Публічний реєстрПомірний
Звіт про здоров'я програмного забезпеченнясхема 0.27.0 · метрики 1.13.0 · 2026-07-27 13:12 UTC
rmovva / HypotheSAEs
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382
rmovva/HypotheSAEs має індекс здоров’я 53 зі 100, що відповідає смузі «Помірний». Найвищий показник — Vitality (69/100), найнижчий — AI Readiness (24/100). Останнє оновлення було 3 дні тому. Більшість нещодавньої роботи виконує один учасник.
53
загалом / 100Індекс здоров'я програмного забезпечення
Метрики згруповано у зважені категорії на шкалі 1–100. Загальна оцінка починається як їхнє середнє; коли публічні дані активують Політику юрисдикцій високого ризику, рейтинг коригується й отримує верхню межу 49 («Під ризиком»). Готовність до ШІ не входить до індексу.
53
Відмінний85-100Зразковий; відповідає практично всім перевіреним критеріям
Добрий70-84Здоровий; незначні прогалини
Помірний50-69Прийнятний, але з помітними прогалинами; рекомендовано перевірку
У зоні ризику30-49Суттєві слабкі місця; впровадження потребує обережності
Критичний1-29Серйозні проблеми (покинутий, єдиний мейнтейнер, без базової гігієни)
Профіль оцінок
Кожна вісь — окрема категорія. Форма важить більше, ніж середнє: здоровий об'єкт заповнює всю фігуру, тоді як профіль із піками та провалами означає, що сила в одному вимірі маскує ризик в іншому.
Власність
Raj MovvaОсобистий обліковий запис
20 підписників33 публічні репозиторіїз лют. 2016 р.UC Berkeley
Цей репозиторій належить особистому обліковому запису. Проєкт з єдиним власником несе більший ризик безперервності, ніж підтримуваний організацією.
Пакетні екосистеми
| Реєстр | Пакет | Версія | Завантажень / міс | Версії | Остання публікація |
|---|---|---|---|---|---|
| PyPI | hypothesaes | 2.0.1 | 240 | 13 | 24 дні тому |
Метрики за категоріями
Життєздатність
Чи живий проєкт — чи пишеться код і чи виходять релізи?
69
Активність розробки
62Помірний
Як обчислюється оцінка
| 36/36 | Свіжість push — останній push 3 дн. тому |
| 7.6/36 | Ритм комітів — 11/52 тижнів із комітами |
| 15.3/18 | Обсяг комітів — 50 комітів за останній рік |
| 3/10 | OpenSSF Scorecard: Maintained — 3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3 |
Використані вхідні дані
| commits_last_year | 50 |
| human_commit_share | 1 |
| days_since_last_push | 3 |
| active_weeks_last_year | 11 |
Дисципліна релізів
80Добрий
Як обчислюється оцінка
| 16.2/27 | Випускає релізи — 7 тегів версій (без релізів GitHub) |
| 36/36 | Свіжість релізів — останній реліз 24 дн. тому |
| 19.8/27 | Ритм релізів — реліз кожні ~72,6 дн. |
| 0/10 | OpenSSF Scorecard: Signed-Releases — немає даних |
Використані вхідні дані
| releases_count | 7 |
| latest_release_tag | v2.0.1 |
| releases_from_tags | так |
| days_since_latest_release | 24 |
| mean_days_between_releases | 72,6 |
Виключено з оцінювання (немає даних або не застосовно): OpenSSF Scorecard: Signed-Releases. Залишкові ваги перенормовано.
Спільнота та впровадження
Чи має проєкт користувачів, завантаження, увагу та влаштовані умови для контриб’юторів?
45
Популярність і впровадження
44У зоні ризику
Як обчислюється оцінка
| 31.7/60 | Зірки — 91 зірок |
| 11.9/25 | Форки — 28 форків |
| 0/15 | Спостерігачі — 2 спостерігачів |
Використані вхідні дані
| forks | 28 |
| stars | 91 |
| watchers | 2 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Здоров'я спільноти
50Помірний
Як обчислюється оцінка
| 22.5/22.5 | README |
| 22.5/22.5 | Ліцензія — визнана ліцензія (Apache-2.0) |
| 0/18 | Настанови CONTRIBUTING |
| 0/13.5 | Кодекс поведінки |
| 0/7.2 | Шаблон issue |
| 0/6.3 | Шаблон PR |
Використані вхідні дані
| has_readme | так |
| has_license | так |
| has_contributing | ні |
| has_issue_template | ні |
| has_code_of_conduct | ні |
| has_pull_request_template | ні |
Впровадження в екосистемі (завантаження)
40У зоні ризику
Як обчислюється оцінка
| 31.8/80 | Щомісячні завантаження — 240 завантажень/місяць у pypi |
| 0/20 | Залежні пакети в реєстрі — ця екосистема цього не повідомляє |
Використані вхідні дані
| packages | hypothesaes |
| dependents | — |
| ecosystems | pypi |
| total_downloads | — |
| monthly_downloads | 240 |
Виключено з оцінювання (немає даних або не застосовно): Залежні пакети в реєстрі. Залишкові ваги перенормовано.
Сталість та врядування
Чи переживе проєкт своїх людей — бас-фактор, реактивність, хто за ним стоїть і як супроводжуються пакети?
57
Стійкість мейнтейнерів (бас-фактор)
16Критичний
Як обчислюється оцінка
| 9/54 | Бас-фактор — на 1 контриб’ютор(ів) припадає половина всіх комітів |
| 0.3/22.5 | Розподіл комітів — головний контриб’ютор — автор 99% комітів |
| 4.1/13.5 | Широта контриб’юторів — 3 контриб’юторів |
| 3/10 | OpenSSF Scorecard: Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
Використані вхідні дані
| bus_factor | 1 |
| contributors_sampled | 3 |
| top_contributor_share | 0,987 |
Реактивність на issue та PR
76Добрий
Як обчислюється оцінка
| 37.4/46.8 | Вирішення issue — закрито 80% issue |
| 38.2/38.3 | Прийняття PR — злито 5/5 вирішених PR |
| 0/15 | OpenSSF Scorecard: Code-Review — Found 2/30 approved changesets -- score normalized to 0 |
Використані вхідні дані
| merged_prs | 5 |
| open_issues | 1 |
| closed_issues | 4 |
| issue_closed_ratio | 0,8 |
| closed_unmerged_prs | 0 |
Власність та опіка
53Помірний
Як обчислюється оцінка
| 10/30 | Підтримка власника — особистий (користувацький) обліковий запис |
| 0/20 | Верифікований домен — не застосовно до користувацьких облікових записів |
| 9.5/25 | Охоплення власника — 20 підписників у rmovva |
| 23.2/25 | Послужний список — 33 публічних репозиторіїв, вік облікового запису ~10 р. |
Використані вхідні дані
| followers | 20 |
| owner_type | User |
| is_verified | — |
| owner_login | rmovva |
| public_repos | 33 |
| account_age_days | 3 814 |
Виключено з оцінювання (немає даних або не застосовно): Верифікований домен. Залишкові ваги перенормовано.
