Pith Number

pith:BMFR3ZQI

pith:2026:BMFR3ZQINADOCHC7Y67C3X2ELG

not attested not anchored not stored refs resolved

Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation

Changxing Ding, Deli Cai, Haoyang Ma

CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions

arxiv:2605.13729 v1 · 2026-05-13 · cs.CV · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BMFR3ZQINADOCHC7Y67C3X2ELG}

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

Experiments on HumanML3D and KIT datasets demonstrate that CMC achieves state-of-the-art performance in control accuracy and motion quality.

C2weakest assumption

The simplified controlled-joint representation produced by the first-stage trajectory model supplies sufficient partial observations for the second-stage text-conditioned inpainting model to generate consistent, artifact-free full-body motions.

C3one line summary

CMC decouples trajectory control and text-conditioned motion completion with selective inpainting to achieve state-of-the-art accuracy and quality in multimodal human motion generation.

References

60 extracted · 60 resolved · 0 Pith anchors

[1] Crowdmogen: Event-driven collective human motion generation.Int 2026

[2] Executing your commands via motion diffusion in latent space 2023

[3] Hop: Heterogeneous topology-based multimodal entanglement for co-speech gesture generation 2025

[4] Interaction transformer for human reaction generation.IEEE Trans 2023

[5] Mofusion: A framework for denoising-diffusion- based motion synthesis 2023

Receipt and verification

First computed	2026-05-18T02:44:16.574472Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d

Aliases

arxiv: 2605.13729 · arxiv_version: 2605.13729v1 · doi: 10.48550/arxiv.2605.13729 · pith_short_12: BMFR3ZQINADO · pith_short_16: BMFR3ZQINADOCHC7 · pith_short_8: BMFR3ZQI

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/BMFR3ZQINADOCHC7Y67C3X2ELG \
  | 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: 0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "432a5cc1ad1844833dafbad0849898ebfd24540ea00ac7eeb4e95cbf5565b36b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T16:09:04Z",
    "title_canon_sha256": "ffc513ec70a965715c626553edbe9916f128d80952cf6f48e29a3690c44b00b7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13729",
    "kind": "arxiv",
    "version": 1
  }
}