File uploaded with MsUpload

The Solar Oracle Walkman

2025-09-04T14:46:31Z

Abao: /* Experiments */

<gallery widths="220px" heights="400px">
File:WikiGrenier - Lecteur Sony Mini Disc 03.jpg|Sony MD player Sony MZ-R55.
File:Sony WM-F107.jpeg|Sony WM-F107 exhibited in Solar Biennale 2025 in Lausanne.
File:I-V tester made by Marc Dusseiller.jpg|The DIY I-V tester made by Marc Dusseiller.
</gallery>

[[太陽能神喻隨身聽]](chinese version)

=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.

=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.

==The first prototype v1==
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 in:to 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:
<gallery widths="220px" heights="400px">
File:DIY DSSC with screen printed pattern.jpg|DIY DSSC with screen printed pattern and hollyhock dye made by Shih Wei Chieh.
File:DIY DSSC with cyanotype pattern.jpg|DIY DSSC with cyanotype pattern made by Shih Wei Chieh.
File:I-V tester made by Marc Dusseiller_2.jpg|The measurement of the I-V curve tester is uploaded to Thingspeak and a local server, and can be fetched in Max/MSP.
</gallery>
===The 7-D voiceprint===
<code>V = [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, Σκ, A*]</code>
All features are computed on a 64-point resampled I–V trace and normalized by <code>Voc</code> and <code>Isc</code> to be invariant to irradiance and device size.

; FF (fill factor)
: <code>FF = (Vmpp * Impp) / (Voc * Isc)</code>

; 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:
: <code>Rs ≈ -ΔV/ΔI (evaluated near I ≈ Isc)</code>
: <code>Rsh ≈ -ΔV/ΔI (evaluated near V ≈ Voc)</code>
: Then report dimensionless forms:
: <code>Rs* = Rs * (Isc / Voc)</code>
: <code>Rsh* = Rsh * (Isc / Voc)</code>

; Σκ (curvature_sum)
: Sum of absolute turning angles along the 64-point polyline of the I–V trace: for each consecutive pair of segments <code>s_i = (ΔV_i, ΔI_i)</code>, accumulate
: <code>|angle(s_i, s_{i+1})|</code>, and report <code>Σκ = Σ |angle(s_i, s_{i+1})|</code>.
: (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 <code>(Isc * Voc)</code>.
: Discrete approximation on the resampled trace:
: <code>A* ≈ (Σ I[i] * ΔV[i]) / (Isc * Voc)</code>

===The preprocessing of fuzzy extraction with ml.scale and ml.principle===
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.

<gallery widths=500px heights=500px>
File:iv_curve_machine_learning.png|An example Max patch of the machine learning process for the raw seven features: [FF, Vmpp/Voc, Impp/Isc, Rs, Rsh, curvature_sum, area].
</gallery>
'''Solar Oracle Walkman v1 — Overview'''
<pre>
[Light]
▼
[Patterned DSSC “Mini-Disc”]
▼
[I–V Scanning / ESP32-S3 Tester]
▼
[Feature Extraction, 7D]
F = [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, Σκ, A*]
▼
ml.scale normalization
▼
ml.principle (PCA)
▼
input RAVE nn~ decoder
▼
Real-time audio output
Cross-modal mapping: I–V latent → audio latent
(mapping chosen by artistic / compositional context)
</pre>

