Pith Number

pith:7EEIF6IW

pith:2025:7EEIF6IW46QKWYCE6JV7UAV4YB

not attested not anchored not stored refs resolved

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Boshen Xu, Dingyi Yang, Jian Luan, Jianzhong Ju, Junqi Lin, Kejun Lin, Liang Zhang, Qin Jin, Wenxuan Wang, Xiangnan Fang, Yang Du, Ye Wang, Zewen He, Zhenbo Luo, Zihan Xiao, Zihao Yue, Ziheng Wang

Reinforcement learning post-training enables large vision-language models to achieve state-of-the-art temporal video grounding with only 2.5K training examples.

arxiv:2503.13377 v3 · 2025-03-17 · cs.CV · cs.AI · cs.CL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7EEIF6IW46QKWYCE6JV7UAV4YB}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Time-R1 achieves state-of-the-art performance across multiple downstream datasets using only 2.5K training data, while improving its general video understanding capabilities.

C2weakest assumption

That reinforcement learning with verifiable rewards on the curated RL-friendly dataset will produce genuine generalization improvements rather than overfitting to the specific reward formulation or benchmark construction.

C3one line summary

Time-R1 applies RL with verifiable rewards to post-train LVLMs for temporal video grounding, reaching state-of-the-art results on multiple datasets using only 2.5K samples while also improving general video capabilities.

References

87 extracted · 87 resolved · 10 Pith anchors

[1] DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning 2025 · arXiv:2501.12948

[2] Ht- step: Aligning instructional articles with how-to videos 2023

[3] Localizing moments in video with natural language 2017

[4] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

[5] Activitynet: A large-scale video benchmark for human activity understanding 2015

Formal links

3 machine-checked theorem links

Cited by

34 papers in Pith

VISD: Enhancing Video Reasoning via Structured Self-Distillation

CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models

Receipt and verification

First computed	2026-05-17T23:38:15.370647Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f90882f916e7a0ab6044f26bfa02bcc0583d66f90901bbdde83aedd8fcbce415

Aliases

arxiv: 2503.13377 · arxiv_version: 2503.13377v3 · doi: 10.48550/arxiv.2503.13377 · pith_short_12: 7EEIF6IW46QK · pith_short_16: 7EEIF6IW46QKWYCE · pith_short_8: 7EEIF6IW

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/7EEIF6IW46QKWYCE6JV7UAV4YB \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f90882f916e7a0ab6044f26bfa02bcc0583d66f90901bbdde83aedd8fcbce415

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c47461ba7328122a8cf3804f43f934a641731cf10e3ddf62d5cb9ec145d00de7",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-03-17T17:04:20Z",
    "title_canon_sha256": "97209bd8163ae50201f4f63563823b1191ded3d066d238972ab094ea7017c1da"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.13377",
    "kind": "arxiv",
    "version": 3
  }
}