pith. machine review for the scientific record. sign in
Pith Number

pith:RWPCTPJL

pith:2026:RWPCTPJLWPFBOS2ZUN22NCRY65
not attested not anchored not stored refs resolved

Towards Continuous Sign Language Conversation from Isolated Signs

Chanyoung Kim, Jiwoo Park, Junhyeok Kim, Kyobin Choo, Minseo Kim, Seong Jae Hwang, Youngmin Kim

SignaVox generates 3D sign language responses directly from prior signing context without text or glosses.

arxiv:2605.14705 v1 · 2026-05-14 · cs.CV

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open

Claims

C1strongest claim

We train SignaVox, a direct sign-to-sign conversational model that generates 3D body, hand, and facial motion responses from prior signing context without spoken-language text or externally provided glosses at inference time.

C2weakest assumption

That the recomposed continuous sign videos from isolated clips using BRAID accurately capture natural co-articulation and semantics, and that the retrieval-guided translator provides high-quality gloss sequences without significant errors.

C3one line summary

Constructs continuous sign conversation data from isolated signs using retrieval and diffusion models to train a direct sign-to-sign conversational AI.

References

112 extracted · 112 resolved · 5 Pith anchors

[1] Bsl-1k: Scaling up co-articulated sign language recognition using mouthing cues 2020
[2] The american sign language lexicon video dataset 2008
[3] Qwen3-VL Technical Report 2025 · arXiv:2511.21631
[4] Parent american sign language skills correlate with child–but not toddler–asl vocabulary size.Language Acquisition, 31(2):85–99, 2024 2024
[5] Sign language recognition, generation, and translation: An interdisciplinary perspective 2019
Receipt and verification
First computed2026-05-17T23:38:59.278087Z
Builderpith-number-builder-2026-05-17-v1
SignaturePith Ed25519 (pith-v1-2026-05) · public key
Schemapith-number/v1.0

Canonical hash

8d9e29bd2bb3ca174b59a375a68a38f75a8fe70f86fcdbff0c7e6533c7559edb

Aliases

arxiv: 2605.14705 · arxiv_version: 2605.14705v1 · doi: 10.48550/arxiv.2605.14705
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/RWPCTPJLWPFBOS2ZUN22NCRY65 \
  | 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: 8d9e29bd2bb3ca174b59a375a68a38f75a8fe70f86fcdbff0c7e6533c7559edb
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "e0b60c4cf692b6cc64e2e598144604ef4cb967219f8df0a8eac84ec4dae19222",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T11:22:27Z",
    "title_canon_sha256": "3787827a34fe7a7499ea1aab7ff42a63fe1a511ff566e18dac4dbc97214d9b6d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14705",
    "kind": "arxiv",
    "version": 1
  }
}