Pith Number

pith:HVR6JYBJ

pith:2026:HVR6JYBJ7NDJ5PFQG6V5U7EYMB

not attested not anchored not stored refs resolved

An LLM-Based System for Argument Reconstruction

Douglas Aldred, Fabio G. Cozman, Paulo Pirozelli, Victor Hugo Nascimento Rocha

An LLM pipeline reconstructs natural language text into argument graphs with premises, conclusions, and support, attack or undercut relations.

arxiv:2605.13793 v1 · 2026-05-13 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{HVR6JYBJ7NDJ5PFQG6V5U7EYMB}

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

Results show that the system can adequately recover argumentative structures and, when adapted to different annotation schemes, achieve reasonable performance across benchmark datasets.

C2weakest assumption

That the multi-stage LLM pipeline reliably identifies argumentative components and their relations without systematic human correction or domain-specific fine-tuning beyond the described prompting.

C3one line summary

An LLM pipeline turns natural language arguments into structured graphs of premises, conclusions, and support/attack/undercut relations.

References

12 extracted · 12 resolved · 2 Pith anchors

[1] Abstract dialectical frameworks.Proceedings of the Twelfth International Conference on Principles of Knowledge Representation and Reason- ing (KR 2010), pp 2010

[2] Claudette Cayrol and Marie-Christine Lagasquie-Schiex. On the acceptability of arguments in bipo- lar argumentation frameworks.Proceedings of the Eighth European Conference on Symbolic and Quantitativ 2005

[3] Do emotions really affect argument convincingness? a dynamic approach with LLM-based manipulation checks 2025

[4] ISBN 979-8-89176-256-5 2025

[5] Which side are you on? a multi-task dataset for end-to-end argument summarisation and evaluation 2024

Receipt and verification

First computed	2026-05-18T02:44:15.596283Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3d63e4e029fb469ebcb037abda7c986058a1e01fa154c3a0819a4e39cb49783f

Aliases

arxiv: 2605.13793 · arxiv_version: 2605.13793v1 · doi: 10.48550/arxiv.2605.13793 · pith_short_12: HVR6JYBJ7NDJ · pith_short_16: HVR6JYBJ7NDJ5PFQ · pith_short_8: HVR6JYBJ

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/HVR6JYBJ7NDJ5PFQG6V5U7EYMB \
  | 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: 3d63e4e029fb469ebcb037abda7c986058a1e01fa154c3a0819a4e39cb49783f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8d0e79fb930445624dd1d57cbf1345c4fc9c5447549e226fd0ed062a77d84a30",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T17:13:45Z",
    "title_canon_sha256": "343a4f7361632b6be5f355203c41c04410d921b181613586ab727426a3c397e8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13793",
    "kind": "arxiv",
    "version": 1
  }
}