==The 2nd prototype v2: RAVE as mediator and fuzzy extractor=
PCA is merely linear dimensionality reduction; it cannot guarantee "reproducibility under varying illumination" or "error correction for a binary key." Hence this design uses a fuzzy extractor: it converts the continuous latent vector z into an error-correctable, verifiable bitstring and outputs a stable key K, meeting both identity reproducibility and on-chain requirements.
We trained a custom I–V encoder in Google Colab (since the RAVE encoder cannot directly handle curve data, we trained a Conv1D architecture). The input is a continuous seven-dimensional "voiceprint" (FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, curvature_sum, area); the output is a latent vector z whose dimensionality aligns with the downstream audio decoder. Training uses triplet loss (pulling samples from the same cell together and pushing different cells apart) plus prior matching so that z follows the decoder’s Gaussian prior. Measurement noise and illumination drift are addressed via data augmentation (gain scaling, small noise, temporal jitter).
Because z is continuous and slightly noisy, we apply a further fuzzy extraction: z is first normalized and quantized, then passed through ECC to derive a stable key K, and finally we compute the on-chain commitment keccak256(K || salt). At first registration, we generate a pseudonymous index panel_id = keccak256("panel-id" || K) for cataloging; thereafter, each report need only reconstruct K' and compute keccak256(K' || salt), and the contract will automatically attribute the record to that panel_id, with no need to upload a human ID.
The audio decoder is trained independently on musical data (or we simply adopt an existing RAVE decoder); its sole job is to sonify z. Because the encoder enforces stability and geometric relations in z, repeated measurements of the same cell yield reproducible timbre and dynamics. This is a cross-modal mapping (I–V → audio latent): semantic order is maintained only on the encoder side, while the decoder-side mapping is entirely determined by artistic/compositional context (for example mapping to AM/FM, filtering, distortion, spatial parameters, etc.), with the goal being auditory/musical qualities rather than identity verification.
Overall, RAVE—more precisely, the combination of the I–V encoder and the RAVE decoder—serves as an intermediate layer. On one hand, it establishes a Verifiable Semantic Space (VSP): physical I–V measurements are embedded via contrastive learning into clustered yet separated geometric structures, and the fuzzy extractor yields the key K and the on-chain commitment. According to Jha et al. (2025), semantic stability relies on three core constraints: reconstruction — the transformed representation can be mapped back to its source; cycle-consistency — round-trip transforms preserve meaning; and vector-space preservation (VSP) — pairwise distances among embeddings remain preserved after mapping. On the other hand, it supports aesthetic generation: stable z values produce reproducible sonic styles and narratives. Philosophically, this does not equate the two media; rather, it anchors generation in an oracle, allowing aesthetics to unfold on a foundation of physical verification. Thus, RAVE becomes a "translational membrane": the inner layer preserves the geometry and commitments of the real (identity and causality), while the outer layer releases perceivable semantics and sound (aesthetics and expression). On-chain handles verification; off-chain handles computation and generation — a clean division of labor that both secures DSSC identity and preserves artistic freedom.

<gallery widths=500px heights=250px>
File:latent VSP comparison.png|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.
</gallery>

== Smart Contract Verification System ==
The smart contract of the Solar Oracle Walkman is deployed on Ethereum [https://sepolia.etherscan.io/address/0xeF19a90e5786dd0e89264F38f52CF81102db938e Sepolia Testnet] (contract address: <code>0xeF19a90e5786dd0e89264F38f52CF81102db938e</code>).
The contract functions as a decentralized digital notary, responsible for:
- Verifying signatures and data integrity (EIP-712)
- Managing submissions keyed by <code>panel_id</code>
- Storing and publishing commitments and metadata associated with I–V voiceprints

Note: Fuzzy extraction and derivation of the key K are all performed off-chain; the contract does not execute FE.

=== Verification Flow (On-chain) ===
Inputs (submitted from off-chain):
# <code>panel_id</code>: generated off-chain as <code>panel_id = keccak256("panel-id" || K)</code>
# <code>commitment</code>: computed off-chain as <code>commitment = keccak256(K || salt)</code>
# Signature: signed according to [[EIP-712]] standard
# <code>timestamp</code>, <code>nonce</code>
# (Optional) 7-dimensional voiceprint <code>[FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, curvature_sum, area]</code>, for visualization or research

Contract responsibilities:
# Verify EIP-712 signature, <code>timestamp</code>, and <code>nonce</code>
# Manage submissions indexed by <code>panel_id</code>; check <code>commitment</code> consistency with existing records (or update by business rules)
# Store <code>panel_id</code>, <code>commitment</code>, timestamp, and (optional) 7-D voiceprint; emit events for subscription

=== Panel ID and Identity Management (On-chain Perspective) ===
# Origin (off-chain): <code>panel_id = keccak256("panel-id" || K)</code>
# On-chain archiving: measurements are indexed and queried by <code>panel_id</code>
# Identity verification: off-chain reconstruction of <code>K'</code>, compute <code>keccak256(K' || salt)</code> and compare with on-chain <code>commitment</code>; contract only accepts the minimal required submission for proof and notarization

