Skip to content

Commit 9754280

Browse files
ishraqkhannishraqkhann
committed
Added new data
0 parents  commit 9754280

File tree

117 files changed

+21099
-0
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

117 files changed

+21099
-0
lines changed

‎.github/ISSUE_TEMPLATE/research_question.md‎

Lines changed: 22 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,22 @@
1+
---
2+
name: Research Question
3+
about: Ask questions about the Chronos research or methodology
4+
title: '[RESEARCH] '
5+
labels: 'question, research'
6+
assignees: ''
7+
---
8+
9+
**Research Topic**
10+
Which aspect of the research are you asking about? (e.g., AGR mechanism, evaluation methodology, benchmark design)
11+
12+
**Your Question**
13+
Clearly state your research question or area of confusion.
14+
15+
**Context**
16+
Have you:
17+
- [ ] Read the full research paper?
18+
- [ ] Checked the FAQ?
19+
- [ ] Searched existing issues?
20+
21+
**Additional Information**
22+
Any additional context, references, or related work that might be relevant.

‎.github/workflows/quality.yml‎

Lines changed: 42 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,42 @@
1+
name: Code Quality
2+
3+
on:
4+
push:
5+
branches: [ main, develop ]
6+
pull_request:
7+
branches: [ main ]
8+
9+
jobs:
10+
quality:
11+
runs-on: ubuntu-latest
12+
13+
steps:
14+
- uses: actions/checkout@v3
15+
16+
- name: Set up Python
17+
uses: actions/setup-python@v4
18+
with:
19+
python-version: '3.10'
20+
21+
- name: Install dependencies
22+
run: |
23+
python -m pip install --upgrade pip
24+
pip install black flake8 mypy isort
25+
pip install -r requirements.txt
26+
27+
- name: Format check with Black
28+
run: |
29+
black --check benchmarks/ tests/ scripts/
30+
31+
- name: Import sort check with isort
32+
run: |
33+
isort --check-only benchmarks/ tests/ scripts/
34+
35+
- name: Lint with flake8
36+
run: |
37+
flake8 benchmarks/ tests/ scripts/ --count --select=E9,F63,F7,F82 --show-source --statistics
38+
flake8 benchmarks/ tests/ scripts/ --count --exit-zero --max-complexity=10 --max-line-length=88 --statistics
39+
40+
- name: Type check with mypy
41+
run: |
42+
mypy benchmarks/ --ignore-missing-imports

‎.github/workflows/tests.yml‎

Lines changed: 48 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,48 @@
1+
name: Tests
2+
3+
on:
4+
push:
5+
branches: [ main, develop ]
6+
pull_request:
7+
branches: [ main ]
8+
9+
jobs:
10+
test:
11+
runs-on: ubuntu-latest
12+
strategy:
13+
matrix:
14+
python-version: [3.8, 3.9, '3.10', 3.11]
15+
16+
steps:
17+
- uses: actions/checkout@v3
18+
19+
- name: Set up Python ${{ matrix.python-version }}
20+
uses: actions/setup-python@v4
21+
with:
22+
python-version: ${{ matrix.python-version }}
23+
24+
- name: Cache dependencies
25+
uses: actions/cache@v3
26+
with:
27+
path: ~/.cache/pip
28+
key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
29+
restore-keys: |
30+
${{ runner.os }}-pip-
31+
32+
- name: Install dependencies
33+
run: |
34+
python -m pip install --upgrade pip
35+
pip install -r requirements.txt
36+
pip install -e .
37+
38+
- name: Run tests with pytest
39+
run: |
40+
pytest tests/ -v --cov=benchmarks --cov-report=xml --cov-report=html
41+
42+
- name: Upload coverage to Codecov
43+
uses: codecov/codecov-action@v3
44+
with:
45+
file: ./coverage.xml
46+
flags: unittests
47+
name: codecov-umbrella
48+
fail_ci_if_error: false

