Running
Value-as-Tool GVR Tree Explorer
🌳
Branched GVR rollouts of Qwen3.5-9B on ArXivMath
Anikait Singh
asingh15
AI & ML interests
None yet
Recent Activity
updated a Space about 10 hours ago
asingh15/value-as-tool-gvr-tree-explorer published a Space about 10 hours ago
asingh15/value-as-tool-gvr-tree-explorer updated a dataset about 10 hours ago
asingh15/value-as-tool-gvr-treesOrganizations
None yet
Running
Value-as-Tool Rollout Explorer
🧮
Problem-by-problem viewer of proof-harness rollouts
Running
Rubric Diversity Task Explorer
🔎
Search tasks, rubrics, difficulty evidence and references
Running
Rubric Diversity Atlas
🧭
Explore task rubrics and the variety of valid responses.
Running
Amazon C2 Varied Rubrics Viewer
🧭
Inspect selection diversity for Amazon C2 rubrics
Running
Amazon C11 Distillation Viewer
🔬
Explore Amazon C11 distillation data and reviewer metrics
Running
Amazon V3 Candidate Dataset Explorer
🧭
Explore and compare AI response datasets with interactive charts
Running
TCS Direction Beam Partial 1017 MC8
🚀
Explore beam-search trajectories for AI problem solving
Running
Amazon Qwen27 Candidate Diversity
🧭
Explore and compare product review candidates across variants
Running
Qwen3.5-2B + Qwen3.6-27B Candidate Explorer
🧭
Explore AI evaluation results and reward data for model tasks
Running
Qwen3.5-2B Tool-Use Explorer
🔧
Explore Qwen3.5-2B tool-use dataset and compare model runs
Running
Qwen3.6-27B Tool-Use Explorer
🔧
Explore Qwen3.6-27B tool-use candidates and their results
Running
TCS Direction Beam Full Trace
🚀
Explore direction-beam trajectories and scores for any problem
Running
Direction-Beam Proof Explorer
🔎
Explore a model's proof‑search trace for an olympiad problem
Running
WikiRace Qwen3.5 Explorer
🚀
Explore WikiRace model performance and navigation rollouts
Running
TCS Value Trajectory Explorer
🚀
Explore model performance trajectories across problems
Running
WikiGame Qwen3.5 Explorer
🚀
Explore WikiGame benchmark results and model performance
Running
Humanual Rubric Explorer
🚀
Explore and browse rubric records from the Humanual dataset
Running
Humanual Amazon Full | Qwen3.6-27B
🚀
Explore Humanual dataset with filters and score visualizations
Running
Rollout Trajectory Explorer
📊
Explore model reasoning trajectories and grades
Running
Humanual Book | Qwen3.6-27B
🚀
Explore and filter human‑evaluated LLM response dataset
Running
Polaris Token Entropy
🚀
Inspect token entropy and forks in Polaris trajectory-v2.
Running
Qwen3.5 Flatness Pilot
🚀
Explore model performance and reasoning trajectories
Running
PRM Trajectory Explorer
🚀
Inspect prefix values and terminal correctness.