=== Security Mechanisms ===

==== EIP-712 Structured Signatures ====
The contract implements [[EIP-712]] standard, providing verifiable structured signatures for measurement submissions:

<syntaxhighlight lang="solidity">
struct IVMeasurement {
uint256 timestamp;
bytes32 panelId;
bytes32 commitment;
uint256[7] voiceprint;
bytes32 nonce;
}
</syntaxhighlight>

==== Data Integrity Checks ====
# Timestamp verification: prevent replay attacks
# Nonce mechanism: ensure uniqueness of each transaction
# Voiceprint range check: if 7-D voiceprint is provided, validate feature ranges
# Commitment consistency: check consistency of <code>commitment</code> for the same <code>panel_id</code>

=== Storage Structure ===

==== Measurement Records ====
Each verified measurement record includes:
# Panel ID: anonymized identifier of the DSSC (derived off-chain)
# Commitment: Keccak-256 commitment hash (computed off-chain)
# Timestamp: measurement time
# Voiceprint (optional): 7-D I–V voiceprint features
# Verification Status: verification result

=== Oracle Mechanism (On-chain Role) ===
The contract acts as one end of a [[Blockchain Oracle]], verifying and notarizing signed data submitted from off-chain:
# Data verification: signature, timestamp, nonce, and data integrity
# Identity confirmation: compare <code>commitment</code> by <code>panel_id</code>
# State update: update on-chain data structures
# Event emission: emit events upon successful verification

<gallery widths="700px" heights="400px">
File:solar oracle walkman smart contract.png|
</gallery>

'''Solar Oracle Walkman v2 — Overview'''
<pre>
[Light]
▼
[Patterned DSSC “Mini-Disc”]
▼
[Continuous I–V Scanning / ESP32-S3 Tester]
▼
[I–V Encoder (Conv1D trained in Colab) — off-chain]
Input: 7-D sequence [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, curvature_sum, area]
Output: latent vector z = (z1, z2, …, zn)
Training: triplet loss + prior matching
Augmentation: gain scaling / noise / temporal jitter
▼
[Fuzzy Extractor — off-chain]
z → normalization / quantization
→ ECC + helper data → stable key K
→ commit = keccak256(K || salt)
Enrollment: panel_id = keccak256("panel-id" || K)
Verification: new K′ → keccak256(K′ || salt) → compare with stored commitment
│
├───────────────► [Oracle / On-chain Path]
│ Package {pubkey, panel_id, commitment, timestamp, nonce, signature}
│ Smart contract: verify EIP-712 signature, timestamp, nonce
│ Smart contract: check keccak256(K′ || salt) == commitment (on verify calls)
│ Smart contract: store panel_id, commitment, metadata; emit events
│ Feedback: OK / FAIL
│
▼
[input RAVE nn~ decoder]
▼
Real-time audio output
Cross-modal mapping: I–V latent → audio latent
(mapping chosen by artistic / compositional context)
</pre>

=Oracle as Bridge in the Solar Oracle Walkman: a Minimal Cognitive Generative System=
Perception and machine learning can both be read as generative: they predict first, then correct. In Solar Oracle Walkman, the patterned DSSC’s I–V curve is measured and mapped into a latent state for sound, while a separate fuzzy extractor derives a verifiable key for on-chain proof. Here the oracle is the bridge: it carries a cryptographic claim (e.g., keccak256(K || salt)) from the physical world to the smart contract, keeping sonic imagination tethered to measurable traces.
Following Stinson’s generic mechanism, we make the in-skull/out-skull loop explicit. Out-skull: light, temperature, material; in-skull: models and priors (RAVE encoder–decoder, human listener), and—conceptually—on-chain verification as institutional memory. The Walkman is staged as a minimal cognitive generative system: a tiny theatre where measurement becomes prediction, error becomes style, and verification becomes composition.
Notes. RAVE is not the fuzzy extractor. The encoder yields a compact latent z for music; a standard fuzzy extractor (operating on z or the 7-D features) outputs (K, W) for identity stability and on-chain verification.