‎.gitignore‎

Lines changed: 92 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,92 @@
1+
# Python
2+
__pycache__/
3+
*.py[cod]
4+
*$py.class
5+
*.so
6+
.Python
7+
build/
8+
develop-eggs/
9+
dist/
10+
downloads/
11+
eggs/
12+
.eggs/
13+
lib/
14+
lib64/
15+
parts/
16+
sdist/
17+
var/
18+
wheels/
19+
*.egg-info/
20+
.installed.cfg
21+
*.egg
22+
MANIFEST
23+
24+
# Virtual environments
25+
venv/
26+
env/
27+
ENV/
28+
.venv
29+
30+
# Jupyter Notebooks
31+
.ipynb_checkpoints
32+
*.ipynb_checkpoints/
33+
34+
# IDE
35+
.vscode/
36+
.idea/
37+
*.swp
38+
*.swo
39+
*~
40+
.project
41+
.pydevproject
42+
43+
# OS
44+
.DS_Store
45+
.DS_Store?
46+
._*
47+
.Spotlight-V100
48+
.Trashes
49+
ehthumbs.db
50+
Thumbs.db
51+
52+
# Testing
53+
.coverage
54+
.pytest_cache/
55+
htmlcov/
56+
.tox/
57+
.nox/
58+
coverage.xml
59+
*.cover
60+
.hypothesis/
61+
62+
# Documentation
63+
docs/_build/
64+
site/
65+
66+
# Data and results
67+
data/raw/
68+
data/processed/
69+
results/raw_data/sensitive/
70+
*.pkl
71+
*.h5
72+
*.hdf5
73+
74+
# Logs
75+
*.log
76+
logs/
77+
78+
# Environment variables
79+
.env
80+
.env.local
81+
82+
# Temporary files
83+
tmp/
84+
temp/
85+
*.tmp
86+
*.temp
87+
*.bak
88+
89+
# Model files (proprietary)
90+
models/
91+
weights/
92+
checkpoints/

‎CHANGELOG.md‎

Lines changed: 64 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,64 @@
1+
# Changelog
2+
3+
All notable changes to the Kodezi Chronos research repository will be documented in this file.
4+
5+
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
6+
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
7+
8+
## [1.0.0] - 2025-07-14
9+
10+
### Added
11+
- Initial release of Kodezi Chronos research repository
12+
- Complete research paper (arXiv:2507.12482)
13+
- Multi Random Retrieval (MRR) benchmark specification
14+
- Comprehensive evaluation results and metrics
15+
- Adaptive Graph-Guided Retrieval (AGR) documentation
16+
- Architecture overview and design principles
17+
- Case studies demonstrating debugging capabilities
18+
- Contribution guidelines and code of conduct
19+
- FAQ and documentation
20+
21+
### Research Highlights
22+
- 65.3% debugging success rate (6-7x improvement over GPT-4)
23+
- 78.4% root cause accuracy
24+
- 91% retrieval precision with AGR
25+
- 40% reduction in debugging cycles
26+
- Successful handling of repository-scale contexts
27+
28+
### Benchmark Results
29+
- 5,000 real-world debugging scenarios evaluated
30+
- Statistical significance (p < 0.001) across all metrics
31+
- Comprehensive ablation studies
32+
- Performance analysis across bug categories and repo sizes
33+
34+
### Documentation
35+
- Complete API design documentation
36+
- Evaluation methodology and protocols
37+
- Reproduction guidelines for researchers
38+
- Integration patterns for future deployment
39+
40+
### Known Limitations
41+
- Lower performance on hardware-specific bugs (23.4%)
42+
- Challenges with domain-specific logic (28.7%)
43+
- Limited effectiveness on UI/visual bugs (8.3%)
44+
45+
## Future Releases
46+
47+
### [Planned for Q4 2025]
48+
- Model release through Kodezi OS platform
49+
- Additional language support announcements
50+
- Extended benchmark suite
51+
- Performance optimizations
52+
53+
### [Planned for Q1 2026]
54+
- Full Kodezi OS integration
55+
- Enterprise deployment options
56+
- Advanced debugging features
57+
- Cross-repository capabilities
58+
59+
---
60+
61+
For more information about Kodezi Chronos:
62+
- Research Paper: [arXiv:2507.12482](https://arxiv.org/abs/2507.12482)
63+
- Model Access: [https://kodezi.com/os](https://kodezi.com/os)
64+
- Contact: [email protected]