Супровід пакетів
100Відмінний
Як обчислюється оцінка
| 25/25 | Опубліковано й доступно — 1 пакет(ів) у pypi |
| 35/35 | Свіжість публікацій — остання публікація 24 дн. тому |
| 20/20 | Історія версій — 13 опублікованих версій |
| 20/20 | Не застарілий — активний, не deprecated і не yanked |
Використані вхідні дані
| packages | hypothesaes |
| ecosystems | pypi |
| any_deprecated | ні |
| min_days_since_publish | 24 |
Інженерна якість
Чи наявні базові інженерні практики та документація?
44
Інженерні практики
24Критичний
Як обчислюється оцінка
| 0/24 | Процеси CI |
| 24/24 | Наявні тести |
| 0/16 | Конфігурація лінтера |
| 0/9.6 | Pre-commit-хуки |
| 0/6.4 | .editorconfig |
| 0/20 | OpenSSF Scorecard: CI-Tests — 0 out of 3 merged PRs checked by a CI test -- score normalized to 0 |
Використані вхідні дані
| has_ci | ні |
| has_tests | так |
| has_editorconfig | ні |
| has_linter_config | ні |
| has_precommit_config | ні |
Документація
75Добрий
Як обчислюється оцінка
| 30/30 | README |
| 0/25 | Каталог документації |
| 15/15 | Сайт документації / домашня сторінка — https://hypothesaes.org |
| 10/10 | Опис репозиторію |
| 10/10 | Теми — 6 тем |
| 10/10 | Wiki |
Використані вхідні дані
| topics | ai-for-science, computational-social-science, interpretability, nlp, sparse-autoencoders, topic-modeling |
| has_wiki | так |
| homepage | https://hypothesaes.org |
| has_readme | так |
| has_docs_dir | ні |
| has_description | так |
Безпека
Чи міцні видимі практики безпеки й ланцюга постачання, без непослабленої пов’язаності з юрисдикціями високого ризику?
43
Стан безпеки
29Критичний
Як обчислюється оцінка
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 0/2.5 | CI-Tests — 0 out of 3 merged PRs checked by a CI test -- score normalized to 0 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 2/30 approved changesets -- score normalized to 0 |
| 0.8/2.5 | Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
| 0/10 | Dangerous-Workflow — немає даних |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | Ліцензія — license file detected |
| 2.2/7.5 | Maintained — 3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3 |
| 0/5 | Packaging — немає даних |
| 0/5 | Pinned-Dependencies — немає даних |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — немає даних |
| 0/7.5 | Token-Permissions — немає даних |
| 7.5/7.5 | Vulnerabilities — 0 existing vulnerabilities detected |
Використані вхідні дані
| source | openssf_scorecard |
| checks_evaluated | 13 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 5 |
| scorecard_aggregate | 2,9 |
Виключено з оцінювання (немає даних або не застосовно): dangerous_workflow, packaging, pinned_dependencies, signed_releases, token_permissions. Залишкові ваги перенормовано.
Сповіщення про залежності
100Відмінний
Як обчислюється оцінка
| 35/35 | Прямі залежності без відомих сповіщень — жодна пряма залежність не має відомих сповіщень |
| 25/25 | Непрямі залежності без відомих сповіщень — жодна непряма залежність не має відомих сповіщень |
| 0/40 | Немає задавнених сповіщень — жодне сповіщення не має дати публікації |
Використані вхідні дані
| source | osv |
| advisories | 0 |
| affected_packages | 0 |
| assessed_packages | 145 |
| unassessed_packages | 0 |
| affected_by_severity | none |
| direct_affected_packages | 0 |
Виключено з оцінювання (немає даних або не застосовно): Немає задавнених сповіщень. Залишкові ваги перенормовано. Звірено з runtime-замиканням залежностей pypi:hypothesaes@2.0.1 — тим, що тягне за собою встановлення опублікованого пакета, — 145 пакетів. Досяжність не аналізується.
Готовність до ШІ
Наскільки репозиторій оснащений для розробки та супроводу за участі ШІ-агентів? Незалежний, експериментальний бейдж — вага 0.0, тож він подається окремо і не впливає на загальний індекс здоров'я.
24
Контекст і настанови для агентів
2Критичний
Як обчислюється оцінка
| 0/45 | Інструкції для агентів — немає CLAUDE.md / AGENTS.md / правил редактора |
| 0/15 | Машиночитана документація (llms.txt) |
| 2.1/40 | Читабельна історія комітів — намір зазначено у 4 з 100 людських комітів (структурований заголовок або пояснювальний текст) |
Використані вхідні дані
| has_llms_txt | ні |
| legible_history_share | 0,04 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Як обчислюється оцінка
| 0/18 | Розгортання однією командою |
| 22/22 | Автоматизовані тести |
| 0/11 | Конфігурація лінтера / форматера |
| 0/11 | Статична перевірка типів |
| 0/10 | Відтворюване середовище |
| 0/10 | Підтверджена практика роботи з агентами — серед останніх 100 комітів немає створених агентом |
| 0/8 | Автоматизоване супроводження — автоматичних оновлень залежностей не виявлено |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — немає даних |
Використані вхідні дані
| has_nix | ні |
| has_tests | так |
| lockfiles | — |
| has_dockerfile | ні |
| typed_language | ні |
| bootstrap_files | — |
| has_devcontainer | ні |
| has_linter_config | ні |
| typecheck_configs | — |
| agent_commit_share | 0 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Виключено з оцінювання (немає даних або не застосовно): OpenSSF Scorecard: Pinned-Dependencies. Залишкові ваги перенормовано.
