[ICLR 2026] An official implementation of "SIM-CoT: Supervised Implicit Chain-of-Thought"
active 2025-09-25 → 2026-05-17 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 235 days from 2025-09-25 to 2026-05-17. Pushes: 4 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 1 in a day. Comments: 10 total, peak 2 in a day. Stars: 68 total, peak 20 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 |
|---|---|---|---|---|
| Wiselnn570 | 10 | 4 | 0 | 6 |
| JuseonDo | 3 | 0 | 0 | 0 |
| montvid | 1 | 0 | 0 | 0 |
| krkawzq | 1 | 0 | 0 | 1 |
| epc314 | 1 | 0 | 0 | 0 |
| Arsiuuu | 1 | 0 | 0 | 0 |
| fpshuang | 1 | 0 | 0 | 0 |
| ZeroVector1201 | 1 | 0 | 0 | 1 |
| Oleg20502 | 1 | 0 | 0 | 1 |
| neerajgangwar | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#15epc3142026-05-17 03:19LLaMA3-CODI-8B HF checkpoint evaluates far below the reported GSM8K-Aug accuracy
- Issue#13fpshuang2026-04-08 10:32How to get decoded sequence from latent?
- Issue comment#11ZeroVector12012026-02-28 11:09Reproducing Llama3.2 1B results
- Issue comment#9Wiselnn5702026-02-09 11:30Reproducing CODI score
- Issue comment#6krkawzq2026-02-07 11:38Problems with CoT, Coconut, SIM-CoT training
- Issue comment#6Wiselnn5702026-02-02 02:34Problems with CoT, Coconut, SIM-CoT training
- Issue comment#6Oleg205022026-02-01 13:46Problems with CoT, Coconut, SIM-CoT training
- Issue comment#9Wiselnn5702026-01-27 08:11Reproducing CODI score
- Issue#9JuseonDo2026-01-27 05:26Reproducing CODI score
- Issue#8JuseonDo2026-01-14 07:02Question Regarding Reproducibility of SFT-CoT Performance
- Issue comment#7Wiselnn5702025-12-29 06:30Reproducing Results from Table 2 for Llama-1B
- Issue comment#7neerajgangwar2025-12-29 06:03Reproducing Results from Table 2 for Llama-1B
- Issue#8JuseonDo2025-12-21 17:27Question Regarding Reproducibility of SFT-CoT Performance
- Issue comment#6Wiselnn5702025-12-02 07:38Problems with CoT, Coconut, SIM-CoT training
- Issue comment#4Wiselnn5702025-11-26 05:55Hyperparameters for Coconut + SIM-CoT
- Issue#5Arsiuuu2025-11-10 04:48How to get analysis result in Figure 1?
- Issue#3montvid2025-10-25 12:35Instead of gpt2 train on nanochat
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 68 stars here means stars gained during the window, not the repo's star count.