The Solar Oracle Walkman

• 

  Sony MD player Sony MZ-R55.

• 

  Sony WM-F107 exhibited in Solar Biennale 2025 in Lausanne.

• 

  The DIY I-V tester made by Marc Dusseiller.

Abstract

The Solar Oracle Walkman is an exploration of energy trading and sound sculpture. Its exterior references the retro Sony WM-F107, while the device measures the I–V curve of a 6 × 6 cm handmade, artistically patterned DSSC whose TiO₂ porous layer is produced by cyanotype or screen printing. Each “solar mini-disc” yields a unique I–V voiceprint that is sent—via an oracle, a mechanism for securely bridging off-chain data to the blockchain—to a smart contract for verification. Conceptually, the Walkman operates like a cold wallet: each DSSC is a physical token, and the built-in I–V tester is its reader. Upon verification, the Walkman plays generative, semantically constrained music; the on-chain verdict gates playback. In the current Max/MSP prototype, the measured I–V curve is decomposed into seven dimensionless features [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, Σκ, A*], optionally reduced with PCA, then manually mapped to the latent inlets of an nn~ RAVE decoder, achieving reproducible sonic identity without an explicit semantic structure. Next, we will record continuous I–V data under varied illumination and train a RAVE encoder to learn compact, robust latent embeddings of each cell; these embeddings will feed a fuzzy-extractor pipeline (quantization → error correction with helper data → hash) to derive a stable key. On-chain we anchor only a commitment to that key, preserving privacy while enabling verification. With appropriate vector-space preservation, distances in latent space will reflect differences in photovoltaic behavior, allowing the device to act as a “divinatory machine” that links matter, perception, and imagination.

Generative systems for composition

Perception and AI can both be read as generative mechanisms: they do not merely receive signals but actively predict and correct them. In the Walkman, the on-chain voiceprint acts as an anchor—constraining generation with empirical traces—while the decoder’s expressivity acts as an invocation, sustaining imagination within verifiable bounds. Following Stinson’s generic-mechanism view and Feigl’s correspondence model, we design explicit bridges from measurement (I–V traces) to latent variables (audio embeddings). This keeps the artwork legible as an experiment: every sonic decision can be traced back to a measurable transformation on the energy curve.

• 

  Diagram of Stinson's generic mechanism.

• 

  A logical empiricist picture of a scientific theory. Reproduced from Herbert Feigl 1970.

• 

  Diagram of Stinson and Feigl's model applied to the current project structure.

Experiments

The solar oracle walkman is mainly made of 3 components: a I-V curve tester, a patterned solar mini disc and a smart contract. The I-V curve of each solar mini disc is measured and uploaded to a smart contract deployed on Sepolia Testnet to be verified, once its I-V data passes the verification, the corresponding music will be generated and allowed to play from the walkman accordingly. The sound of each "solar mini disc" are expected to be reproducible, generative and semantic, like a period of generative music with clear mechanism rather than completely randomness. To make each solar mini disc a generative device, I firstly assume I need to design a hash operation to gain a “ voiceprint (V)” for each solar glass; A hash operation is the process of feeding input data such as numbers, text, files, or a set of I-V curve parameters—into a mathematical function or algorithm to produce a hash value. Hash algorithms can take input of any length but always generate a fixed-length output. They are designed to be fast to compute, yield the same output for the same input, and produce drastically different outputs when the input changes even slightly.

Smart Contract Implementation

The Solar Oracle Walkman project includes a blockchain-based smart contract that validates and permanently stores IV voiceprint data from handmade DSSCs on the Ethereum network. Deployed on Sepolia testnet at address 0xeF19a90e5786dd0e89264F38f52CF81102db938e, the contract functions as a decentralized digital notary that verifies the authenticity of IV characteristic measurements through advanced security validation rules, EIP-712 signatures, and comprehensive data integrity checks. This immutable system ensures that each DSSC's unique electrical fingerprint can be cryptographically verified and stored permanently, creating a tamper-proof record of the device's performance characteristics while exploring how generative systems can serve as fuzzy extractors in cognitive energy transactions.

• 

Using ml.scale and ml.principle as preprocessing pipeline for fuzzy extraction of I–V curve features

A DIY I-V curve tester is connected to computer and the 16 points of I-V curve measurements are sent to the Max/MSP via serial communications. I-V curve is often used to analysis the characteristics of a solar cell, therefore it is ideally the "voiceprint" of the panel, especially the DSSC with cyanotyped and screen printded TiO2 layer. In this research, the shape of I-V curve is deconstructed into seven features that are often used to measure different characteristics of the panel, and then apply machine learning to each feature so the shape can be learned by the computer. This method is expected to ensures the irradiance invariance, so the reproducibility of the audio output of the solar mini disc will be resilient even it's put under different light exposure. The voiceprint V consists seven features of the I-V curve: V = [FF (Fill Factor), Vmpp/Voc, Impp/Isc, Rs (series resistance), Rsh (shunting resistance), sum of curvature, total area of the I-V curve]. Noticing the calculation made here are dimensionless. A dimensionless feature vector is a set of numerical descriptors that have been normalized so they no longer carry physical units such as volts, amperes, or ohms. By converting raw measurements into dimensionless quantities—for example, by taking ratios like Vmpp/Voc or Impp/Isc, the features capture only the relative shape or behavior of the data, independent of its absolute scale. This process is crucial when comparing or classifying I-V curves under varying light intensities, as it ensures that differences in the vector reflect intrinsic device characteristics rather than changes in measurement conditions. The feature definitions (scale-free) are listed below:

• 

  DIY DSSC with screen printed pattern and hollyhock dye made by Shih Wei Chieh.