Читабельність коду для моделей
55Помірний
Як обчислюється оцінка
| 0/45 | Типізований код — Jupyter Notebook без конфігурації перевірки типів |
| 55/55 | Керовані розміри файлів — 0/19 файлів вихідного коду понад 60 КБ |
Використані вхідні дані
| primary_language | Jupyter Notebook |
| largest_source_bytes | 21 515 |
| source_files_sampled | 19 |
| oversized_source_files | 0 |
Машиночитні інтерфейси
40У зоні ризику
Як обчислюється оцінка
| 0/40 | Схема API (OpenAPI/GraphQL/proto) |
| 0/20 | Сервер MCP |
| 40/40 | Придатні до запуску приклади — notebooks |
Використані вхідні дані
| example_dirs | notebooks |
| has_mcp_signal | ні |
| api_schema_files | — |
Ключові факти
91зірок GitHub
3контриб'юторів
50комітів за останні 12 місяців
3днів від останнього пушу
7релізів
1бас-фактор
1відкритих issue
PyPIпакетних екосистем
Попередження щодо збору даних
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
Докладніше
Історія зірок і форків 0 ★ / 28 ⇿
0Зірки
28Форки
7Релізи
Коли додано кожну зірку й форк — зібрано з GitHub і згруповано за днями. Кумулятивне зростання розміщено просто над денними додаваннями, з яких воно складається, тож їх видно одне проти одного: рівномірне органічне накопичення виглядає зовсім інакше, ніж різкий короткочасний сплеск. Там, де цю різницю можна виміряти, її подано як автентичність росту.
Мажорні 2Мінорні 4Патчі 1
Кожна точка охоплює 2 днів.
OpenSSF Scorecard 2.9 / 10
2.9сукупно
Незалежна, не прив'язана до інструментів оцінка безпеки від відкритого проєкту OpenSSF Scorecard. Кожна перевірка винагороджує практику безпеки, а не інструмент конкретного постачальника. Перевірки, які Scorecard не зміг визначити, позначено н/д і виключено з оцінки безпеки (вони ніколи не зараховуються як нуль).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| 0 | CI-Tests | 0 out of 3 merged PRs checked by a CI test -- score normalized to 0 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 2/30 approved changesets -- score normalized to 0 |
| 3 | Contributors | project has 1 contributing companies or organizations -- score normalized to 3 |
| н/д | Dangerous-Workflow | no workflows found |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 3 | Maintained | 3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3 |
| н/д | Packaging | packaging workflow not detected |
| н/д | Pinned-Dependencies | no dependencies found |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| н/д | Signed-Releases | no releases found |
| н/д | Token-Permissions | No tokens found |
| 10 | Vulnerabilities | 0 existing vulnerabilities detected |
Усі залежності 17
Повний розв'язаний набір залежностей із графа залежностей GitHub: 0 прямих і 17 непрямих (транзитивних) пакетів. Транзитивне замикання є повним, коли в репозиторії закомічено lockfile.
| Реєстр | Пакет | Версія | Зв'язок |
|---|---|---|---|
| PyPI | accelerate | — | непряма |
| PyPI | jmespath | — | непряма |
| PyPI | jupyter | — | непряма |
| PyPI | matplotlib | — | непряма |
| PyPI | numpy | — | непряма |
| PyPI | openai | — | непряма |
| PyPI | pandas | — | непряма |
| PyPI | pytest | — | непряма |
| PyPI | scikit-learn | — | непряма |
| PyPI | scipy | — | непряма |
| PyPI | sentence-transformers | — | непряма |
| PyPI | setuptools | — | непряма |
| PyPI | statsmodels | — | непряма |
| PyPI | tiktoken | — | непряма |
| PyPI | torch | — | непряма |
| PyPI | tqdm | — | непряма |
| PyPI | transformers | — | непряма |
Сповіщення про залежності 0
Встановлення pypi:hypothesaes@2.0.1 тягне 145 пакетів, прямих і транзитивних: 0 мають відомі сповіщення, з них 0 — прямі залежності.
Жодне відоме сповіщення не стосується оцінених залежностей.
Сповіщення означає, що версія, записана в графі залежностей, потрапляє в уражений діапазон. Досяжність не аналізується, а граф містить піниї розробки й тестування — знахідка може стосуватися інструментів, а не поставленого коду.
Звіт у форматі JSON машиночитний
{
"data": {
"repo": {
"topics": [
"ai-for-science",
"computational-social-science",
"interpretability",
"nlp",
"sparse-autoencoders",
"topic-modeling"
],
"is_fork": false,
"size_kb": 17296,
"has_wiki": true,
"homepage": "https://hypothesaes.org",
"languages": {
"Python": 134111,
"Jupyter Notebook": 2052287
},
"pushed_at": "2026-07-24T00:08:27Z",
"created_at": "2025-03-12T19:09:33Z",
"owner_type": "User",
"updated_at": "2026-07-24T00:08:32Z",
"description": "HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382",
"is_archived": false,
"is_disabled": false,
"license_spdx": "Apache-2.0",
"default_branch": "main",
"license_spdx_raw": "Apache-2.0",
"primary_language": "Jupyter Notebook",
"significant_languages": [
"Jupyter Notebook"
]
},
"owner": {
"blog": "www.rajivmovva.com",
"name": "Raj Movva",
"type": "User",
"login": "rmovva",
"company": "UC Berkeley",
"location": null,
"followers": 20,
"avatar_url": "https://avatars.githubusercontent.com/u/17256372?v=4",
"created_at": "2016-02-15T17:45:41Z",
"is_verified": null,
"public_repos": 33,
"account_age_days": 3814
},
"license": {
"state": "standard",
"spdx_id": "Apache-2.0",
"raw_spdx": "Apache-2.0",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v2.0.1",
"kind": "patch",
"published_at": "2026-07-02T18:10:43Z"
},
{
"tag": "v2.0.0",
"kind": "major",
"published_at": "2026-03-08T01:04:17Z"
},
{
"tag": "v1.1.0",
"kind": "minor",
"published_at": "2025-10-29T22:48:12Z"
},
{
"tag": "v1.0.0",
"kind": "major",
"published_at": "2025-09-15T22:54:41Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2025-07-29T06:52:17Z"
},
{
"tag": "v0.2.0",
"kind": "minor",
"published_at": "2025-05-04T01:34:29Z"
},
{
"tag": "v0.1.0",
"kind": "minor",
"published_at": "2025-04-22T20:41:16Z"
}
],
"recent_commits": [
{
"oid": "706d8979c71befe8e3151f51a8d4dbf87d4d7e41",
"body": "…nality (#12)\n\n* Updated separation score metric\n* Adding additional annotation funtionality",
"is_bot": false,
"headline": "Updated separation score metric & added additional annotation functio…",
"author_name": "adityad2123",
"author_login": "adityad2123",
"committed_at": "2026-07-24T00:08:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dff36e4b6aefa16f47ac3bf82a5838395bd144c4",
"body": null,
"is_bot": false,
"headline": "Bump version: 2.0.1",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2026-07-02T18:10:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4573abd87482ad3f02f850e0ca38897cac3e699b",
"body": null,
"is_bot": false,
"headline": "Fix interpretation precision metric",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2026-05-25T23:27:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "36d012d65ea46a98c7778b4002acf01ee64f628f",
"body": "* migrate llm client to responses api with openai-compatible base url\n\n* unify annotation and interpretation on api-based llm inference\n\n* update docs and tests for openai-compatible local endpoint flow\n\n* clarify local quickstart notebook note for unified api path\n\n* set uncapped token defaults and\n[…]\nble high matmul precision for local embeddings\n\n* Make vLLM optional for main install\n\n* Run through of local notebook using vLLM server\n\n* Remove in-process vLLM inference path\n\n* Bump version: 2.0.0",
"is_bot": false,
"headline": "2.0.0: unify local LLM support on OpenAI-compatible serving (#11)",
"author_name": "Raj Movva",
"author_login": "rmovva",
"committed_at": "2026-03-08T01:04:17Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a97898986e2e650dd1a9d186bbc3953d928c5ca2",
"body": null,
"is_bot": false,
"headline": "Update Python badge range",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:59:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0e4098bd4cd47f07ab5cac8d328c00a741e7d7d2",
"body": null,
"is_bot": false,
"headline": "Ignore agent guide file",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:53:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "10def8e108fdd5d2e0811ad0747ad158730143e6",
"body": null,
"is_bot": false,
"headline": "Bump version: 1.1.0",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:48:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a43671a256545fd553c8e566832838cbb131793b",
"body": null,
"is_bot": false,
"headline": "shutdown vLLM engine after testing",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:45:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1387a3082b398ca1b13708c6292f62e6ef803c74",
"body": "….14 currently doesn't work)",
"is_bot": false,
