Using Large Language Models for Time Series Anomaly Detection
active 2023-12-06 → 2026-05-02 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 879 days from 2023-12-06 to 2026-05-02. Pushes: 161 total, peak 15 in a day. Pull requests: 52 total, peak 3 in a day. Issues: 31 total, peak 2 in a day. Comments: 46 total, peak 10 in a day. Stars: 75 total, peak 5 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| sarahmish | 209 | 102 | 43 | 41 |
| Linh-nk | 45 | 33 | 8 | 0 |
| github-actions[bot] | 23 | 23 | 0 | 0 |
| abaranov25 | 5 | 3 | 1 | 0 |
| gonzo-opera | 4 | 0 | 0 | 1 |
| shahrokhvahabi | 4 | 0 | 0 | 3 |
| Qi2yU | 3 | 0 | 0 | 1 |
| vc1492a | 2 | 0 | 0 | 0 |
| kingminzhuang | 2 | 0 | 0 | 0 |
| nat-hu | 1 | 0 | 0 | 0 |
| kveerama | 1 | 0 | 0 | 0 |
| petteriTeikari | 1 | 0 | 0 | 0 |
| algomaschine | 1 | 0 | 0 | 0 |
| Aquariuaa | 1 | 0 | 0 | 0 |
| Rafael-sick | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#58sarahmish2026-05-02 19:55Bug fix in Float2Scalar
- Issue#56abaranov252026-02-08 21:50Add a New K-Means Binning Primitive
- Issue#55nat-hu2026-01-16 10:38Question about completeness of benchmark/paper-benchmark.csv
- Pull request#54abaranov252025-12-19 23:04
- Issue#53kveerama2025-12-10 19:10Can we make it configurable to be able to use any LLM model?
- Releasesarahmish2025-10-06 18:46v0.1.0 - 2025-10-06
- Pull request#50sarahmish2025-10-06 16:41
- Pull request#49sarahmish2025-09-12 02:30
- Pull request#46sarahmish2025-06-05 16:06
- Pull request#45sarahmish2025-06-03 15:40
- Pull request#45sarahmish2025-05-29 22:47
- Issue#43sarahmish2025-05-28 14:08Add parse list of intervals to ``parse_anomaly_response``
- Pull request#44sarahmish2025-05-28 14:08
- Pull request#44sarahmish2025-05-25 16:46
- Issue#36sarahmish2025-05-19 14:55Add benchmarking suite to `sigllm`
- Pull request#42sarahmish2025-05-19 14:55
- Pull request#39sarahmish2025-04-18 02:40
- Pull request#41sarahmish2025-04-14 16:22
- Issue#38kingminzhuang2025-04-14 13:51reproduce the experimental results
- Issue comment#40sarahmish2025-04-13 19:13Trying to reduce the run time for a single time series
- Pull request#42sarahmish2025-04-13 19:02
- Pull request#41sarahmish2025-04-11 23:38
- Issue#40gonzo-opera2025-04-03 20:01Trying to
- Issue comment#37gonzo-opera2025-04-03 19:59ValueError: not enough values to unpack (expected 3, got 1)
- Issue#37gonzo-opera2025-04-03 19:58ValueError: not enough values to unpack (expected 3, got 1)
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 75 stars here means stars gained during the window, not the repo's star count.