• 

  DIY DSSC with cyanotype pattern made by Shih Wei Chieh.

• 

  The measurement of the I-V curve tester is uploaded to Thingspeak and a local server, and can be fetched in Max/MSP.

The 7-D voiceprint is defined as: V = [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, Σκ, A*] All features are computed on a 64-point resampled I–V trace and normalized by Voc and Isc to be invariant to irradiance and device size.

FF (fill factor)

FF = (Vmpp * Impp) / (Voc * Isc)

Vmpp/Voc and Impp/Isc

Scale-free ratios capturing the operating point at maximum power.

Rs* and Rsh* (dimensionless ohmic estimates)

First estimate the local slopes on the resampled curve:

Rs ≈ -ΔV/ΔI (evaluated near I ≈ Isc)

Rsh ≈ -ΔV/ΔI (evaluated near V ≈ Voc)

Then report dimensionless forms:

Rs* = Rs * (Isc / Voc)

Rsh* = Rsh * (Isc / Voc)

Σκ (curvature_sum)

Sum of absolute turning angles along the 64-point polyline of the I–V trace: for each consecutive pair of segments s_i = (ΔV_i, ΔI_i), accumulate

|angle(s_i, s_{i+1})|, and report Σκ = Σ |angle(s_i, s_{i+1})|.

(Intuition: larger Σκ indicates a more “bent” I–V shape.)

A* (normalized area under the I–V curve)

Definition: area from V=0 to V=Voc divided by (Isc * Voc).

Discrete approximation on the resampled trace:

A* ≈ (Σ I[i] * ΔV[i]) / (Isc * Voc)

Using ml.scale and ml.principle as preprocessing pipeline for fuzzy extraction of I–V curve features To make the sound of every solar mini disc reproducible and solid for smart contract verification, ml.* library in Max/MSP is a solution. Ml.* is a toolbox of machine learning algorithms implemented in Max to enable real-time interactive music and video with unsupervised machine learning, aimed at computer musicians and artists. The raw seven features are first sent to ml.scale object for the normalization in range from 0 to 1. The values are then passed to ml.principle, which performs Principal Component Analysis (PCA). This converts the seven values into a new 7-dimensional PCA space which is a mathematical method that rotates and compresses data into fewer dimensions while preserving as much variance as possible. ml.principle is the Max/MSP object that implements PCA: it learns the principal axes from training data, and then projects new data into that reduced space. I am not familiar with how fundamentally the mathematics works, however, I got an okay explanation from GPT below in the photo gallery.

• 

  An example Max patch of the machine learning process for the raw seven features: [FF, Vmpp/Voc, Impp/Isc, Rs, Rsh, curvature_sum, area].

• 

  The mathematical explanation for the principle component analysis (PCA) made by GPT.

From sound reproducibility to semantical composition

According to Jha et al. (2025), semantic stability is maintained through three key constraints: reconstruction (the translated representation can be mapped back to the source), cycle-consistency (round-trips preserve meaning), and vector space preservation (VSP), which ensures that pairwise distances among embeddings remain intact across the mapping. The 7-D voiceprint remains primarily a registry of unique identities, sufficient for reproducibility but unable to guarantee meaningful relational structure among different cells. This means that the smart contract verification built on the current pipeline can reliably answer whether a signal is genuine or not, but cannot provide further semantic interpretation of how one energy curve relates to another, which limit the design capacity of the generative music, and the difficulty to make the artwork to be align with the philosophy theories proposed in the project.

RAVE as fuzzy extractor for trustable oracle space and generative music engine

RAVE encoder + fuzzy extractor for trustable oracle space and generative music I use a trained encoder to produce compact, illumination-robust latent embeddings z from sequential I–V data (optionally guided by the 7-D voiceprint). These embeddings do not by themselves constitute a fuzzy extractor; rather, they feed into a standard fuzzy-extractor pipeline—quantization → error-correcting code with helper data → hash—to derive a stable key K from noisy measurements. In blockchain terms, we anchor only a commitment to that key commit = keccak256(K || salt2) on-chain; subsequent measurements reproduce K′ and submit commit′ = keccak256(K′ || salt2) for comparison. With this design, the oracle becomes a grounded interface: it accepts only evidence reconcilable with the physical device while leaving meaning construction to the off-chain sound engine. I will collect sequential I–V data under varied illumination and train the encoder with contrastive/triplet objectives so that repeated measurements of the same cell map nearby in latent space while different cells map farther apart (vector-space preservation). This yields not only reproducible identity but relational structure among cells—supporting semantic, generative composition.