<pre>

[ GENERIC MECHANISM KIND ]
(Grounded inference: sense = abstract = validate = act)
│
──────────────────────────────────────────
│ │
[ COMPUTATIONAL MODEL ] [ TARGET SYSTEM ]
Solar Oracle Walkman human cognition
DSSC I–V measurement environment / sensory input
encoder + latent z_iv predictive priors + latent z_brain
fuzzy extractor -> K social/institutional memory
oracle verify (smart contract) (report/peer/record)
│ │
──────────────────────────────────────────
│
decoder│actions
│
[ controlled hallucinations (reality, music) ]

</pre>

Why oracle matters here. The oracle lets the piece claim: “this sound arose from this cell, now, under these conditions,” without freezing creativity; it anchors a generative act to evidence. The result is a system that is at once playful and accountable.
Conservative assessment. This is a performative engineering sketch of cognition, not a testable theory of consciousness; it sits at a respectful distance from formal consciousness science.

=Discussion=
# '''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.
# '''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.
# '''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. In this context, “oracle” refers not only to the blockchain bridge for off-chain data, but also resonates with its ancient meaning—an oracular revelation. When DSSC voiceprints serve only for verification, the oracle acts as a gatekeeper; but once endowed with semantic structure, capable of revealing relations among energy curves and translating them into sound space, it transcends verification and functions as a “machine of divination,” converting physical traces into messages from another world.

=References=
#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.
#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.
#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.
#https://www.hackteria.org/wiki/A_RAVE_and_starvation_synth_based_generative_sonic_device_powered_by_dye_sensitized_solar_cell
#https://github.com/shihweichieh2023/IVcurve_tester
#https://github.com/rjha18/vec2vec
#https://github.com/shihweichieh2023/solar-oracle-walkman

太陽能神諭隨身聽

2025-09-04T14:43:33Z

Abao: /* 實驗 */

<gallery widths="220px" heights="400px">
File:WikiGrenier - Lecteur Sony Mini Disc 03.jpg|Sony MD player Sony MZ-R55.
File:Sony WM-F107.jpeg|Sony WM-F107 exhibited in Solar Biennale 2025 in Lausanne.
File:I-V tester made by Marc Dusseiller.jpg|The DIY I-V tester made by Marc Dusseiller.
</gallery>
= 摘要 =
太陽能神諭隨身聽（Solar Oracle Walkman）是一個能源交易與聲音雕塑的探索。外觀參考了復古的 Sony WM-F107，而內部裝置則用於測量一片 6 × 6 公分手工製作、帶有藝術圖案的 DSSC（染料敏化太陽能電池）的 I–V 曲線，其 TiO₂ 多孔層透過氰版顯影或網版印刷製成。每一片「太陽能迷你碟」都會產生獨特的 I–V 聲紋（voiceprint），並透過 oracle（將鏈外資料安全橋接至區塊鏈的機制）傳送至智慧合約進行驗證。
概念上，這台隨身聽運作如同冷錢包：每片 DSSC 是一個實體代幣，而內建的 I–V 測試器則是其讀取器。完成驗證後，隨身聽會播放生成的、語意受限的音樂；鏈上的判定會作為播放的門檻。
在目前的 Max/MSP 原型中，量測到的 I–V 曲線會被分解為七個無量綱特徵 [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, Σκ, A*]，可選擇使用 PCA 降維，然後手動映射至 nn~ RAVE 解碼器的潛在輸入口，以達成可重現的聲音身份，而不依賴明確的語意結構。下一步，我們將記錄在不同光照下的連續 I–V 數據，並訓練 RAVE 編碼器以學習每片電池的緊湊且具魯棒性的潛在嵌入。這些嵌入會輸入至模糊提取（fuzzy extractor）流程（量化 → 輔助資料錯誤更正（ECC） → 雜湊），以導出穩定的金鑰。鏈上只會錨定該金鑰的承諾值，以維護隱私並允許驗證。若能保持向量空間的幾何關係，潛在空間中的距離將能反映光伏行為的差異，使裝置能作為一部「占卜機」，連結物質、感知與想像。