"headline": "Make tests more robust / fix bugs; allow Python versions 3.10-3.13 (3…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:21:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dcd3ab91e6b749bfc7647842b2028c6ec2c81f9f",
"body": "…ations",
"is_bot": false,
"headline": "Increment version to 1.0.0; remove support for get_multiple_sae_activ…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-15T22:54:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4d8be7369ff0103dc19f1085ca496f5c363613d1",
"body": null,
"is_bot": false,
"headline": "Document Batch Top-K activation function + add to quickstart",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-15T22:23:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "00c9e3fb8db7f1a9d27887989614ec1c872f25b6",
"body": null,
"is_bot": false,
"headline": "Add option to use BatchTopK instead of TopK",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-15T21:52:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4e1dbc5ece17f6b2efa00dcd6762e4d232882d60",
"body": null,
"is_bot": false,
"headline": "add bair commons notice",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-10T22:26:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c894c82d0d010afd54b8ca26c317f10e5b91c44f",
"body": null,
"is_bot": false,
"headline": "Bump version: 0.3.1",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T05:32:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1e0d7e9f43213af2ba49c2741a61c0825404e109",
"body": null,
"is_bot": false,
"headline": "Update quickstart nb",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T05:27:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "39ae7af15cd56338bd9fe771bded68b4714ced3d",
"body": null,
"is_bot": false,
"headline": "Fix Python versioning (currently <3.13 due to scipy bug)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T04:38:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "22a756dbf71906462dcef1e67600a5ebe8d9771b",
"body": null,
"is_bot": false,
"headline": "Cache prompts to avoid reloading prompt file",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T04:37:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "766e37142b007af7eb601eb3d578aa29b3eb58ce",
"body": null,
"is_bot": false,
"headline": "Store OpenAI client as a global to avoid re-initializing it",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T04:29:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f364a0982a7fe5bdbe60082f6584869241cde95b",
"body": null,
"is_bot": false,
"headline": "Fix bug in computing neuron prevalences",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-28T07:02:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "25279cb8e06551a36ad6294702e38156bc494c8c",
"body": null,
"is_bot": false,
"headline": "README FAQ: rate limits + privacy",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-14T17:59:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d0c959dcddbbdb6dd3f30399fee03a31d7065137",
"body": null,
"is_bot": false,
"headline": "Update README FAQ",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-14T17:49:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "06baeb1cf3e07170bd9e5bfebebca7ba6edc5bbc",
"body": null,
"is_bot": false,
"headline": "Add jmespath dependency for transformers/vllm",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-14T03:44:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2955fbe1a87c8f1ab42c9fe6bad43bd13ae4264",
"body": null,
"is_bot": false,
"headline": "include reasoning_effort param for gpt-5",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-10T06:23:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d158297f84433f076bdf512b76826341f48293ae",
"body": null,
"is_bot": false,
"headline": "Specify python version <= 3.12 (3.13 causes conflicts)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-10T05:52:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b91425adb98fe22b818533a8f0c42a8c38242bc0",
"body": "…ity code to allow kwargs",
"is_bot": false,
"headline": "Set gpt-4.1-mini to default completion model; cleanup surface similar…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-06T00:38:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "22fb957862c503edd36ca121378574da5b3f9b01",
"body": "Add torch device param to SAE constructor",
"is_bot": false,
"headline": "Allow torch.device selection (#7)",
"author_name": "Andre Shportko",
"author_login": "Antebe",
"committed_at": "2025-08-06T00:34:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "67c5a4e408dc3b96f0e0eeae4fe9a682e63df7e9",
"body": "…d OOM",
"is_bot": false,
"headline": "Move vLLM loading *after* embedding computation in quickstart to avoi…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-31T21:16:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bb10034a86fe89e26afc45e6129409ff0cee0ab2",
"body": "… is >0), and print prevalence",
"is_bot": false,
"headline": "support interpreting top N neurons ranked by prevalence (how often it…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-30T18:25:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a497503b1e0881dab6fd7c8ef49fabc2c65f4e52",
"body": null,
"is_bot": false,
"headline": "Fix directory name in quickstart",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T07:00:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fd9a5ec359998220307856697ae2159caea4985a",
"body": null,
"is_bot": false,
"headline": "Rename data & experiments directories",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T07:00:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "309443c0834ee9ceee653dd525f4d7c5c174d96d",
"body": "Support local LLM use for neuron interpretation and concept annotation",
"is_bot": false,
"headline": "Merge pull request #6 from rmovva/llmlocal",
"author_name": "Raj Movva",
"author_login": "rmovva",
"committed_at": "2025-07-29T06:52:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "491d9686f25bf92088b2f7a0b6b11473a266c75d",
"body": null,
"is_bot": false,
"headline": "Bump version: 0.3.0",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T06:48:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2923de09bada6bb8d2b2c324f0e2eeec11ef281",
"body": null,
"is_bot": false,
"headline": "Substantial README cleanup",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T02:17:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55814505a936e7434ffc12b0f412d2b21f8c5d8d",
"body": null,
"is_bot": false,
"headline": "Docs cleanup",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T01:48:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "85a36dd51d82d70b6830658d1aa417f64039dbfe",
"body": null,
"is_bot": false,
"headline": "Cleanup/finalize local LLM benchmarking results",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T01:35:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4b9ca159ad3770b63a75025461de58dde2d54f1c",
"body": null,
"is_bot": false,
"headline": "Correct sampling params for 'o*' models",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T01:35:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "adb774cdf12c2326d7fb0ee93f6d83642009ee3e",
"body": null,
"is_bot": false,
"headline": "Add some notes about vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T22:56:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2401a4ae6c3cbe0e3846835f360ffeb3774b6e1a",
"body": null,
"is_bot": false,
"headline": "Fix imports",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T16:40:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "56c9751d59fb80dc7b935a5bb3380782070f4d6f",
"body": null,
"is_bot": false,
"headline": "Update run through of detailed_usage notebok",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T16:39:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55af8983f7631c3a8bd97f892628fc94f5034b6f",
"body": null,
"is_bot": false,
"headline": "Update README",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:50:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0c8ee0079c9932cc86efa9aa154b4ed595d3ca0e",
"body": null,
"is_bot": false,
"headline": "Re-run quickstart with refactored code.",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:36:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e39e5a854d024d4d1809638d0b8c29481fab687c",
"body": null,
"is_bot": false,
"headline": "Edit \"sae_source_info\" code",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:31:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5a2c34dd1806c62511f9f80e210b47ce1b5a6a66",
"body": "…om 4o)",
"is_bot": false,
"headline": "Change quickstart default OpenAI models to gpt-4.1 / gpt-4.1-mini (fr…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:03:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9959d0973d97fd290d0faa7b05ad7bcce2d9fb7c",
