the review has insufficient remaining quota. Try requesting a review at a lower effort level.

An organization owner can choose the repository organization as the billing source for reviews requested by members with a paid Copilot license. Learn about Copilot code review billing.

@github-actions

github-actions Bot commented Nov 7, 2026

Copy link
Copy Markdown

Code Hygiene

The following items are defined but not yet in active use. Routine cleanup — no impact on functionality.

  • laiser/llm_methods.py:87 — unused variable 'args' (100% confidence)
  • laiser/llm_models/llama_cpp_handler.py:45 — unused variable 'chat_format' (100% confidence)
  • laiser/llm_models/llama_cpp_handler.py:86 — unused variable 'exc' (100% confidence)
  • laiser/llm_models/llama_cpp_handler.py:86 — unused variable 'exc_type' (100% confidence)
  • laiser/llm_models/llama_cpp_handler.py:86 — unused variable 'tb' (100% confidence)
  • laiser/llm_models/llm_router.py:71 — unused variable 'args' (100% confidence)
  • laiser/llm_models/llm_router.py:86 — unused variable 'args' (100% confidence)
  • laiser/llm_models/llm_router.py:89 — unused variable 'args' (100% confidence)
  • laiser/services.py:127 — unused variable 'raw_description' (100% confidence)

@github-actions

github-actions Bot commented Nov 7, 2026

Copy link
Copy Markdown

Complexity Analysis

Average: C — Moderate (13.75)

Hotspots tracked below. These are functional, well-exercised components — listed for visibility as the codebase scales.

Grade Name Type Score
F FAISSIndexManager.initialize_index Method 51
E SkillExtractionService.extract_and_align_core Method 36
E FAISSIndexManager.search_similar_skills Method 32
D ResponseParser._parse_skills_from_response Method 24
D FAISSIndexManager Class 22
C ResponseParser.parse_knowledge_task_response Method 20
C _BaseTaxonomyFAISSIndexManager.search_similar Method 18
C ResponseParser Class 17
C ResponseParser.parse_ksa_extraction_response Method 16
C ResponseParser.parse_skill_extraction_response Method 15
C openai_generate Function 14
C parse_output_vllm Function 13
C AlignmentService.align Method 11
C LLMRouter._initialize_components Method 11
C anthropic_generate Function 11
B SkillExtractionService._deduplicate Method 10
B GeminiAPI.generate_with_config Method 10
B load_model_from_vllm Function 10
B _BaseTaxonomyFAISSIndexManager.initialize_index Method 9
B ResponseParser.parse_ksa_details_response Method 8
B SkillExtractionService Class 8
B _BaseTaxonomyFAISSIndexManager Class 8
B llm_generate Function 8
B SkillExtractorRefactored._expand_allowed_sources Method 7
B get_completion_vllm Function 7
B LLMRouter.generate Method 7
B llama_cpp_chat Function 7
B AlignmentService Class 6
B SkillExtractionService._normalize_mixed_concept_rows Method 6
B fetch_model_output Function 6
B GeminiAPI Class 6
B LlamaCppBackend.__init__ Method 6

@phanindra-max
phanindra-max merged commit 3c22a25 into main Nov 7, 2026
33 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants