🏗️ Building on HF

Kshitij Thakkar PRO

kshitijthakkar

AI & ML interests

Building the evaluation and observability layer for AI. Creator of TraceVerse—turning real-world LLM interactions into datasets, benchmarks, and cost-efficient model insights.

Recent Activity

published a dataset 2 days ago

kshitijthakkar/AgentTrove

updated a Space 3 days ago

kshitijthakkar/repro-docalculus-derivation-graphs

updated a bucket 3 days ago

kshitijthakkar/repro-docalculus-derivation-graphs-artifacts

View all activity

Organizations

published a dataset 2 days ago

kshitijthakkar/AgentTrove

Viewer • Updated Apr 30 • 1.7M • 3

updated a Space 3 days ago

Repro - Do-Calculus Derivation Graphs

🔗

Explore do‑calculus derivation graphs and sync with an AI agent

updated a bucket 3 days ago

kshitijthakkar/repro-docalculus-derivation-graphs-artifacts

104 kB

liked a Space 6 days ago

PaperVerse Explorer

😻

Research Paper Stats on Hugging Face

published a dataset 6 days ago

kshitijthakkar/GLM-5.1-Reasoning-1M-Cleaned

Preview • Updated Apr 29 • 108

published a model 6 days ago

kshitijthakkar/qwen3-4b-sft-v2-titanium-mix

Text Generation • 4B • Updated May 7 • 3

liked a model 7 days ago

poolside/Laguna-S-2.1-NVFP4

Text Generation • 68B • Updated 5 days ago • 158k • 151

updated a collection 7 days ago

ICML 2026 Reproductions - agent-repro challenge

Collection

Trackio logbooks: claim-by-claim reproductions of ICML 2026 papers for the Agent Reproducibility Challenge. • 27 items • Updated 7 days ago

updated a Space 7 days ago

DynaSchedBench reproduction

🎯

View and sync experiment logs with an AI agent

published a Space 7 days ago

DynaSchedBench reproduction

🎯

View and sync experiment logs with an AI agent

updated a bucket 7 days ago

kshitijthakkar/repro-dynaschedbench-observability-artifacts

247 kB

published a bucket 7 days ago

kshitijthakkar/repro-dynaschedbench-observability-artifacts

247 kB

updated a collection 7 days ago

ICML 2026 Reproductions - agent-repro challenge

Collection

Trackio logbooks: claim-by-claim reproductions of ICML 2026 papers for the Agent Reproducibility Challenge. • 27 items • Updated 7 days ago

updated a bucket 7 days ago

kshitijthakkar/repro-cbu-judge-reliability-artifacts

632 kB

updated a Space 7 days ago

Repro - Judging What We Cannot Solve: Consequence-Based Utility for Oracle-Free Evaluation

🎯

Explore logs and collaborate with an AI coding agent

published a Space 7 days ago

Repro - Judging What We Cannot Solve: Consequence-Based Utility for Oracle-Free Evaluation

🎯

Explore logs and collaborate with an AI coding agent

published a bucket 7 days ago

kshitijthakkar/repro-cbu-judge-reliability-artifacts

632 kB

updated a Space 7 days ago

Repro - Provable Benefits of RLVR over SFT: Learning to Backtrack Efficiently

🔃

Collaborate on a logbook with an AI coding agent

updated a Space 8 days ago

ICML Provincia

🏛

Replay the ICML 2026 Agent‑Repro challenge logs

updated a Space 10 days ago

Repro - TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

🎯

Explore and sync research logbook with your coding agent

Kshitij Thakkar PRO

AI & ML interests

Recent Activity

Organizations

kshitijthakkar's activity

Repro - Do-Calculus Derivation Graphs

kshitijthakkar/repro-docalculus-derivation-graphs-artifacts

PaperVerse Explorer

DynaSchedBench reproduction

DynaSchedBench reproduction

kshitijthakkar/repro-dynaschedbench-observability-artifacts

kshitijthakkar/repro-dynaschedbench-observability-artifacts

kshitijthakkar/repro-cbu-judge-reliability-artifacts

Repro - Judging What We Cannot Solve: Consequence-Based Utility for Oracle-Free Evaluation

Repro - Judging What We Cannot Solve: Consequence-Based Utility for Oracle-Free Evaluation

kshitijthakkar/repro-cbu-judge-reliability-artifacts

Repro - Provable Benefits of RLVR over SFT: Learning to Backtrack Efficiently

ICML Provincia

Repro - TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning