Pith. sign in
Pith Number

pith:OHNVEV57

pith:2026:OHNVEV57C5R7ZRKJT5IFR7ZLGC
not attested not anchored not stored refs pending

Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval

Du-Seong Chang, HaeJun Yoo, Insung Lee, Myoung-Wan Koo, Yongseop Shin

Multimodal LLM audio encoders match state-of-the-art retrieval while excelling at complex user queries and hard negatives.

arxiv:2604.18360 v2 · 2026-04-20 · cs.SD · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{OHNVEV57C5R7ZRKJT5IFR7ZLGC}

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

OEA achieves comparable text-to-audio retrieval performance to state-of-the-art M2D-CLAP, while demonstrating clear advantages in two critical areas: (1) dominant text-to-text retrieval (+22% relative improvement), and (2) substantially superior hard negative discrimination (+4.3%p HNSR@10, +34.7% relative TFR@10), revealing that LLM backbones provide superior semantic understanding of complex queries.

C2weakest assumption

That the five User-Intent Query formulations accurately capture real-world search behavior and that observed gains are caused by the multimodal LLM backbone rather than differences in training data, scale, or other unstated factors.

C3one line summary

Omni-Embed-Audio uses multimodal LLMs to match CLAP on standard audio retrieval while improving text-to-text retrieval by 22% relative and hard negative discrimination by 4.3 points HNSR@10 on user-intent queries.

Receipt and verification
First computed 2026-06-02T02:04:17.864783Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3

Aliases

arxiv: 2604.18360 · arxiv_version: 2604.18360v2 · doi: 10.48550/arxiv.2604.18360 · pith_short_12: OHNVEV57C5R7 · pith_short_16: OHNVEV57C5R7ZRKJ · pith_short_8: OHNVEV57
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/OHNVEV57C5R7ZRKJT5IFR7ZLGC \
  | 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: 71db5257bf1763fcc5499f5058ff2b309f79469835fc035e7a297e751df47bb3
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "c71db82ae68cf48b45abec4ee3d1ebd433ea1122a17fda15efec9ac51d276218",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-04-20T14:50:33Z",
    "title_canon_sha256": "fc418e7de2ea951045d10e7ac57469466a5bdaf533fe209814cf4a66b8a8d411"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.18360",
    "kind": "arxiv",
    "version": 2
  }
}