{"id":51302348,"url":"https://github.com/zer0contextlost/sentinalai","last_synced_at":"2026-06-30T21:01:57.741Z","repository":{"id":356128747,"uuid":"1231137214","full_name":"zer0contextlost/SentinalAI","owner":"zer0contextlost","description":null,"archived":false,"fork":false,"pushed_at":"2026-05-06T18:51:36.000Z","size":90,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-06T19:39:07.995Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zer0contextlost.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-06T17:03:10.000Z","updated_at":"2026-05-06T18:51:41.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/zer0contextlost/SentinalAI","commit_stats":null,"previous_names":["zer0contextlost/sentinalai"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/zer0contextlost/SentinalAI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zer0contextlost%2FSentinalAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zer0contextlost%2FSentinalAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zer0contextlost%2FSentinalAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zer0contextlost%2FSentinalAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zer0contextlost","download_url":"https://codeload.github.com/zer0contextlost/SentinalAI/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zer0contextlost%2FSentinalAI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34983171,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-30T02:00:05.919Z","response_time":92,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-06-30T21:01:56.437Z","updated_at":"2026-06-30T21:01:57.734Z","avatar_url":"https://github.com/zer0contextlost.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SentinalAI\n\nResearch codebase for AI-generated code detection via style fingerprinting.\n\n## What This Is\n\nAn empirical study of whether stylometric features can reliably detect AI-generated\ncode. Includes a 65-feature extractor, corpus collection pipelines, and classifier\nevaluation across two datasets — SemEval-2026 Task 13 (500K samples, 34 AI models)\nand a novel paired Codeforces corpus (same problem, human vs. AI solution).\n\n## Project Structure\n\n```\nfeatures/          65-feature extractor (lexical + Python AST)\ncollector/         corpus collection — SemEval pull, Codeforces AI gen, GitHub human scrape\nscripts/           feature matrix build, perplexity validation, classifier training/eval\nmodels/            baseline and paired corpus classifier training\napi/               inference endpoint (stub)\n```\n\n## Datasets\n\n**SemEval-2026 Task 13** — `DaniilOr/SemEval-2026-Task13` on HuggingFace  \n500K samples, 34 AI generators, Python/C++/Java\n\n**Paired Codeforces corpus** — built by this repo  \n96 competitive programming problems each solved by a human (pre-2022 GitHub) and an AI (deepseek-coder:6.7b).\nCollected via `collector/scrape_codeforces.py` and `collector/fetch_github_human_solutions.py`.\n\n## Setup\n\n```bash\npip install -r requirements.txt\n# Requires Ollama running at localhost:11434 for AI generation and perplexity scoring\n# ollama pull deepseek-coder:6.7b\n```\n\n## Running\n\n```bash\n# Pull SemEval corpus\npython collector/pull_semeval_dataset.py\n\n# Build feature matrix\npython scripts/build_feature_matrix.py\n\n# Train baseline on SemEval\npython models/train_baseline.py\n\n# Build paired corpus features\npython scripts/build_paired_features.py\n\n# Train on paired corpus (leave-one-problem-out CV)\npython scripts/train_paired_classifier.py\n\n# Cross-dataset generalization tests\npython scripts/test_generalization.py\npython scripts/test_generalization_reverse.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzer0contextlost%2Fsentinalai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzer0contextlost%2Fsentinalai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzer0contextlost%2Fsentinalai/lists"}