"body": null,
"is_bot": false,
"headline": "fix tokenizer_kwargs",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T05:47:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "de22ee0662a2c69efdb352a5822332d34bdc4e61",
"body": null,
"is_bot": false,
"headline": "Fix bug where openAI models are not loaded in vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T05:43:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c6c28ed5d4867809c966ad37dcef3881abe2187c",
"body": null,
"is_bot": false,
"headline": "push quickstart nb for local LLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T04:51:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "390cf8be6aa416e068a6c6332d00c15a04d28e4a",
"body": null,
"is_bot": false,
"headline": "Change names",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:37:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4790181ad0ac90e72196bca7007bbe73175a25bf",
"body": null,
"is_bot": false,
"headline": "Change vLLM func to get_vllm_engine",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:36:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6d90b4c05da2e63d448babce21063aa64043d4d2",
"body": null,
"is_bot": false,
"headline": "Set default tokens for thinking-style generations to 8192",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:35:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ed7137d441f3f72585ee409db1c9806829c11de3",
"body": "…or vLLM)",
"is_bot": false,
"headline": "Manually pass through progress_desc to parallel_annotate (can't use f…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:35:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a4222953dbf34df3d34da16c03025e11d8c9c873",
"body": null,
"is_bot": false,
"headline": "Clear embedding model from GPU memory after embeddings are generated",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T23:38:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e0182b9de0c519ac7d4b455cd318f5ed97d9ccf1",
"body": "…_sae()",
"is_bot": false,
"headline": "Remove extraneous annotator model parameter from quickstart.interpret…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T23:37:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ddb02815c6aa760db4a68211fcc28d689fca6610",
"body": null,
"is_bot": false,
"headline": "Bugfix (prompt_template_name --> annotate_prompt_name)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T22:42:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "403b220d6b6e97eab50d291a6e2537e085655d41",
"body": null,
"is_bot": false,
"headline": "Removing annot caching from benchmarking script",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T22:36:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "75d176848e388a8feec4a25d8be0db4397054fc5",
"body": null,
"is_bot": false,
"headline": "Refactor local bencmarking annot/interp code a bit",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T22:33:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2c7896ee408247809958c518d5022c9f59047b09",
"body": null,
"is_bot": false,
"headline": "Push autointerp result figures",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-25T05:25:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7e556238749f7ec56d9981252cd6a467e77d5bb5",
"body": null,
"is_bot": false,
"headline": "Add script to score interp fidelities",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T17:10:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cbac0d1360146e285a26a52f198b516a7ec217b3",
"body": null,
"is_bot": false,
"headline": "Rename variables for clearer kwargs",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T17:08:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "19a68c58823b6f3fc4d6cf3abdf0530560e92bd1",
"body": null,
"is_bot": false,
"headline": "Clarify the prompt_template variables to disambiguate interp/annotatoin",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T17:03:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "01e5df4c3d8624441d6431c8ae8b12321085336b",
"body": null,
"is_bot": false,
"headline": "Fix: select same neurons for every model for interp experiment",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T05:50:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c33b0a16d8e914a57b6564b7582eda95181e2025",
"body": null,
"is_bot": false,
"headline": "Update interpretation benchmarking script",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T05:40:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4fe764adbc1dbcb365ff9bed0e21a7a277bd9eb2",
"body": null,
"is_bot": false,
"headline": "fix bug: temperature=None doesn't work for vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T04:51:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6dc2dd984b5cc0f84f39bc8dbff98d60d3238204",
"body": "…rams for vLLM",
"is_bot": false,
"headline": "Slight refactor to handling of temperature / max tokens / sampling pa…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T23:57:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3be7e4b63c9b30996e1377f6fb5d4ae015945865",
"body": null,
"is_bot": false,
"headline": "working on README update",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T23:57:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3bbc17be0f6de9723f6ea0e8d1086ae1252872e5",
"body": null,
"is_bot": false,
"headline": "Change defaults to 4.1/4.1-mini for openai",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T21:51:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ef614675f23a49a4af3eb6c31996d5c8c30357f7",
"body": null,
"is_bot": false,
"headline": "Skip \"None\" interpretations from scoring",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T21:41:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7d770a9930f3fae1443333c634b7054f07ec9598",
"body": null,
"is_bot": false,
"headline": "Edit prompts, reduce example count",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T19:00:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a4cb4e6c073eda6994fe080d417f44d1a634cce0",
"body": null,
"is_bot": false,
"headline": "Fix interp prompt for test, use more thinking tokens",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T18:18:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "33a5eefeae02b5bbc6853ad9762b07d1a01a7347",
"body": "…erp samples",
"is_bot": false,
"headline": "Use different random seed for each interpretation candidate's autoint…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T18:18:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f3cd87fa3d4a8fb822c41474c399b57f4a0bf9de",
"body": "…o think more concisely",
"is_bot": false,
"headline": "Fix parsing of thinking outputs; add new prompt to encourage models t…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T18:03:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4f5265cbcb12aaa6bf514fb715de77a16e20422f",
"body": null,
"is_bot": false,
"headline": "Fix bug in parsing autointerps from models with <think> tags",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T17:41:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "973abd7d312db64dd6e5087d36a7398279476989",
"body": null,
"is_bot": false,
"headline": "more local LLM testing code for interpretations now",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T06:16:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5141230a17c5e2cd12cc4d890bc376a2aaf65248",
"body": null,
"is_bot": false,
"headline": "fix bug for nomic embeddings",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T06:14:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d67d4ffb4dfe70c6dbe42bdc5a06de309298d645",
"body": null,
"is_bot": false,
"headline": "Pareto frontier of annotation quality vs. time taken",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:27:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8036bf2bc5c4dbd07676937222a1dd6a8ea9472a",
"body": null,
"is_bot": false,
"headline": "use enable_thinking=False in tests",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:26:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "071a931db0937966bf6a9dcdbeccb197f767093b",
"body": null,
"is_bot": false,
"headline": "Set default enable_thinking to False",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:26:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f80041fe728c0cb5147a4aca7e923f4d50a87ce4",
"body": null,
"is_bot": false,
"headline": "Add param to *only* draw from cached annotations",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:25:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1c9ec1b61372f92b343cfc68129db88f9279ce48",
