Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #8641

GIFT-Eval

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

MODELS · 1 SOURCE · Hugging Face

IBM publishes Granite timeseries ensemble recipe with probabilistic and IQR aggregation

IBM's Granite TSFM provides a permissively licensed ensemble recipe that combines four pre-trained Granite architectures to produce median and quantile forecasts without retraining or fitted ensemble weights. Two aggregation recipes are available — a default Probabilistic Ensemble (uniform probability pooling) and an IQR-based weighting variant — downloadable via Hugging Face and evaluated across 97 GIFT-Eval configurations with leaderboard scores captured on 20 October 2026.

6.0

MODELS · 1 SOURCE · Mistral AI

Mistral releases Timestral family of time-series foundation models (5M–209M params)

Mistral has released Timestral, a family of four time-series foundation models (5M, 28M, 123M, 209M parameters) that deliver probabilistic, multivariate forecasts, support past and known-future covariates, and are optimized for CPU inference. The 209M checkpoint ranks first among pretrained zero-shot entries on the GIFT-Eval, TIME and fev-bench leaderboards, and the family is trained using synthetic pre-training, covariate-aware attention, and long-context learning, with optional fine-tuning via Mistral Forge.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

TW3Cast: frozen router of lightly fine-tuned foundation models ranks #3 on GIFT‑Eval; artifacts released

TW3Cast is a time-series forecasting system that reached rank 3 of 130 on the GIFT‑Eval benchmark by mean MASE as of 2026‑09‑14. It uses no agents or language models: a routing table computed once on the training split (and then frozen) selects among four modes per dataset/configuration — specialists (LoRA or full fine-tunes of Chronos‑2, TiRex or Toto), quantile blends, blends of base models, or a selection tournament run on a backtest — with every decision taken on that training-split backtest. Three guard mechanisms (accuracy+calibration criterion, asymmetric margin for candidates that saw the series in training, and conservative per-window gates) limit selection bias. Reported mean MASE ranks: best base model 33.8, tournament 38.0, full router 19.4. The paper (arXiv:2609.28506v1) releases the routing table, expert index, pinned base-model revisions, score file and a dated snapshot of public scores plus a script to regenerate the leaderboard numbers.

7.0