Pith. sign in
Pith Number

pith:63R7DN2V

pith:2026:63R7DN2VF7IQ6PBDVXY2JYU7JK
not attested not anchored not stored refs pending

Benchmarking Parameter-Efficient Fine-Tuning of Large Language Models for Low-Resource Tajik Text Generation with the Tajik Web Corpus

Mullosharaf K. Arabov

Mistral 7B with QLoRA rank 16 reaches mean perplexity 5.03 on Tajik text generation after release of the largest open Tajik web corpus.

arxiv:2605.03742 v2 · 2026-05-05 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{63R7DN2VF7IQ6PBDVXY2JYU7JK}

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

Best results were achieved by Mistral 7B with QLoRA (r=16): mean perplexity 5.03, standard deviation 0.03. The novelty lies in creating the largest verified Tajik corpus and the first systematic analysis of PEFT effectiveness for Tajik text generation.

C2weakest assumption

That a random 10,000-document subsample from the web corpus is representative of Tajik text distribution and that perplexity alone sufficiently captures generation quality without human evaluation or downstream task metrics.

C3one line summary

Releases Tajik Web Corpus (~1.11B characters) and finds Mistral 7B with QLoRA rank 16 yields lowest perplexity of 5.03 for Tajik generation while full fine-tuning on small models causes forgetting.

Cited by

1 paper in Pith

Receipt and verification
First computed 2026-08-11T02:23:59.697059Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

f6e3f1b7552fd10f3c23adf1a4e29f4a9951ce897780fc43a72fe01a22098aa2

Aliases

arxiv: 2605.03742 · arxiv_version: 2605.03742v2 · doi: 10.48550/arxiv.2605.03742 · pith_short_12: 63R7DN2VF7IQ · pith_short_16: 63R7DN2VF7IQ6PBD · pith_short_8: 63R7DN2V
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK \
  | 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: f6e3f1b7552fd10f3c23adf1a4e29f4a9951ce897780fc43a72fe01a22098aa2
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "bd279189055479395f8ce35e5a5af4576172286dbd13b713f45fbbefb9257e9b",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-05T13:28:31Z",
    "title_canon_sha256": "8adc5928b591238e86711a9db759efd6cf7b308323ccd7c75d34322a95716a71"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.03742",
    "kind": "arxiv",
    "version": 2
  }
}