---
title: 'COOkeD: Diverse Interpretations in Research'
url: https://www.emergentmind.com/topics/cooked
type: topic
---

# COOkeD: Diverse Interpretations in Research

In the cited literature, **COOkeD** is not a single method or acronym with a stable definition. It is a reused label across several research programs, each centered on a different notion of *cookedness*, *cooking*, or constructions figuratively “cooked up” from simpler ingredients. These uses span cooking state recognition in images, state-change prediction from recipe text, post-distribution authorization of healthcare data via Anti-Adversarial processing, heterogeneous ensemble out-of-distribution detection, and formal colorings derived from Szlam’s Lemma [2212.08586, 2001.08665, 2403.17755, 2507.22576, 2411.04346].

## 1. Terminological scope and principal meanings

The term appears in the literature as a domain-specific label rather than as a unified framework. In food perception, it refers to recognizing preparation states such as *whole*, *diced*, *julienne*, *grated*, *juiced*, *creamy paste*, and *sliced* from images [2212.08586]. In recipe understanding, it refers to predicting state changes such as *custard cooked* or *temperature hot* from instructional text [2001.08665]. In healthcare ML, “cooked” data are Anti-Adversarial examples that a model must see at both training and deployment to function normally [2403.17755]. In trustworthy vision, COOkeD denotes “CLIP for OOD detection with some extra knowledge,” a three-member ensemble for OOD detection [2507.22576]. In combinatorics, it refers to colorings “cooked up” by Szlam’s Lemma [2411.04346].

| Use of COOkeD | Definition in the cited work | Representative mechanism |
|---|---|---|
| Food vision | Cooking state recognition from images | ViT with ImageNet-21k pretraining [2212.08586] |
| Recipe understanding | Joint action recognition and state-change prediction | Shared GRU encoder with two MLP decoders [2001.08665] |
| Healthcare protection | Anti-Adversarial “cooked” inputs for authorization control | SSIM-constrained perturbation generation [2403.17755] |
| OOD detection | Heterogeneous ensemble of supervised, zero-shot, and probe classifiers | Probability averaging plus entropy scoring [2507.22576] |
| Mathematics | Colorings “cooked up” from a red-blue partition and template set | Szlam coloring and ordered Szlam coloring [2411.04346] |

A recurrent misconception is to treat COOkeD as a single acronym or benchmark family. The cited record instead shows a polysemous research label whose meaning depends entirely on disciplinary context. This suggests a shared rhetorical motif—transformation under structured rules—rather than a shared technical lineage.

## 2. Cooking state recognition in vision and language

In computer vision, COOkeD is closely aligned with **Cooking State Recognition** (CSR), the task of identifying the preparation state of an ingredient rather than its object class. The CSR formulation evaluated in “Rethinking Cooking State Recognition with Vision Transformers” uses the Cooking State Recognition Challenge Dataset introduced by Jelodar et al., with **5,902 images**, **7 cooking states**, and **18 object types**. Images are resized to **224×224**, normalized with sample-wise centering to zero mean and unit standard deviation, and split into **4,106 training**, **728 validation**, and **1,068 test** images. The seven-class taxonomy is limited to preparation states and explicitly does **not** include labels such as *raw*, *baked*, *boiled*, or *fried* [2212.08586].

The key technical claim of that work is that ViT self-attention is well suited to CSR because the task depends on subtle texture and geometry cues with high intra-class similarity across ingredients. Two variants are studied: **ViT-B/16** with **12 encoder layers**, **12 heads**, **embedding dimension 768**, **MLP size 3,072**, and about **86M parameters**; and **ViT-L/16** with **24 layers**, **16 heads**, **embedding dimension 1,024**, **MLP size 4,096**, and about **307M parameters**. Fine-tuning ImageNet-21k pretrained weights is decisive: **ViT-B/16** trained from scratch yields about **55.4%** accuracy without augmentation and **55.1%** with augmentation, whereas fine-tuning achieves **93.0%** without augmentation and **94.3%** with augmentation. On the test split, average precision, recall, and F1 are each **0.94**; per-class recall reaches **0.97** for *diced* and is **0.92** for *grated*, *julienne*, and *whole*. The main confusions are *juiced* versus *creamy paste* and *whole* versus *sliced* [2212.08586].

