aguennoune17/negenWM-jepa-v2

ATLASCRISPRWorldModel
├── CRISPRContextEncoder  x(t) → s(t)    [84→256→128→64  + LayerNorm + GELU]
│   └── One-hot 20-nt (80-dim) + 4 features physico-chimiques
├── CRISPRTargetEncoder   EMA(ContextEncoder), ∇=0  [R3]
│   └── Momentum=0.996 — mise à jour chaque batch
├── CRISPRJEPAPredictor   s(t) → ŝ(t+Δ)  [latent space only — R1]
│   └── 12/20 positions contexte → prédiction 8/20 masquées
└── CRISPRNegentropicWM   Soft Collapse + NER  [R5, R8]
    └── NER = (τ·specificity + κ·cleavage − λ·friction) / lambda_cost

Logits = κ·Stability + τ·Alignment − λ·EnergyCost + LatentUtility
NER    = (InformationGain − ExternalFriction) / EnergyCost

{
  "lot_id":          "ATLAS-CRISPR-SPRINT3-2026-04-15",
  "tag_name":        "dna-lot-v3.0.0-crispr",
  "sequencing_hash": "2d907f4b5c00d01d52a671163c43fbb2...",
  "ndc_target":      "ndc-nexus-biocontinuum-eu-010",
  "ner_score":       0.6909,
  "collapse_risk":   0.3091,
  "layer":           "terra",
  "signers":         ["CNRS", "UTokyo"],
  "valid_years":     100,
  "sdg_alignments":  ["SDG-3.8.1", "SDG-12.2.1", "SDG-17.17.1"],
  "created_at":      "2026-04-15T22:28:15.870578+00:00"
}

from safetensors.torch import load_file
import torch, json

# Charger les poids Sprint 3
state_dict = load_file("model.safetensors")
config     = json.load(open("config.json"))

print(f"Sprint    : {config['sprint']}")
print(f"NER score : {config['ner_score']}")
print(f"Lot ADN   : {config['lot_id']}")

# Inférence directe (nécessite train_jepa_crispr.py)
from train_jepa_crispr import ATLASCRISPRWorldModel, ATLASCRISPRDataset
import torch

model = ATLASCRISPRWorldModel()
model.context_encoder.load_state_dict(state_dict)
model.eval()

# Encoder un guide ARN
dataset = ATLASCRISPRDataset("data/atlas_crispr_10k_benchmark.csv")
ctx, tgt, props = dataset[0]
with torch.no_grad():
    out = model(ctx.unsqueeze(0), tgt.unsqueeze(0), props.unsqueeze(0))
    print(f"Embedding : {out.context_embedding.shape}")  # (1, 64)
    print(f"NER       : {out.ner_scores.item():.4f}")

@misc{atlas-nwm-sprint3-crispr-2026,
  title     = {ATLAS NWM v2 Sprint 3 — I-JEPA Self-supervised on CRISPR 10k},
  author    = {Guennoune, Abderrahim and GitHub Copilot (Claude Sonnet 4.6)},
  year      = {2026},
  howpublished = {\url{https://huggingface.co/aguennoune17/negenWM-jepa-v2}},
  note      = {DOI: 10.57967/hf/8178 · DNA Lot: dna-lot-v3.0.0-crispr}
}

NERHead(dim_in=768, patch_size=14, features=256)
│
├── _BaseDPTHead              # Pyramide features → feature map [B*S, 256, H, W]
│   └── 4 couches VGT token_list[i] → resize + conv → fuse
│
├── ner_proj (Conv2d 256→1)  # Score brut [B*S, 1, H, W] → sigmoid → NER [B,S,H,W]
│
├── Sky Prior (λ_sky=0.30)   # Absorption douce sur pixels ciel : NER *= (1 − λ·P_sky)
│
└── Soft Collapse Mask        # training → sigmoid différentiable ∈ (0,1)
                              # inference → (NER ≥ τ).float() ∈ {0.0, 1.0}

from hyworld2.worldrecon.hyworldmirror.models.heads.ner_head import NERHead
import torch

# Initialisation
ner_head = NERHead(
    dim_in=768,        # dim tokens VGT (DINOv2-compatible)
    patch_size=14,     # patch size DINOv2
    features=256,      # taille feature map DPT
    kappa=1.0,
    lam=0.5,
    tau=0.35,
    kappa_learnable=True,   # R-6 : κ/λ/τ → nn.Parameter
).to(device)

# Inférence (hard_mask=True → binaire {0, 1})
with torch.no_grad():
    ner, mask = ner_head(
        token_list,          # list[4] de [B, S, N_tokens, 768]
        images,              # [B, S, 3, H, W]
        patch_start_idx=4,   # 4 register tokens DINOv2
        hard_mask=True,      # R-8 : soft en training, binaire en inférence
    )
    # ner  : [B, S, H, W] ∈ [0, 1]  — carte de confiance NER spatiale
    # mask : [B, S, H, W] ∈ {0, 1}  — masque Soft Collapse binaire

# Training (hard_mask=False → différentiable)
ner, mask = ner_head(token_list, images, patch_start_idx=4, hard_mask=False)
# mask ∈ (0, 1) — gradients fluides pour backprop