logs
Datasets
All datasets matching “logs”observation-masking-eval-logs
Eval Logs
Paper | Code
This repository contains model evaluation logs for four deep-research / web-agent benchmarks. Each run directory contains evaluated.jsonl judge results and node_0_shard_*.jsonl trajectory logs. Plot files and local bookkeeping files are intentionally excluded.
CM denotes the observation mask context management setting used in the paired run.
Data Access
You can download all released evaluation data, including tasks and… See the full description on the dataset page: https://huggingface.co/datasets/i-DeepSearch/observation-masking-eval-logs.encrypted-logstest-mcp-logs(Put queries first as heuristics don't detect when there are no logs)
RAVine-logs
RAVine-logs
This repository contains the running logs of the experiments conducted in the paper RAVine: Reality-Aligned Evaluation for Agentic Search. These logs can be used for result reproduction or detailed case analysis of agentic LLMs with search performance.
RAVine is a comprehensive evaluation system for agentic search, encompassing the web environment, benchmark datasets, and a novel evaluation method, serving as a full-process, reproducible, and goal-aligned evaluation… See the full description on the dataset page: https://huggingface.co/datasets/sapphirex/RAVine-logs.nba-game-logs
NBA Player Game Logs
One row per player per regular-season game, 2021-22 through 2025-26, in a
canonical schema used by cbratkovics/nba-ai-ml
for point-in-time feature engineering and batch prediction of points, rebounds, and assists.
Provenance
Historical backfill: Eoin Moore, Historical NBA Data and Player Box Scores, Kaggle (eoinamoore/historical-nba-data-and-player-box-scores), version 515, CC0 1.0. Only PlayerStatistics.csv and TeamHistories.csv are used;… See the full description on the dataset page: https://huggingface.co/datasets/cbratkovics/nba-game-logs.ULP-logs