"body": null,
"is_bot": false,
"headline": "Refactor interpret_neurons.py to work for local LLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:25:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "87ea5d87dfc69ebbc7954cf3af902321857ab3bd",
"body": null,
"is_bot": false,
"headline": "Push local experiments for annotation",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T17:45:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "85ddf5e7d34c5dfb7701f909d98204a6d5e0b76b",
"body": null,
"is_bot": false,
"headline": "Increase gpu util slightly",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T17:42:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "92d15441a692113dec2280f95e39cf1bc3c1665c",
"body": null,
"is_bot": false,
"headline": "Add bug note",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T03:01:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ca391403f5b724e86b580b4011eeeb26021253cf",
"body": "…b to local folder",
"is_bot": false,
"headline": "reset_prefix_cache() before sleeping (not fixing bug); Move testing n…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T02:59:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3b52bf8c5a6592aad9beccf451f1bd3e628ed194",
"body": null,
"is_bot": false,
"headline": "Rename max_new_tokens to max_tokens; allow flexible prompt choice",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T22:36:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cc5d62068886f15b9ae515653a81c942090bb24a",
"body": null,
"is_bot": false,
"headline": "Only show tqdm bar for vLLM inference (not for prompt processing)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T22:35:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "154d52ec7500a243270c85853faa9b06455c989f",
"body": null,
"is_bot": false,
"headline": "Fix sleeping + lower gpu-util to allow more models in memory",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T19:29:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "94769635a6e92f928cae7aa9982f2519cba6b51f",
"body": null,
"is_bot": false,
"headline": "Need enable_sleep_mode=True parameter for sleep to actually free memory.",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T18:16:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "eca27f7116a77862e77f9bc0b63c668cdba5b2c1",
"body": "…ory.",
"is_bot": false,
"headline": "Adding sleep mode functionality, so we can page models on/off GPU mem…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T18:04:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b39990d100626cb5632dbfb59ffc31fc28018832",
"body": null,
"is_bot": false,
"headline": "Update requirements.txt for vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T17:34:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1df65c46fb97d6943498495ad9d92e8ae1f372f1",
"body": null,
"is_bot": false,
"headline": "Simplify testing of local LLMs; assign 0 to missing local annotations",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T06:50:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7b4ce9b4a3c51ba48b7230661dd6f29bc449e5a6",
"body": null,
"is_bot": false,
"headline": "Cleanup annotate.py and _local_annotate() function",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T05:50:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2d71587a901d096de9c8d58891b2aa0b09a844a",
"body": null,
"is_bot": false,
"headline": "Make vLLM code more concise: getting completions + model init",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T05:26:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0ce45afe794a7257f3d92cad9226bc02ffc8be9f",
"body": null,
"is_bot": false,
"headline": "test qwen3 \"thinking\"",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-11T03:29:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6db71abf9b386dc9bef61a239f4d36059d434a86",
"body": null,
"is_bot": false,
"headline": "Some accuracy results comparing gemma-3-1b-it to gpt-4.1",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-11T03:09:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "640fbe420889f92defbaa3adaccf3b68e08f5cc6",
"body": null,
"is_bot": false,
"headline": "batched vLLM - still slow?",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T03:32:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "514b67bc6abf766fb096abd6cbde7b0506bcf127",
"body": null,
"is_bot": false,
"headline": "add model as explicit parameter to annotation functions",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T02:43:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "03613ddfb356fd84213cf190f6f8586541db7f5d",
"body": null,
"is_bot": false,
"headline": "add temporary profiling script",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T02:11:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c48efbc6c72422bb1e8c7cd4cbab9e98ca5ae20a",
"body": null,
"is_bot": false,
"headline": "fix argument bug - duplicated progress_desc",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T02:11:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "440291a391c02d74d811ecc5ad9b06568dd070bd",
"body": "…ists on HF before loading.",
"is_bot": false,
"headline": "Tests passing for gemma3 models; fix tqdm progress; check if model ex…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-08T06:44:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4870e53582e5bb08c9959a4186d5b84de784a71b",
"body": null,
"is_bot": false,
"headline": "Unit tests for local LLMs",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-08T05:22:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d71c5977742959a7efb62fd2b835cf2b5720df08",
"body": null,
"is_bot": false,
"headline": "Local LLM annotation: Fix pipeline batching / improve performance",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-07T23:12:50Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 7,
"commits_last_year": 50,
"latest_release_at": "2026-07-02T18:10:43Z",
"latest_release_tag": "v2.0.1",
"releases_from_tags": true,
"days_since_last_push": 3,
"active_weeks_last_year": 11,
"days_since_latest_release": 24,
"mean_days_between_releases": 72.6
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": false,
"health_percentage": 42,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "hypothesaes",
"exists": true,
"license": null,
"keywords": [
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3"
],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/hypothesaes/",
"is_deprecated": false,
"latest_version": "2.0.1",
"repository_url": "https://github.com/rmovva/HypotheSAEs",
"versions_count": 13,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": 240,
"first_published_at": "2025-03-16T05:38:41.099368Z",
"latest_published_at": "2026-07-02T18:10:54.071752Z",
"latest_version_yanked": null,
"days_since_latest_publish": 24
}
]
},
"popularity": {
"forks": 28,
"stars": 91,
"watchers": 2,
"fork_history": {
"days": [
{
"date": "2025-04-08",
"count": 1
},
{
"date": "2025-06-08",
"count": 1
},
{
"date": "2025-06-12",
"count": 1
},
{
"date": "2025-07-14",
"count": 1
},
{
"date": "2025-07-22",
"count": 1
},
{
"date": "2025-08-01",
"count": 1
},
{
"date": "2025-08-04",
"count": 1
},
{
"date": "2025-08-09",
"count": 1
},
{
"date": "2025-09-01",
"count": 1
},
{
"date": "2025-09-04",
"count": 1
},
{
"date": "2025-09-06",
"count": 1
},
{
"date": "2025-09-09",
"count": 1
},
{
"date": "2025-09-25",
"count": 1
},
{
"date": "2025-09-29",
"count": 1
},
{
"date": "2025-10-11",
"count": 1
},
{
"date": "2025-10-21",
"count": 1
},
{
"date": "2025-10-25",
"count": 1
},
{
"date": "2025-11-07",
"count": 1
},
{
"date": "2025-11-27",
"count": 1
},
{
"date": "2025-12-21",
"count": 1
},
{
"date": "2026-01-11",
"count": 1
},
{
"date": "2026-01-12",
"count": 1
},
{
"date": "2026-02-02",
"count": 1
},
{
"date": "2026-02-12",
"count": 1
},
{
"date": "2026-05-13",
"count": 1
},
{
"date": "2026-05-31",
"count": 1
},
{
"date": "2026-06-11",
"count": 1
},
{
"date": "2026-07-13",
"count": 1
}
],
"complete": true,
"collected": 28,
"total_forks": 28
},
"star_history": null,
"open_issues_and_prs": 3
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"notebooks"
],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [],
"largest_source_bytes": 21515,
"source_files_sampled": 19,
"oversized_source_files": 0,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [
"pyproject.toml",
"requirements.txt"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 145,
"malicious_count": 0,
