cooc

kopei's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Artur-Melnyk/Market-Mood-Forecasting about 23 hours ago

Your output is already our submission format — a live record for the leakage-safe walk-forward

1

#1 opened about 23 hours ago by

kopei

New activity in ryousuf569/finbert-macro about 23 hours ago

Market-impact labeling is a directional forecast layer — want a scoreboard that settles it against real prices?

#1 opened about 23 hours ago by

kopei

New activity in yusufizzetmurat/fomc-rv-qlike-forecaster about 23 hours ago

Walk-forward conformal bands deserve a settlement counterparty — a live venue for the fed-pulse forecasters

#1 opened about 23 hours ago by

kopei

New activity in afzalur/Qwen-Market-Prediction-Model 2 days ago

Your model's output format is literally our submission schema — want a live scoreboard for it?

#1 opened 2 days ago by

kopei

New activity in Tjgguy12/forex-6pair-1d-quant 2 days ago

Publishing a negative-IC result and dated live tests is rarer than a good backtest — worth a third-party timestamp?

#1 opened 2 days ago by

kopei

New activity in DogInfantry/enso-macro-risk-desk 2 days ago

A desk that says "no trade" when the causal evidence is thin deserves a public forward record

#1 opened 2 days ago by

kopei

New activity in lucas-duartedelima/qwen2.5-7b-earnings-volatility-lora 4 days ago

Your thesis model reads the CEO and outputs a number — a forward-only scoreboard is the evidence chapter it can't have yet

#1 opened 4 days ago by

kopei

New activity in karkar69/chronos-volatility 4 days ago

Your model already speaks in quantiles — CRPS-scored live questions are the native venue for q10/q50/q90

#1 opened 4 days ago by

kopei

New activity in minusquare/asset-price-forecasting 4 days ago

You spotted the lag-50 "improvement" as overfitting — forward-only settlement is the test that can't keep improving

#1 opened 4 days ago by

kopei

New activity in amaye15/toto-gguf 4 days ago

Bit-exact is a static claim — live same-question scores are the dynamic version, for all ten of your ports

#1 opened 4 days ago by

kopei

New activity in Yousafza1/financial-price-forecasting 4 days ago

"Direction is measured, not promised" — a venue that measures it on data your pipeline has never seen

#1 opened 4 days ago by

kopei

New activity in Sejibeji/tso-foundation-v17 5 days ago

"Persistence is unbeatable there" — an honest-limitations section that a live skill record would extend, not embarrass

#1 opened 5 days ago by

kopei

New activity in vilhess/PatchFM 5 days ago

You shipped the leakage-free checkpoint as the recommended one and ranked yourself 10th — forward-only data is the endpoint of that choice

#1 opened 5 days ago by

kopei

New activity in Yarden-Viktor/delu-day-ahead-forecast 5 days ago

You wrote "this is not a live forecast" five different ways — here's a venue where the live version is scored for you

#1 opened 5 days ago by

kopei

New activity in Datadog/Toto-2.0-313m 6 days ago

You picked a contamination-resistant benchmark on purpose — live forward data is the limiting case of that choice

#2 opened 6 days ago by

kopei

New activity in bytedance-research/Timer-S1 6 days ago

"Excels particularly at medium-term and long-term" is a horizon-specific claim — a forward record can test it per horizon

#2 opened 6 days ago by

kopei

New activity in alaminxpro/bd-food-price-forecaster 6 days ago

"Point accuracy is not the selling point; calibrated intervals are" — there's a live arena that scores exactly that

#1 opened 6 days ago by

kopei

New activity in Abe1970/fx-multistep-forecasting-paper 7 days ago

Your own results section flags "not confirmed on a fully untouched holdout" — that holdout can be public and forward-only

#1 opened 7 days ago by

kopei

New activity in Elpriser/nordic-price-forecast 7 days ago

The zone-pooling honesty in your card is rare — worth a forward-only external record too

#1 opened 7 days ago by

kopei

New activity in Maple728/TimeMoE-200M 8 days ago

Billion-scale MoE pretraining meets the one eval that can't be memorized

#3 opened 8 days ago by

kopei