Verite

Verite!: Cross-Domain Deception Detection

Verite! is a cross-domain deception detection classifier built on ModernBERT-base. It detects deceptive content (fake news, phishing, spam, job scams, political misinformation, product review fraud, and Twitter rumours) with a single unified model.

Code and training script: github.com/Daxlia/Verite

Evaluated on the DIFrauD benchmark — 7 domains, ~103K samples.

---

Results

Evaluated on the DIFrauD test set (macro-F1 and AUC-ROC, higher is better).

Single seed (seed=42) on 2×NVIDIA T4. Multi-seed ensemble (3 seeds) expected to improve further.

Per-Domain Breakdown

Ablation Study

---

Model Description

Verite! extends ModernBERT-base with four feature streams fused before classification:

All four streams are concatenated (512+512+256+10 = 1290-d), projected through LayerNorm → Linear(512) → GELU, then through 5× multi-sample dropout into a HypersphericalHead (prototype classifier on the unit hypersphere, scale=20).

Architecture diagram:

Input Text ──────────────────────── Linguistic Features (8-d)
    │                                         │
    ▼                                         ▼
ModernBERT-base (149M params, fp32)     ling_proj → feat_emb (512-d)
    │                                         │
    ├── AttentionPooling ──► semantic_proj ──► sem_emb  (512-d) ──┐
    ├── LocalConsistencyModule (4 segs) ──► cons_emb (256-d) ─────┤
    └── SpectralFeatures (top-8 FFT + centroid + entropy) ► spec (10-d)
                                                                   │
             Concatenate [sem_emb | feat_emb | cons_emb | spec]  (1290-d)
                                         │
                               LayerNorm → Linear(512) → GELU
                                         │
                         Multi-sample Dropout (5×) → HypersphericalHead
                                         │
                                  Logits (2 classes)

---

Training

Trained on 2×NVIDIA T4 (16 GB each) via Kaggle (~13 h, < 14 h total session). The encoder always runs in fp32 to avoid SDPA overflow on sm75 hardware; head layers use fp16 via PyTorch AMP.

Training objectives:

• Focal loss (γ=2.0) with class-balanced weights and label smoothing (ε=0.05)
• Supervised Contrastive loss (λ=0.1, τ=0.07) on semantic embeddings
• Domain MTL cross-entropy (λ=0.1) across 7 domain heads

Regularization stack:

• AdamW + LLRD (decay=0.9): encoder LR=1e-5, head LR=1e-4
• Cosine schedule with 8% linear warmup
• Gradient accumulation (×4), gradient clipping (0.7)
• EMA (decay=0.995) — used for final checkpoint selection
• Adversarial Weight Perturbation (AWP, ε=0.001) from epoch 4 onward

Hyperparameters:

---

Usage

Important: This model uses a custom architecture defined in VeriteTrainer.py. You must have that file in your Python path before loading.

Installation

pip install torch>=2.1.0 transformers>=4.47.0 safetensors sentencepiece

Inference

import torch
from torch.utils.data import DataLoader
from transformers import AutoTokenizer
from safetensors.torch import load_file

from VeriteTrainer import DeceptionReasoningModel, Config, DeceptionDataset, collate_fn

cfg       = Config()
tokenizer = AutoTokenizer.from_pretrained("Daxlia/verite")

model = DeceptionReasoningModel(cfg)
model.load_state_dict(load_file("model.safetensors"))
model.eval()

texts = ["Congratulations! You've been selected to receive a $1,000 gift card. Click here to claim."]

dataset = DeceptionDataset(texts, [0] * len(texts), tokenizer, cfg)
loader  = DataLoader(dataset, batch_size=8, shuffle=False, collate_fn=collate_fn)

with torch.no_grad():
    for batch in loader:
        out  = model(input_ids=batch["input_ids"],
                     attention_mask=batch["attention_mask"],
                     ling_feats=batch["ling_feats"])
        prob = torch.softmax(out["logits"], dim=-1)[:, 1]
        for t, p in zip(texts, prob.tolist()):
            label = "DECEPTIVE" if p > 0.5 else "GENUINE"
            print(f"[{label}] P(deceptive) = {p:.4f} | {t}")

Output format

---

Domains

The model was trained jointly on all 7 DIFrauD domains:

---

Limitations

• Max input length is 256 tokens; longer texts are truncated.
• Inference requires VeriteTrainer.py — no AutoModel-compatible registration yet.
• Performance is weakest on Political Statements (F1=0.456) and Product Reviews (F1=0.642) — domains with subtle, opinion-heavy deception signals.
• Results reported for a single training seed; variance across seeds has not been fully characterized.

---

Citation

@misc{verite2026,
  author    = {Daxlia},
  title     = {Verite!: Cross-Domain Deception Detection with ModernBERT},
  year      = {2026},
  doi       = {10.5281/zenodo.20256648},
  url       = {https://doi.org/10.5281/zenodo.20256648}
}

---

AI Disclosure

This project was developed with assistance from AI tools:

• ChatGPT (OpenAI) — Bug identification, algorithmic suggestions, and research ideation
• Claude (Anthropic) — Code implementation, debugging, and writing of documentation files

All AI-generated content was reviewed, validated, and adapted by the author.

---

License

This model is released under the MIT License.

The base encoder ModernBERT-base is licensed under Apache 2.0.
The DIFrauD dataset is subject to its own license; refer to the dataset repository.