Context is Key: A Benchmark for Forecasting with Essential Textual Information
active 2024-10-16 → 2026-03-10 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 511 days from 2024-10-16 to 2026-03-10. Pushes: 69 total, peak 12 in a day. Pull requests: 27 total, peak 4 in a day. Issues: 24 total, peak 2 in a day. Comments: 64 total, peak 9 in a day. Stars: 74 total, peak 6 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 |
|---|---|---|---|---|
| ashok-arjun | 65 | 28 | 3 | 20 |
| aldro61 | 39 | 21 | 10 | 3 |
| AndrewRWilliams | 26 | 12 | 4 | 6 |
| korbit-ai[bot] | 21 | 0 | 0 | 18 |
| marcotet | 20 | 5 | 5 | 6 |
| nicolaschapados | 6 | 3 | 1 | 0 |
| BennyTMT | 5 | 0 | 0 | 3 |
| boranhan | 4 | 0 | 0 | 2 |
| jyanc | 2 | 0 | 0 | 0 |
| xiyuanzh | 2 | 0 | 0 | 1 |
| junwoopark92 | 2 | 0 | 0 | 1 |
| Gunnar-Stunnar | 2 | 0 | 0 | 1 |
| Dynamite2003 | 2 | 0 | 0 | 0 |
| ishaan-jaff | 2 | 0 | 1 | 1 |
| rottenivy | 2 | 0 | 2 | 0 |
| NielsRogge | 2 | 0 | 0 | 1 |
| ztb-35 | 1 | 0 | 0 | 0 |
| danielgweng | 1 | 0 | 1 | 0 |
| Caelyn-gao | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#32marcotet2026-01-30 19:06The prediction interface parameters of the chronos model have a problem; context should be changed to inputs.
- Issue#33Dynamite20032026-01-25 05:59Why not move "from cik_benchmark.baselines.timegen import timegen1" to experiment_timegen1?
- Issue#32Dynamite20032026-01-25 05:54The prediction interface parameters of the chronos model have a problem; context should be changed to inputs.
- Issue#30ashok-arjun2025-08-25 20:19[Train DualChronos on dateless CAF]
- Issue comment#21NielsRogge2025-08-08 17:58Release CiK (Context is Key) dataset on Hugging Face
- Issue comment#21marcotet2025-08-08 17:05Release CiK (Context is Key) dataset on Hugging Face
- Issue comment#21marcotet2025-08-08 16:32Release CiK (Context is Key) dataset on Hugging Face
- Issue#26BennyTMT2025-07-17 12:34Data Request
- Pull request#29marcotet2025-07-15 17:32
- Issue comment#26BennyTMT2025-07-15 15:20Data Request
- Issue comment#26marcotet2025-07-15 15:16Data Request
- Issue comment#29korbit-ai[bot]2025-07-15 15:11Update results post bug fix of the Causal tasks
- Issue comment#13AndrewRWilliams2025-07-11 20:08Add LiteLLM - support for Vertex AI, Gemini, Anthropic, Bedrock (100+LLMs)
- Pull request#13AndrewRWilliams2025-07-11 20:08
- Pull request#27AndrewRWilliams2025-07-11 20:06
- ReleaseAndrewRWilliams2025-07-11 19:46ICML 2025
- Issue comment#26BennyTMT2025-07-11 11:34Data Request
- Issue comment#26Caelyn-gao2025-07-11 06:16Data Request
- Pull request#28marcotet2025-07-09 17:05
- Issue comment#27AndrewRWilliams2025-07-02 20:40Causal task covariate normalization fix
- Issue comment#27marcotet2025-07-02 20:01Causal task covariate normalization fix
- Issue comment#27AndrewRWilliams2025-07-02 19:57Causal task covariate normalization fix
- Pull request#27AndrewRWilliams2025-07-02 18:59
- Issue comment#26BennyTMT2025-05-30 18:24Data Request
- Issue#26BennyTMT2025-05-28 23:31Data Request
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 74 stars here means stars gained during the window, not the repo's star count.