A linguistic counterpart appears in “Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model.” There, COOkeD concerns procedural text rather than images. The model uses a shared two-layer **GRU** encoder with **1600** and **800** units over one-hot token inputs, coupled to two independent **MLP** decoders of **500 hidden units** each: one for verb prediction and one for multi-label state-change prediction. The tasks are separated at the output level but coupled through the shared encoder and the summed loss $L_{\text{total}} = L_{\text{action}} + L_{\text{state}}$. A bounded tangent-based loss is used in practice, and training uses **RMSProp** with learning rate **1e-4** for **201 epochs**. On the **693-sentence** Bosselut et al. benchmark, the model reaches **67%** average state-change accuracy versus **55%** in Bosselut et al. (2018), and about **81%** action accuracy, while using **10K** training samples rather than **65,815** carefully filtered recipes [2001.08665].

Related work broadens cooked-state recognition beyond fixed taxonomies. “One-shot recognition of any material anywhere using contrastive learning with physics-based rendering” introduces **MatSim**, a synthetic-to-real benchmark for material states that explicitly includes smooth transitions such as **raw → cooked → burned**, mixtures, and transparent containers. A ConvNeXt-based siamese encoder produces **512D L2-normalized embeddings** and, on real-image benchmarks, achieves **0.78** top-1 accuracy on Set 1 subclasses with masking, versus **0.67** for the best OpenCLIP H/14 baseline with cropping. Training on mixtures and transparent vessels improves generalization to real food and drink states [2212.00648].

Taken together, these works establish two distinct but complementary notions of COOkeD in food AI: one grounded in **fine-grained visual state discrimination**, the other in **textual state-change inference**. Both are driven by subtle transitions rather than coarse object identity.

## 3. “Cooked” data as Anti-Adversarial authorization in healthcare

In “DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection,” COOkeD denotes healthcare data that have been deliberately transformed into **Anti-Adversarial examples (AntiAdv)** before distribution. The central idea is not watermarking in the usual pre-distribution sense, but post-distribution control: models trained on cooked data perform normally only when deployment inputs are also cooked through the same process [2403.17755].

The formal objective is threefold: minimize performance of the cooked model $f_P$ on raw inputs $D_T$, preserve performance of $f_P$ on cooked inputs $D_P$ so that it matches a raw model $f_r$ on $D_T$ within tolerance $\epsilon$, and constrain the transformation so that similarity $d(X_T, X_P)$ remains bounded. In practice, the similarity constraint is implemented as **SSIM $\ge 0.8$** between each raw image and its cooked counterpart. AntiAdv examples are generated by minimizing a confidence-maximizing loss rather than maximizing a misclassification loss:
$$
x^* = \arg\min_\delta \mathcal{L}(f_\theta(x_i + \delta), y_i).
$$
Pseudo-labels are obtained from a surrogate raw-data model $\hat{y}_i = \arg\max_k f_r(x_i)_k$, and perturbations are optimized with **Adam** at learning rate **$5\times10^{-3}$** until the SSIM condition is met. The cooked model itself is then trained with **SGD** for **200 epochs**, batch size **128**, momentum **0.9**, and learning rate **$1\times10^{-3}$** on architectures including **ResNet18**, **ResNet50**, **VGG16**, and **ConvNeXt-T** [2403.17755].

The experimental logic is captured by two metrics: **Copyright Protection (CP)**, defined as $\mathcal{E}(f_P,D_T)-\mathcal{E}(f_r,D_T)$, and **Performance Preservation (PP)**, defined as $-|\mathcal{E}(f_P,D_P)-\mathcal{E}(f_r,D_T)|$. Lower CP indicates stronger protection; PP near zero indicates that cooked deployment preserves normal performance. On MedMNIST 2D data, **AntiAdv (Pseudo)** yields **CP −18.78, PP −0.67** for ResNet18, **CP −9.63, PP −0.91** for ResNet50, **CP −16.11, PP −0.56** for VGG16, and **CP −13.81, PP −1.59** for ConvNeXt-T. Random noise is substantially weaker, for example **CP −2.65, PP −1.61** on ResNet18. On 3D datasets, AntiAdv often outperforms Adv on both CP and PP in larger datasets; one reported example is **ResNet18 AntiAdv (Pseudo) CP −18.67, PP −1.75**, versus **Adv CP −6.03, PP −23.93** [2403.17755].

A common misunderstanding is to interpret DataCook as generic robustness augmentation. The paper’s deployment model is stricter: the system is designed so that **unauthorized raw test inputs cause the cooked model to fail or degrade sharply**, and access to the cooking procedure becomes the authorization mechanism. In this usage, COOkeD denotes controlled **input-space transformation as governance infrastructure**, not culinary state.

## 4. COOkeD as heterogeneous ensemble OOD detection

A separate and explicitly acronymic usage appears in “COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP,” where COOkeD means **CLIP for OOD detection with some extra knowledge**. The method addresses the observation that OOD detection performance is constrained by the capabilities of any single underlying classifier. Instead of choosing between the classical supervised setting and the zero-shot CLIP setting, COOkeD combines both with a third component, a linear probe on CLIP image features [2507.22576].