‎CITATION.cff‎

Lines changed: 51 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,51 @@
1+
cff-version: 1.2.0
2+
title: "Kodezi Chronos: A Debugging-First Language Model for Repository-Scale, Memory-Driven Code Understanding"
3+
message: "If you use this research, please cite it as below."
4+
type: software
5+
authors:
6+
- given-names: Ishraq
7+
family-names: Khan
8+
email: [email protected]
9+
affiliation: Kodezi Inc.
10+
orcid: 'https://orcid.org/0000-0000-0000-0000'
11+
- given-names: Assad
12+
family-names: Chowdary
13+
email: [email protected]
14+
affiliation: Kodezi Inc.
15+
- given-names: Sharoz
16+
family-names: Haseeb
17+
email: [email protected]
18+
affiliation: Kodezi Inc.
19+
- given-names: Urvish
20+
family-names: Patel
21+
email: [email protected]
22+
affiliation: Kodezi Inc.
23+
identifiers:
24+
- type: doi
25+
value: 10.48550/arXiv.2507.12482
26+
description: arXiv preprint
27+
repository-code: 'https://github.com/kodezi/chronos-research'
28+
url: 'https://kodezi.com/chronos'
29+
repository: 'https://arxiv.org/abs/2507.12482'
30+
abstract: >-
31+
Large Language Models (LLMs) have advanced code generation and software automation,
32+
but are fundamentally constrained by limited inference-time context and lack of
33+
explicit code structure reasoning. We introduce Kodezi Chronos, a next-generation
34+
architecture for autonomous code understanding, debugging, and maintenance, designed
35+
to operate across ultra-long contexts comprising entire codebases, histories, and
36+
documentation—all without fixed window limits. Kodezi Chronos leverages a multi-level
37+
embedding memory engine, combining vector and graph-based indexing with continuous
38+
code-aware retrieval. This enables efficient and accurate reasoning over millions
39+
of lines of code, supporting repository-scale comprehension, multi-file refactoring,
40+
and real-time self-healing actions. Chronos achieves 65.3% debugging success rate,
41+
representing a 6-7x improvement over state-of-the-art models.
42+
keywords:
43+
- debugging
44+
- language models
45+
- code understanding
46+
- software engineering
47+
- autonomous systems
48+
- memory-driven AI
49+
license: MIT
50+
version: 1.0.0
51+
date-released: '2025-07-14'

‎CODE_OF_CONDUCT.md‎

Lines changed: 45 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,45 @@
1+
# Code of Conduct - Chronos Research Repository
2+
3+
## Important Notice
4+
5+
This repository contains research materials, benchmarks, and documentation for the Kodezi Chronos debugging model. The model itself is proprietary and available only through Kodezi OS. Learn more at https://chronos.so
6+
7+
## Our Pledge
8+
9+
We as members, contributors, and leaders pledge to make participation in our research community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
10+
11+
## Our Standards
12+
13+
Examples of behavior that contributes to a positive environment:
14+
15+
* Using welcoming and inclusive language
16+
* Being respectful of differing viewpoints and experiences
17+
* Gracefully accepting constructive criticism
18+
* Focusing on what is best for the community
19+
* Showing empathy towards other community members
20+
21+
Examples of unacceptable behavior:
22+
23+
* The use of sexualized language or imagery
24+
* Trolling, insulting or derogatory comments, and personal attacks
25+
* Public or private harassment
26+
* Publishing others' private information without permission
27+
* Other conduct which could reasonably be considered inappropriate
28+
29+
## Enforcement Responsibilities
30+
31+
Community leaders are responsible for clarifying and enforcing our standards of acceptable behavior and will take appropriate and fair corrective action in response to any behavior that they deem inappropriate, threatening, offensive, or harmful.
32+
33+
## Scope
34+
35+
This Code of Conduct applies within all community spaces, and also applies when an individual is officially representing the community in public spaces.
36+
37+
## Enforcement
38+
39+
Instances of abusive, harassing, or otherwise unacceptable behavior may be reported to the community leaders responsible for enforcement at [email protected].
40+
41+
All complaints will be reviewed and investigated promptly and fairly.
42+
43+
## Attribution
44+
45+
This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/), version 2.0.

0 commit comments

Comments
 (0)