# language: en license: apache-2.0 library_name: htr tags: [text2text-generation, scientific-writing, style-reconstruction, research] pipeline_tag: text2text-generation

# HTR-Tiny (v0.3.0)

Human Text Reconstruction Transformer — a research model that maps an LLM-rewritten scientific passage back towards the distribution of the pre-2018 human-authored original. Outputs are synthetic reconstructions: they are not the original text, and they are not evidence of human authorship or of AI use. Part of UQO working paper WP-AI-0002.

# Intended use

Research on how LLM rewriting transforms scientific prose; stylometric analysis; benchmarking inverse-paraphrase models; a tool for authors who want a draft re-aligned with historical scientific register as a suggestion that must be checked. Not intended for AI-text detection, authorship attribution, academic-integrity decisions, or production of text presented as human-written.

# How to use

from htr.inference.pipeline import HTRReconstructor
rec = HTRReconstructor.from_pretrained("path/to/HTR-Tiny")
r = rec.reconstruct("LLM-rewritten paragraph …", metadata={"discipline": "economics", "pub_year": 2012, "section_role": "results"})
print(r.reconstruction); print(r.warnings)

CLI: htr reconstruct --model path/to/HTR-Tiny --text "…" --discipline economics --year 2012.

# Training data

Medium stage: denoising pretraining on 258 264 rights-verified pre-2018 passages (PMC OA, CC BY economics/finance journals, arXiv, public-domain books; 20 000 steps), then fine-tuning on 72 698 validated (Haiku 5.5 rewrite → original) pairs of 14 000 passages; 32k SentencePiece; seed 3 (M* by the frozen validation rule). Validation metrics below are exploratory; confirmatory test results in the paper.

# Evaluation (document-safe test split; identity baseline reported alongside)

{
  "chrf": {
    "mean": 68.8415,
    "ci": [
      68.0331,
      69.6149
    ]
  },
  "edit_sim": {
    "mean": 0.6786,
    "ci": [
      0.6706,
      0.6863
    ]
  },
  "rougeL": {
    "mean": 0.6875,
    "ci": [
      0.6789,
      0.696
    ]
  },
  "exact_match": {
    "mean": 0.0,
    "ci": [
      0.0,
      0.0
    ]
  },
  "number_recall": {
    "mean": 0.9906,
    "ci": [
      0.9877,
      0.9934
    ]
  },
  "placeholders_exact": {
    "mean": 0.9953,
    "ci": [
      0.9923,
      0.9979
    ]
  },
  "_baseline_B0_identity": {
    "chrf": 68.4233,
    "edit_sim": 0.6785,
    "rougeL": 0.6841,
    "exact_match": 0.0,
    "number_recall": 1.0,
    "placeholders_exact": 1.0
  }
}

Metrics: chrF++, normalised edit similarity, ROUGE-L, exact match, number recall, placeholder (citation/math/URL) preservation, stylometric Wasserstein distance to originals. Confidence intervals are document-clustered bootstrap.

# Limitations and risks

• Reconstruction from a paraphrase is non-identifiable: many originals map to the same rewrite; the model returns one plausible estimate. Lexical overlap with the true original is bounded.
• Factual integrity is enforced heuristically (protected spans, number checks); residual errors are flagged in warnings, not guaranteed absent. Always verify numbers, citations and negations.
• Trained on Claude rewrites of CC-licensed biomedical, economics/finance, arXiv and public-domain book passages; behaviour on other rewriters, languages or genres is reported in the paper's generalisation experiments only.
• Memorisation: training originals were deduplicated and the model is evaluated for nearest-neighbour overlap; see the paper. Do not use to recover specific copyrighted texts.

# Licence

Code and weights: Apache-2.0. Data licences: see LICENSE-MODEL.txt and the data card. Attribution to NLM/PMC, arXiv, publishers and Project Gutenberg sources is in the data card.

# Citation

Boucher, S.-P. (2026). Human Text Reconstruction: Learning the Inverse of LLM-Induced Transformations in Scientific Writing. UQO Working Paper AI-0002.