"assessed_package": "pypi:hypothesaes@2.0.1",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"pypi"
],
"dependencies": [],
"all_dependencies": {
"error": null,
"source": "github-sbom",
"packages": [
{
"name": "accelerate",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "jmespath",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "jupyter",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "matplotlib",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "numpy",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "openai",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pandas",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pytest",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "scikit-learn",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "scipy",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "sentence-transformers",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "setuptools",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "statsmodels",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "tiktoken",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "torch",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "tqdm",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "transformers",
"direct": false,
"version": null,
"ecosystem": "pypi"
}
],
"collected": true,
"truncated": false,
"total_count": 17,
"direct_count": 0,
"indirect_count": 17
}
},
"maintainership": {
"issues": {
"open_prs": 2,
"merged_prs": 5,
"open_issues": 1,
"closed_ratio": 0.8,
"closed_issues": 4,
"closed_unmerged_prs": 0
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "rmovva",
"commits": 148,
"avatar_url": "https://avatars.githubusercontent.com/u/17256372?v=4"
},
{
"type": "User",
"login": "Antebe",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/54448351?v=4"
},
{
"type": "User",
"login": "adityad2123",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/76717200?v=4"
}
],
"contributors_sampled": 3,
"top_contributor_share": 0.987
},
"quality_signals": {
"has_ci": false,
"has_tests": true,
"ci_workflows": [],
"has_docs_dir": false,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 0,
"reason": "0 out of 3 merged PRs checked by a CI test -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 0,
"reason": "Found 2/30 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": null,
"reason": "no workflows found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 3,
"reason": "3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": null,
"reason": "no dependencies found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": null,
"reason": "No tokens found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 10,
"reason": "0 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "706d8979c71befe8e3151f51a8d4dbf87d4d7e41",
"ran_at": "2026-07-27T13:12:18Z",
"aggregate_score": 2.9,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-24T00:08:28Z",
"oldest_open_prs": [
{
"number": 9,
"created_at": "2025-08-06T23:54:25Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 10,
"created_at": "2026-01-05T16:42:23Z",
"last_comment_at": null,
"last_comment_author": null
}
],
"last_merged_pr_at": "2026-07-24T00:08:27Z",
"ci_last_conclusion": null,
"oldest_open_issues": [
{
"number": 5,
"created_at": "2025-06-14T23:00:24Z",
"last_comment_at": "2026-01-05T16:29:45Z",
"last_comment_author": "Treasure-Mayowa"
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/rmovva/HypotheSAEs",
"host": "github.com",
"name": "HypotheSAEs",
"owner": "rmovva"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 53,
"inputs": {
"security": 43,
"vitality": 69,
"community": 45,
"governance": 57,
"engineering": 44
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "moderate",
"name": "Vitality",
"value": 69,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "moderate",
"name": "Development activity",
"note": null,
"notes": [],
"value": 62,
"inputs": {
"commits_last_year": 50,
"human_commit_share": 1,
"days_since_last_push": 3,
"active_weeks_last_year": 11
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 3 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 3
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "11/52 weeks with commits",
"points": 7.6,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 11
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "50 commits in the last year",
"points": 15.3,
"status": "partial",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 50
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "good",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 80,
"inputs": {
"releases_count": 7,
"latest_release_tag": "v2.0.1",
"releases_from_tags": true,
"days_since_latest_release": 24,
"mean_days_between_releases": 72.6
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "7 version tags (no GitHub releases)",
"points": 16.2,
"status": "partial",
"details": [
{
"code": "version_tags_no_releases",
"params": {
"count": 7
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 24 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 24
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~72.6 days",
"points": 19.8,
"status": "partial",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 72.6
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "maintained",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": null,
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": 3,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "last human commit 3 days ago",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_maintained",
"params": {
"days": 3
}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "at_risk",
"name": "Community & Adoption",
"value": 45,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "at_risk",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 44,
"inputs": {
"forks": 28,
"stars": 91,
"watchers": 2,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "91 stars",
"points": 31.7,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 91
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "28 forks",
"points": 11.9,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 28
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "2 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 2
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "moderate",
"name": "Community health",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (Apache-2.0)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "Apache-2.0"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
},
{
"key": "ecosystem_adoption",
"band": "at_risk",
"name": "Ecosystem adoption (downloads)",
"note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"registry_dependents"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 40,
"inputs": {
"packages": [
"hypothesaes"
],
"dependents": null,
"ecosystems": "pypi",
"total_downloads": null,
"monthly_downloads": 240
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "240 downloads/month across pypi",
"points": 31.8,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 240,
"ecosystems": "pypi"
}
}
],
"max_points": 80
},
{
"key": "registry_dependents",
"name": "Registry dependents",
"detail": "not reported by this ecosystem",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_reported_by_this_ecosystem",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "moderate",
"name": "Sustainability & Governance",
"value": 57,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 16,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 3,
"top_contributor_share": 0.987
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 99% of commits",
"points": 0.3,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 99
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "3 contributors",
"points": 4.1,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 3
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "good",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 76,
"inputs": {
"merged_prs": 5,
"open_issues": 1,
"closed_issues": 4,
"issue_closed_ratio": 0.8,
"closed_unmerged_prs": 0
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "80% of issues closed",
"points": 37.4,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 80
}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "5/5 decided PRs merged",
"points": 38.2,
"status": "met",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 5,
"decided": 5
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 2/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 53,
