google-research/paper-orchestra
PaperOrchestra is a multi-agent framework for automated AI research paper writing.
Python★ 1,740+313 that day#11 on trending
E30.2/100
Duplication56
7.9% in python, latex, bashDead code7
34%Complexity62
37.8% The score is jscpd's own --health model: markup, data and text left out, tests kept. The numbers below are the trending scan's.
7.93%duplicated code · 718 of 9,055 lines
22clones in code
32code files of 45 scanned
7.38%duplicated over all files · 24 clones
Most complex files
- autoraters/citation_f1.py132 cx
- frontend/app.py127 cx
- methods/agents/literature_review_agent.py101 cx
- autoraters/sxs_paper_quality.py70 cx
- autoraters/sxs_lit_review_quality.py65 cx
- utils/gemini_utils.py56 cx
- methods/agents/content_refinement_agent.py47 cx
- methods/paper_writer_with_plotting.py47 cx
- utils/pdf_utils.py46 cx
- methods/paper_writer.py43 cx
Dead code 34% unused · 43 findings
- autoraters/citation_f1.pyunused-file
- autoraters/sxs_paper_quality.pyunused-file
- autoraters/lit_review_quality.pyunused-file
- autoraters/sxs_lit_review_quality.pyunused-file
- autoraters/prompts/lit_review_quality_prompts.pyunused-file
- methods/paper_writer_with_plotting.py:run_batch_writeupunused-export
- methods/prompts/format_agent.pyunused-file
- autoraters/prompts/sxs_quality_prompts.pyunused-file
- methods/paper_writer.py:run_batch_writeupunused-export
- methods/paper_writer_with_plotting.py:process_paper_taskunused-export
The code number leaves out tests, fixtures, docs, examples, data files, styles, translations and vendored code.
Largest clones in the code
- 117 lines in 2 placespython566 tokens
253 writer_model_name=writer_model_name, 254 research_cutoff=research_cutoff, 255) 256 257if success: 258 result["status"] = "success" 259 result["paper_path"] = final_paper_path 260 print(f"Paper {paper_id} successfully written!") 261else: 262 print(f"Paper {paper_id} writing failed.")First 10 of 117 lines.
- 92 lines in 2 placespython385 tokens
237with ThreadPoolExecutor(max_workers=max_workers) as executor: 238 futures = [] 239 for pid, p1, p2 in common_ids: 240 f = executor.submit( 241 _process_and_save_single_sxs, 242 pid, 243 p1, 244 p2, 245 output_json_path, 246 current_results,First 10 of 92 lines.
- 68 lines in 2 placespython323 tokens
105rating2 = rate_sxs_lit_review(paper2_text, paper1_text, model_name=model_name) 106 107if not rating1 or not rating2: 108 print( 109 f"❌ [{paper_id}] Failed to get ratings for one or both rounds.", flush=True 110 ) 111 return paper_id, False 112 113winner1 = rating1.get("winner", "").lower() if isinstance(rating1, dict) else "" 114winner2 = rating2.get("winner", "").lower() if isinstance(rating2, dict) else ""First 10 of 68 lines.
7 more
- 42 lines in 2 placespython245 tokens
- 45 lines in 2 placespython208 tokens
- 35 lines in 2 placespython203 tokens
- 40 lines in 2 placespython203 tokens
- 26 lines in 2 placespython138 tokens
- 36 lines in 2 placespython134 tokens
- 35 lines in 2 placespython127 tokens
Largest clones over all files, tests and data included
- 117 lines in 2 placespython566 tokens
253 writer_model_name=writer_model_name, 254 research_cutoff=research_cutoff, 255) 256 257if success: 258 result["status"] = "success" 259 result["paper_path"] = final_paper_path 260 print(f"Paper {paper_id} successfully written!") 261else: 262 print(f"Paper {paper_id} writing failed.")First 10 of 117 lines.
- 92 lines in 2 placespython385 tokens
237with ThreadPoolExecutor(max_workers=max_workers) as executor: 238 futures = [] 239 for pid, p1, p2 in common_ids: 240 f = executor.submit( 241 _process_and_save_single_sxs, 242 pid, 243 p1, 244 p2, 245 output_json_path, 246 current_results,First 10 of 92 lines.
- 41 lines in 2 placeslatex335 tokens
23{\tt\small [email protected]} 24} 25 26\begin{document} 27\maketitle 28 29\begin{abstract} 30%%%%%%%%% ABSTRACT %%%%%%%%% 31Abstract here. 32%%%%%%%%% ABSTRACT %%%%%%%%%20\newcommand{\new}{\marginpar{NEW}} 21 22\begin{document} 23 24\maketitle 25 26\begin{abstract} 27%%%%%%%%% ABSTRACT %%%%%%%%% 28Abstract here. 29%%%%%%%%% ABSTRACT %%%%%%%%%First 10 of 41 lines, the second copy on the right.
- 68 lines in 2 placespython323 tokens
- 42 lines in 2 placespython245 tokens
By format, code only
| Format | Files | Lines | Clones | Duplicated lines | Duplication |
|---|---|---|---|---|---|
| python | 31 | 9,032 | 22 | 718 | 7.95% |
| bash | 1 | 23 | 0 | 0 | 0% |
By format, all files
| Format | Files | Lines | Clones | Duplicated lines | Duplication |
|---|---|---|---|---|---|
| python | 31 | 9,032 | 22 | 718 | 7.95% |
| latex | 6 | 756 | 2 | 48 | 6.35% |
| markdown | 6 | 569 | 0 | 0 | 0% |
| bash | 1 | 23 | 0 | 0 | 0% |
| text | 1 | 6 | 0 | 0 | 0% |
Trending appearances
| Day | Rank | Stars | Files | Lines | Clones | All files | Code | Health | Commit |
|---|---|---|---|---|---|---|---|---|---|
| Nov 17, 2026 | #11 | 1,740 (+313) | 45 | 10,386 | 24 | 7.38% | 7.93% | E 30.2 | d9bae99 |
Want this for your own project? Install jscpd and run jscpd ., or measure it the way the baselines were measured.