Pith Number

pith:IK2TXA3I

pith:2026:IK2TXA3ID2XCL7HWXR2MWBGTWZ

not attested not anchored not stored refs resolved

DeepSlide: From Artifacts to Presentation Delivery

Haoseng Liu, Jiahang Li, Ming Yang, Weiguo Zheng, Yuzheng Cai, Zhiwei Zhang

DeepSlide is a multi-agent system that plans time-budgeted narratives and generates synced slides and scripts to improve delivery while matching visual quality.

arxiv:2605.15202 v1 · 2026-04-01 · cs.AI · cs.CL · cs.IR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IK2TXA3ID2XCL7HWXR2MWBGTWZ}

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 20 domains and diverse audience profiles, DeepSlide matches strong baselines on artifact quality while consistently achieving larger gains on delivery metrics, improving narrative flow, pacing precision, and slide--script synergy with clearer attention guidance.

C2weakest assumption

The dual-scoreboard benchmark cleanly separates static artifact quality from dynamic delivery excellence without overlap or bias in the evaluation metrics.

C3one line summary

DeepSlide introduces a multi-agent system for full presentation preparation that matches baselines on slide quality but improves narrative flow, pacing, and script synergy via a new dual-scoreboard benchmark.

References

94 extracted · 94 resolved · 1 Pith anchors

[1] Public policy and superintelligent AI: A vector field approach 2020 · doi:10.1093/oso/9780190936600.001.0001

[2] The craft of scientific presentations: Critical steps to succeed and critical errors to avoid.Physics Today, 57, 07 2004 2004 · doi:10.1063/1.1784305

[3] Autopresent: Designing structured visuals from scratch 2025

[4] Presentations are not always linear! gnn meets llm for document-to-presentation transformation with attribution.arXiv preprint arXiv:2405.13095, 2024 2024

[5] Presentations by the humans and for the humans: Harnessing LLMs for generating persona-aware slides from documents 2024 · doi:10.18653/v1/2024.eacl-long.163

Receipt and verification

First computed	2026-05-20T00:00:45.780797Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

42b53b83681eae25fcf6bc74cb04d3b660050710e7d4ea642ba59f27429b36e1

Aliases

arxiv: 2605.15202 · arxiv_version: 2605.15202v1 · doi: 10.48550/arxiv.2605.15202 · pith_short_12: IK2TXA3ID2XC · pith_short_16: IK2TXA3ID2XCL7HW · pith_short_8: IK2TXA3I

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/IK2TXA3ID2XCL7HWXR2MWBGTWZ \
  | 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: 42b53b83681eae25fcf6bc74cb04d3b660050710e7d4ea642ba59f27429b36e1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d884f98cf98b27b5d27cfe23ea8cf86306306d1df63fd74447b6366fb39c7ac3",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.IR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-01T13:38:36Z",
    "title_canon_sha256": "3749a12252579366b8b52d76c4eba2aa1774f9158bbe8d405db20ea54256ea8f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15202",
    "kind": "arxiv",
    "version": 1
  }
}