"inputs": {
"followers": 20,
"owner_type": "User",
"is_verified": null,
"owner_login": "rmovva",
"public_repos": 33,
"account_age_days": 3814
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "personal (user) account",
"points": 10,
"status": "partial",
"details": [
{
"code": "owner_personal",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": "not applicable to user accounts",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_applicable_to_user_accounts",
"params": {}
}
],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "20 followers of rmovva",
"points": 9.5,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 20,
"login": "rmovva"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "33 public repos, account ~10 yr old",
"points": 23.2,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 33
}
},
{
"code": "account_age_years",
"params": {
"years": 10
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"hypothesaes"
],
"ecosystems": "pypi",
"any_deprecated": false,
"min_days_since_publish": 24
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on pypi",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "pypi"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 24 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 24
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "13 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 13
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "at_risk",
"name": "Engineering Quality",
"value": 44,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "critical",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 24,
"inputs": {
"has_ci": false,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "0 out of 3 merged PRs checked by a CI test -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"topics": [
"ai-for-science",
"computational-social-science",
"interpretability",
"nlp",
"sparse-autoencoders",
"topic-modeling"
],
"has_wiki": true,
"homepage": "https://hypothesaes.org",
"has_readme": true,
"has_docs_dir": false,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://hypothesaes.org",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": "6 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 6
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "at_risk",
"name": "Security",
"value": 43,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "critical",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Dangerous-Workflow, Packaging, Pinned-Dependencies, Signed-Releases, Token-Permissions. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"dangerous_workflow",
"packaging",
"pinned_dependencies",
"signed_releases",
"token_permissions"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 29,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 13,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 5,
"scorecard_aggregate": 2.9
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "0 out of 3 merged PRs checked by a CI test -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 2/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no workflows found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3",
"points": 2.2,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "no dependencies found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "No tokens found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "0 existing vulnerabilities detected",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "excellent",
"name": "Dependency advisories",
"note": "Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:hypothesaes@2.0.1 runtime dependency closure — what installing the published package pulls in — 145 packages. Reachability is not analyzed.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"no_advisories_left_outstanding"
]
}
},
{
"code": "weights_renormalized",
"params": {}
},
{
"code": "advisories_scope_published",
"params": {
"package": "pypi:hypothesaes@2.0.1",
"assessed": 145
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 100,
"inputs": {
"source": "osv",
"advisories": 0,
"affected_packages": 0,
"assessed_packages": 145,
"unassessed_packages": 0,
"affected_by_severity": "none",
"direct_affected_packages": 0
},
"components": [
{
"key": "direct_dependencies_free_of_known_advisories",
"name": "Direct dependencies free of known advisories",
"detail": "no direct dependency carries a known advisory",
"points": 35,
"status": "met",
"details": [
{
"code": "no_direct_advisories",
"params": {}
}
],
"max_points": 35
},
{
"key": "indirect_dependencies_free_of_known_advisories",
"name": "Indirect dependencies free of known advisories",
"detail": "no indirect dependency carries a known advisory",
"points": 25,
"status": "met",
"details": [
{
"code": "no_indirect_advisories",
"params": {}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory carries a publication date",
"points": 0,
"status": "excluded",
"details": [
{
"code": "advisories_no_publication_date",
"params": {}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "excellent",
"name": "Malicious dependencies",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"source": "osv",
"meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
"packages": [],
"red_flag": false,
"assessed_packages": 145,
"malicious_packages": 0,
"direct_malicious_packages": 0,
"withdrawn_malicious_packages": 0,
"installable_malicious_packages": 0
},
"components": [
{
"key": "no_dependency_reported_as_a_malicious_package",
"name": "No dependency reported as a malicious package",
"detail": "no dependency is reported as a malicious package",
"points": 100,
"status": "met",
"details": [
{
"code": "no_malicious_dependencies",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "critical",
"name": "AI Readiness",
"value": 24,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "critical",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 2,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.04,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "4 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 2.1,
"status": "partial",
"details": [
{
"code": "legible_history",
"params": {
"legible": 4,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "critical",
"name": "Verify loop (build / test / typecheck)",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_pinned_dependencies"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 24,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [],
"has_dockerfile": false,
"typed_language": false,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [],
"agent_commit_share": 0,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "no agent-authored commits among the last 100",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_authored_commits",
"params": {
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "no dependencies found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "moderate",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 55,
"inputs": {
"primary_language": "Jupyter Notebook",
"largest_source_bytes": 21515,
"source_files_sampled": 19,
"oversized_source_files": 0
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Jupyter Notebook without a type-check config",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_typecheck_config_language",
"params": {
"language": "Jupyter Notebook"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "0/19 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 19,
"oversized": 0
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "at_risk",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"example_dirs": [
"notebooks"
],
"has_mcp_signal": false,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": "notebooks",
"points": 40,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "notebooks"
}
}
],
"max_points": 40
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token"
],
"report_type": "repository",
"generated_at": "2026-07-27T13:12:30.788867Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/r/rmovva/HypotheSAEs.svg",
"full_name": "rmovva/HypotheSAEs",
"license_state": "standard",
"license_spdx": "Apache-2.0"
}Оцінки — це сигнали, а не гарантії. Вони відображають публічно видимі практики на GitHub — це не аудит коду й не гарантія безпеки.
Відсутні дані виключаються, а ваги перенормовуються — нуль за відсутність ніколи не ставиться. Методологія версіонована й відкрита: метрики v1.13.0, схема v0.27.0 — повна методологія · вікі метрик.
Як окремий результат виглядає на тлі всього реєстру: сукупна статистика — PyPI.