pith:OB35U2QS
StoryScope: Investigating idiosyncrasies in AI fiction
Narrative features alone distinguish AI fiction from human writing at 93 percent accuracy.
arxiv:2604.03136 v5 · 2026-04-03 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{OB35U2QS3XMGUJLK7QDWSZU6HN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Narrative features alone achieve 93.2% macro-F1 for human vs. AI detection and 68.4% macro-F1 for six-way authorship attribution, retaining over 97% of the performance of models that include stylistic cues.
That the automatically induced discourse-level features capture narrative choices independent of surface stylistic signals and that the parallel corpus of prompts sufficiently controls for content to isolate true narrative differences.
StoryScope extracts narrative features showing AI stories favor tidy plots and over-explain themes while human stories show more moral ambiguity and temporal complexity, enabling strong detection and attribution.
Formal links
Cited by
Receipt and verification
| First computed | 2026-08-04T02:40:34.072940Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
7077da6a12ddd86a256afc0769669e3b576bba721167dc7650c540c01dc28d2e
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/OB35U2QS3XMGUJLK7QDWSZU6HN \
| 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: 7077da6a12ddd86a256afc0769669e3b576bba721167dc7650c540c01dc28d2e
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "bbd5e9f3fefa885c2a22787135b736f62bae63407214d31cf46d1ce49fb14e88",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/publicdomain/zero/1.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-04-03T15:56:38Z",
"title_canon_sha256": "59581cc8e8ac19c8af26f1d2822d97511168c4e2a45ba37696ff63637509039f"
},
"schema_version": "1.0",
"source": {
"id": "2604.03136",
"kind": "arxiv",
"version": 5
}
}