The three ensemble members are: a closed-world classifier $f_{\text{cls}}$ trained end-to-end on the in-distribution dataset, a zero-shot CLIP classifier using prompts of the form *“a photo of a [cls]”*, and a linear probe $f_{\text{probe}}$ trained on frozen CLIP image embeddings. Each member outputs softmax probabilities over the ID classes, and the ensemble prediction is the simple average
$$
p_{\text{ens}}(y=c\mid x)=\frac{p_{\text{cls}}+p_{\text{probe}}+p_{\text{zero}}}{3}.
$$
OOD scores are derived post hoc from this averaged distribution, chiefly by **entropy**
$$
H(p_{\text{ens}})=-\sum_{c=1}^C p_{\text{ens}}(y=c\mid x)\log p_{\text{ens}}(y=c\mid x),
$$
with **MSP** also reported. The method is intentionally hyperparameter-free beyond CLIP’s learned temperature **$\tau=100$**, and no temperature scaling or extra calibration is applied [2507.22576].

The implementation is lightweight relative to deep ensembles. The closed-world classifier is trained for **100 epochs** with **SGD**, momentum **0.9**, weight decay **$5\times10^{-4}$**, Nesterov enabled, and cosine annealing; the linear probe trains for **20 epochs** with the same optimizer and schedule. Images are processed at **224×224**. CLIP variants include **ViT-B/32**, **ViT-B/16**, **ViT-L/14**, and **ViT-H/14**. The approach is modular, post-hoc, and avoids CLIP fine-tuning [2507.22576].

Reported results show gains in both ID accuracy and OOD robustness. On **CIFAR-100**, COOkeD attains **86.16%** accuracy, versus **83.30%** for the standard ResNet18 classifier, **79.98%** for the probe, and **66.50%** for zero-shot CLIP. On **CIFAR-100-N**, which introduces about **40% real label noise** in training labels, COOkeD reaches **74.60%**, versus **62.22%** for the standard classifier. On **PatternNet**, COOkeD reaches **99.86%**, while zero-shot CLIP drops to **70.12%** under the paper’s “zero-shot shift” setting. On **ImageNet-1K**, COOkeD reaches **77.26%**, and on the full-spectrum covariate-shift benchmark it reaches **64.67%**, versus **48.77%** for the standard classifier [2507.22576].

The associated OOD performance is likewise strong. For example, with MSP scoring on CIFAR-100, COOkeD reports **84.32%** AUROC on CIFAR-10 and **93.75%** on SVHN, compared with **83.16/81.25** for the standard classifier. The paper further argues that **entropy of the averaged probabilities** is more robust than MSP, especially on far-OOD data, and that averaging per-model MSP values discards informative disagreement [2507.22576].

An important correction to casual descriptions is that COOkeD is **not** a single classifier and **not** merely a CLIP baseline. It is a heterogeneous ensemble whose strength lies in the complementarity of closed-world supervision, zero-shot language alignment, and probe-level feature reuse.

## 5. Formal and normative uses of “cooked”

In mathematics, the relevant meaning is explicitly figurative. “Characterization of Colorings Obtained by a Method of Szlam” separates the mechanism of Szlam’s Lemma from its chromatic-number consequence by defining **Szlam colorings** and **ordered Szlam colorings** of $\mathbb{R}^d$. The starting ingredients are a red-blue partition $R,B$ of $\mathbb{R}^d$ in which no blue pair is at unit distance, together with a finite set $F\subseteq\mathbb{R}^d$ such that no translate of $F$ lies entirely in $R$. From this, one “cooks up” a proper coloring by choosing, for each $v\in\mathbb{R}^d$, an $f\in F$ with $v+f\in B$, yielding the bound
$$
\chi(((\mathbb{R}^d,\|\cdot\|),1))\le |F|.
$$
The paper then characterizes **ordered Szlam colorings** via a dominance property: a coloring is ordered Szlam if and only if there is an ordering of the color set with respect to which the coloring is dominant. The paper includes a one-dimensional periodic example with colors *green*, *yellow*, and *white*, and remarks that a planar 7-color Hadwiger–Isbell tiling construction can be converted into a Szlam coloring [2411.04346].