=生成系統中感知進展的聲音化=
感知與人工智慧都可以被理解為生成機制：它們不只是被動接收訊號，而是主動進行預測與修正。在隨身聽中，鏈上的聲紋扮演著錨點──以經驗痕跡來限制生成──而解碼器的表現力則像是召喚，在可驗證的範圍內支撐想像。
依據 Stinson 的「通用機制觀」以及 Feigl 的「對應模型」，我們設計了從量測（I–V 曲線）到潛在變數（音訊嵌入）的明確橋接。這使得作品能夠被視為一項實驗：每一個聲音決策都可以追溯至能量曲線上的可測變換。
<gallery widths=400 heights=300>
File:Stinson's generic mechanism.png|Stinson的通用機制圖表。
File:A logical empiricist picture of a scientific theory. Reproduced from Herbert Feigl 1970.png|科學理論的邏輯經驗主義圖表。轉載自 Herbert Feigl 1970。
File:diagram of solar oracle walkman.png|Stinson 和 Feigl 模型應用於目前專案結構的圖表。
</gallery>

= 實驗 =
太陽能神諭隨身聽主要由三個元件組成：I-V 曲線測試器、經氰版顯影處理或網版印刷圖案化的DSSC、智慧合約。每片迷你碟的 I–V 曲線會被量測並上傳至部署於 Sepolia 測試網的智慧合約進行驗證。一旦其 I–V 數據通過驗證，相應的音樂就會被生成並允許由隨身聽播放。每片「太陽能迷你碟」的聲音被期望具有可重現性、生成性與語意性——如同一段具備清晰機制的生成音樂，而非完全隨機。為了讓每片太陽能迷你碟成為生成裝置，我首先假設需要設計一個雜湊運算（hash function）來獲得每片太陽能玻璃的「聲紋 (V)」。雜湊運算是將輸入資料（例如數字、文字、檔案，或一組 I–V 曲線參數）送入數學函式或演算法以產生雜湊值的過程。雜湊演算法可以處理任意長度的輸入，但總是輸出固定長度的結果。

==第一個原型 v1==
一個DIY I–V曲線測試器被連接至電腦，其量測的16個I–V曲線點會透過序列通訊傳送到Max/MSP。I–V曲線通常用來分析太陽能電池的特性，因此在此被視為電池的「聲紋」，尤其是那些帶有氰版與網版印刷TiO₂層的DSSC。在本研究中，I–V曲線的形狀被拆解成七個特徵，並對每個特徵應用機器學習，讓電腦能夠「學會」其形狀。此方法預期能夠保證對光照強度的不變性，使太陽能迷你碟的音訊輸出在不同光照下依舊保持穩定再現。

===7-D Voice print（無量綱化）===
7D聲紋定義：<code>V = [FF (填充因子), Vmpp/Voc, Impp/Isc, Rs (串聯電阻), Rsh (旁路電阻), 曲率總和, I–V曲線面積]</code>。注意：這些計算均為無量綱（dimensionless），所謂無量綱特徵向量，指的是經過正規化後不再帶有物理單位（伏特、安培、歐姆）。例如透過比值Vmpp/Voc或Impp/Isc，這些特徵只捕捉相對形狀或行為，而與絕對大小無關。這在比較或分類不同光照條件下的I–V曲線時至關重要，因為它能確保差異反映的是裝置的內在特性，而不是量測條件的變動。

; FF (填充因子)
: <code>FF = (Vmpp * Impp) / (Voc * Isc)</code>
; Vmpp/Voc 與 Impp/Isc
: 無量綱比值，捕捉最大功率點的操作位置。
; Rs* 與 Rsh*（無量綱電阻估計）
: 先估計在重取樣曲線上的局部斜率：
: <code>Rs ≈ -ΔV/ΔI （在 I ≈ Isc 附近）</code>
: <code>Rsh ≈ -ΔV/ΔI （在 V ≈ Voc 附近）</code>
: 再轉換為無量綱形式：
: <code>Rs* = Rs * (Isc / Voc)</code>
: <code>Rsh* = Rsh * (Isc / Voc)</code>
; Σκ (曲率總和)
: 沿著 64 點重取樣 I–V 折線，累積各段角度變化：
: <code>Σκ = Σ |angle(s_i, s_{i+1})|</code>
: （直覺上：Σκ 越大，曲線「彎曲」程度越明顯）
; A* (I–V 曲線面積，正規化)
: 定義：從 V=0 到 V=Voc 的曲線下方面積，除以 <code>(Isc * Voc)</code>
: 離散近似：
: <code>A* ≈ (Σ I[i] * ΔV[i]) / (Isc * Voc)</code>

