Pith Number

pith:Z6HLR2KO

pith:2026:Z6HLR2KOITW2GTPLADW3PQM6WY

not attested not anchored not stored refs resolved

CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding

Ailar Mahdizadeh, Leonid Sigal, Muchen Li, Puria Azadi, Xiangteng He

Treating KV-cache compression as coreset selection improves streaming video understanding under fixed memory budgets.

arxiv:2605.14310 v1 · 2026-05-14 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Z6HLR2KOITW2GTPLADW3PQM6WY}

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

Across four open-source VLMs and five long-video and streaming-video benchmarks, our method improves over heuristic streaming compression baselines under a fixed cache budget.

C2weakest assumption

That a small coreset chosen by joint KV coverage and orthogonality will preserve the information needed for arbitrary future reasoning queries over the full history.

C3one line summary

CoRDS selects a compact KV-cache subset via joint-space coreset coverage and log-det diversity to outperform token-wise heuristics on long-video VLM benchmarks.

References

32 extracted · 32 resolved · 7 Pith anchors

[2] Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution 2024 · arXiv:2409.12191

[3] Long context transfer from language to vision.Transactions on Machine Learning Research, 2025 2025

[4] Infinipot-v: Memory-constrained kv cache compression for streaming video understanding 2025

[5] Streaming long video understanding with large language models 2024

[6] Kim, Bilge Soran, Raghuraman Krishnamoorthi, Mohamed Elhoseiny, and Vikas Chandra 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.003699Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cf8eb8e94e44eda34deb00edb7c19eb6111e73e74512c24e1287abf96d159910

Aliases

arxiv: 2605.14310 · arxiv_version: 2605.14310v1 · doi: 10.48550/arxiv.2605.14310 · pith_short_12: Z6HLR2KOITW2 · pith_short_16: Z6HLR2KOITW2GTPL · pith_short_8: Z6HLR2KO

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/Z6HLR2KOITW2GTPLADW3PQM6WY \
  | 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: cf8eb8e94e44eda34deb00edb7c19eb6111e73e74512c24e1287abf96d159910

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d89c916e7a11a6617f46c67f171b91b726f96ccf276a611b3aeeebd5f145ee1e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T03:22:30Z",
    "title_canon_sha256": "0b3c0d18e1f31bb8b3496673bb86fa0d1b96f8140acf5c2ebf52d0e4339d3520"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14310",
    "kind": "arxiv",
    "version": 1
  }
}