A very different figurative use appears in “Bad, mad, and cooked: Moral responsibility for civilian harms in human-AI military teams.” Here, “cooked” refers to otherwise good human operators who are placed in **untenable decision-making environments through the processes of replacing human decision making with AI determinations in war making**. The chapter contrasts *bad apples*, who intentionally and deliberately kill civilians, with *mad apples*, who have lost their ability to navigate decisions in war, and *cooked apples*, whose ethical agency is compromised by automation bias, vigilance decrement, opacity, time pressure, deskilling, distributed responsibility, and organizational constraints. It proposes two mechanisms for analyzing such situations: **Decision Responsibility Probes** within a Critical Decision Method, and an **AI workplace health and safety framework** adapted to cognitive and psychological risks in targeting decisions [2211.06326].

These works show that outside ML for cooking or data transformation, COOkeD and “cooked” can function as **conceptual operators**. In the mathematical case, the term labels a constructive proof pattern; in the ethical case, it labels a sociotechnical condition in which human agency is distorted by system design.

## 6. Related cooked-state modeling: synthesis, mechanics, and functional food design

Adjacent literature, though not always using COOkeD as the system name, provides the broader technical substrate for cooked-state modeling. “Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devices” introduces an oven-based benchmark with **1,708 cooking sessions** across **30 recipes**, a **70/10/20** train/validation/test split, chef-annotated **basic**, **standard**, and **extended** edible states, and **224×224** RGB processing. Its generator $G_e$ is a compact FiLM-modulated U-Net with **8.68M parameters**, and its learned **Culinary Image Similarity (CIS)** metric is used both as a training loss and as an inference-time progress signal. On the curated oven dataset, COOkeD reports **FID 52.18** and **LPIPS 0.2145**, compared with **FID 75.42** and **LPIPS 0.2523** for Pix2Pix-Turbo and **FID 153.00** and **LPIPS 0.4711** for Pix2Pix. The quantized deployment stack occupies **45 MB** and runs synthesis at **1.2 s/frame** and CIS inference at about **330 ms** per live-target pair on a **5 TOPS NPU** [2511.16965].

Physical studies of cooked matter show that “cookedness” is not always monotone in simple visual or thermal variables. In cooked lutefisk, rheological measurements with a plate-plate rotational rheometer show that the storage modulus $G'$ depends primarily on **fillet size** and **period of fishing**, not systematically on **cooking time**, **cooking temperature**, or **salt amount** within the tested ranges. Large near-head fillets have $G' \approx 6000$–$10000$ Pa in the main season, whereas tail fillets have $G' \approx 2000$–$6000$ Pa; early-season lutefisk is softer in both classes. The phase angle remains low, with **$\tan\delta = 0.10 \pm 0.02$** in series 1 and 2 and **$0.08 \pm 0.02$** in series 3 [2112.08280].

Cooked pasta exhibits a different pattern. “Swelling, Softening and Elastocapillary Adhesion of Cooked Pasta” models cooking as water diffusion into a cylindrical or slab geometry, with diffusion coefficients **$D(80^\circ\mathrm{C}) = 5.682\times10^{-11}\,\mathrm{m^2/s}$** and **$D(100^\circ\mathrm{C}) = 9.921\times10^{-11}\,\mathrm{m^2/s}$** for **2 mm diameter spaghetti**. The modulus evolves through three regimes: a slow decrease in Regime I, a rapid several-orders-of-magnitude drop in Regime II, and a rubbery plateau in Regime III. The raw modulus is **$E_0 = 2.17\ \mathrm{GPa}\pm0.15$**, while the saturated modulus is about **135 kPa** at **$80^\circ\mathrm{C}$** and **50.8 kPa** at **$100^\circ\mathrm{C}$**. The paper further proposes a ruler-based elastocapillary measurement to estimate optimal cooking time [2201.09621].

Functional-food work extends the meaning of cookedness to controlled bioactivity after baking. In “How additive manufacturing can boost the bioactivity of baked functional foods,” 3D food printing is used to vary **layers**, **infill**, and baking conditions for cookies enriched with encapsulated grape-skin polyphenols. The best reported setting is **4 layers**, **30% infill**, baked at **$180^\circ$C for 10 min**, yielding **754.89 ± 41.89 μmol TR/gdry** DPPH activity and **436.74 ± 20.45 mg GAE/gdry** total phenolic content. Relative to free-extract cookies at a central condition, this corresponds to **+115%** antioxidant activity and **+173%** total phenolic content [2010.14385].

These studies collectively indicate that COOkeD, when interpreted through food science and machine perception, spans at least three technical levels: **visual appearance progression**, **mechanical and physicochemical state**, and **task-oriented decision thresholds**. This suggests that future uses of the term will likely continue to couple perceptual models with either deployment constraints, physical models, or formal decision rules rather than converging on a single canonical definition.

Source: https://www.emergentmind.com/topics/cooked