• 

  This figure contrasts the current pipeline with an idealized design that incorporates vector space preservation (VSP). On the left, reproducibility is achieved: each DSSC maps to a stable position in latent space, allowing identity verification but without meaningful relationships across cells. On the right, VSP ensures that pairwise distances in the latent space reflect differences in photovoltaic features, providing not only reproducibility but also relational meaning. In this view, the oracle evolves from a gatekeeper that validates authenticity into a “divinatory machine” that reveals how energy curves relate within a shared semantic structure.

The sonification of hallucinations, an interesting strategy to implement theory in current prototype

Base on the brain prediction theory in the generative system. An interesting and simple strategy for composing is to foreground hallucination as a sonic principle after the system is built as suggested: I isolate what the model fails to explain. After training a RAVE with DSSC I–V sequences, each new measurement produces a latent embedding z1. Passing this through the encoder–decoder loop yields a reconstructed embedding z2. The residual vector r = z1 – z2 is then extracted: this residual represents precisely the component that lies outside the model’s learned prediction. While z1 captures the reproducible voiceprint of the cell, r embodies the “hallucination”—the deviation, noise, or anomaly that the model cannot assimilate. By routing only this residual into a separate RAVE decoder, the auditory output becomes a direct rendering of prediction mismatch. In this way, the system does not merely sonify energy curves, but also transforms epistemic failure into sound: hallucination is heard not as error, but as a generative surplus that destabilizes the boundary between perception and imagination.

  [IV curve]
       │
       ▼
  Encoder → z1
       │
       ▼
  Decoder → z2
       │
       ▼
  Residual r = z1 - z2
       │
       ▼
  Decoder2 → Sound of Hallucination

Discussion

1. Where things are now The oracle walkman works as a simple art sculpture that sonifies DSSC I–V curves in real time. The 7-feature voiceprint is stable across illumination changes after normalization. The mapping is deliberately minimal, which makes evaluation of reproducibility straightforward. A controlled pipeline from sensing to sound is established in Max/MSP. Perception and AI are treated as two sides of the same generative mechanism. The working definition of hallucination is generation that drifts beyond admissible evidence and priors. Brains predict and correct; hallucination is an extreme case of prediction mismatch. The oracle provides external anchors to keep generation within verifiable bounds while leaving room for creative variance.
2. What the theory is doing now Stinson’s generic-mechanism view motivates treating DSSC–RAVE and human perception as different instantiations of a common generative architecture. Feigl’s correspondence model motivates explicit bridges from observation to latent variables, so every design step is tied back to measurable traces. These theoretical lenses are not goals in themselves. They function as design guidelines for dataset building, priors for mapping, and evaluation metrics for drift and variance. Current limitations highlight the absence of vector space preservation (VSP). Without VSP, the latent space serves as a stable registry of identities but cannot guarantee relational meaning across cells. Thus, the oracle functions mainly as a gatekeeper that validates authenticity but offers little semantic interpretation. With VSP, however, the oracle could evolve into a “true oracle machine”: not only verifying truth but also revealing how different energy curves relate, translating physical differences into interpretable structures of another domain.
3. Next steps Build a small but clean training set of DSSC voiceprints with controlled illumination and temperature, then test monotonicity and local smoothness priors. Prototype vec2vec-style constraints: simple cycle checks and distance preservation on a held-out set; log when sonic neighborhoods fail to match energy-curve neighborhoods. Investigate lightweight inference targets and compression for future mobile use. Explore whether traceable energy records can be registered as verifiable hashes derived from sonic voiceprint, then evaluate failure modes and anti-counterfeiting limits. The design of the solar mini disc walkman is therefore not only a music project. It also opens a measured way to ask whether energy can be traceable and traded, and how a physical voiceprint might act as an oracle that links matter, perception, and computation. With stronger constraints such as VSP, this oracle could transcend its role as a verifier and begin to function as a “machine of divination,” translating one world into another without collapsing artistic variability.

References

1. Buckner, Cameron J. 2023. From Deep Learning to Rational Machines: What the History of Philosophy Can Teach Us about the Future of Artificial Intelligence. 1st ed. Oxford University PressNew York. https://doi.org/10.1093/oso/9780197653302.001.0001.
2. Stinson, Catherine. 2020. “From Implausible Artificial Neurons to Idealized Cognitive Models: Rebooting Philosophy of Artificial Intelligence.” Philosophy of Science 87 (4): 590–611. https://doi.org/10.1086/709730.
3. Jha, Rishi, Collin Zhang, Vitaly Shmatikov, and John X. Morris. 2025. “Harnessing the Universal Geometry of Embeddings.” arXiv:2505.12540. Preprint, arXiv, June 25. https://doi.org/10.48550/arXiv.2505.12540.
4. https://www.hackteria.org/wiki/A_RAVE_and_starvation_synth_based_generative_sonic_device_powered_by_dye_sensitized_solar_cell
5. https://github.com/shihweichieh2023/IVcurve_tester
6. https://github.com/rjha18/vec2vec
7. https://github.com/shihweichieh2023/solar-oracle-walkman