<gallery widths="220px" heights="400px">
File:DIY DSSC with screen printed pattern.jpg|施惟捷製作的帶有網版印刷圖案和蜀葵染料的 DIY DSSC。
File:DIY DSSC with cyanotype pattern.jpg|施惟捷製作的帶有藍曬圖案的 DIY DSSC。
File:I-V tester made by Marc Dusseiller_2.jpg|I-V 曲線測試儀的測量結果被上傳至 Thingspeak 和本機伺服器後並在 Max/MSP 中以fetch指令取得。
</gallery>
=== ml.scale 與 ml.principle 作為模糊提取的前處理 ===
為了讓每片太陽能迷你碟的聲音能被智慧合約穩定驗證並重現，Max/MSP 的 ml.* 函式庫是一個解決方案。
ml.scale：先將七個原始特徵正規化到0到1的範圍。
ml.principle：再進行 PCA（主成分分析），將七個值轉換至新的7維PCA空間。PCA是一種數學方法，能將數據旋轉並壓縮到較少維度，同時保留最多變異。
ml.principle 是 Max/MSP 內實作PCA的物件：
它會從訓練數據中學習主軸
並將新的數據投影至該降維空間
<gallery widths=500px heights=500px>
File:iv_curve_machine_learning.png|機器學習過程針對原始七個特徵的max patch範例：[FF、Vmpp/Voc、Impp/Isc、Rs、Rsh、curvature_sum、area]。
</gallery>

'''太陽能神諭隨身聽 v1 — 流程圖'''
<pre>
[光]
▼
[具圖案的 DSSC「迷你碟」]
▼
[I–V 掃描 / ESP32-S3 測試器]
▼
[特徵擷取，7 維]
F = [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, Σκ, A*]
▼
ml.scale 正規化
▼
ml.principle (PCA)
▼
輸入 RAVE nn~ 解碼器
▼
即時聲音輸出
跨模態映射：I–V 潛在向量 → 聲音潛在向量
（映射依藝術 / 作曲語境決定）
</pre>

== 第二個原型v2：RAVE 作為中介層與模糊提取 ==
在V1版本裡用ml.scale和ml.principle做的PCA僅僅是線性降維；它無法保證「在不同光照下仍能重現」和「二進位金鑰的錯誤更正」，因此我提出v2版本，這裡採用了模糊提取器：它將連續的潛在向量 <code>z</code> 轉換為可糾錯、可驗證的位元列，並輸出一個穩定的金鑰 <code>K</code>，以同時滿足身份可重現性與鏈上需求。

=== I–V 編碼器訓練（鏈下） ===
# 平台：Google Colab
# 架構：Conv1D（因 RAVE 編碼器無法直接處理曲線數據）
# 輸入：連續七維「聲紋」 <code>[FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, 曲率總和, 面積]</code>
# 輸出：潛在向量 <code>z = (z1, z2, …, zn)</code>（維度與下游音訊解碼器對齊）
# 訓練目標：triplet loss（相同電池樣本拉近，不同電池樣本推遠）+ 先驗匹配（使 z 服從解碼器的高斯先驗）
# 數據增強：增益縮放 / 小幅噪音 / 時序抖動

=== 模糊提取（鏈下） ===
# <code>z</code> → 正規化、量化
# 經 ECC（錯誤更正碼） → 導出穩定金鑰 <code>K</code>
# 計算承諾值：<code>commit = keccak256(K || salt)</code>

=== Panel ID 與註冊 ===
# 初始註冊：<code>panel_id = keccak256("panel-id" || K)</code>
# 後續驗證：重建 <code>K′</code> → 計算 <code>keccak256(K′ || salt)</code> → 與鏈上 commitment 比對
# 特點：合約自動將紀錄歸屬於 <code>panel_id</code>，無需上傳任何人類身份資訊

=== 音訊解碼器（鏈下） ===
# 訓練：獨立於音樂數據，或採用現有的 RAVE 解碼器
# 功能：將 <code>z</code> 聲音化
# 穩定性：由於編碼器強制 z 的幾何結構穩定，相同電池的重複量測能產生可重現的音色與動態
# 跨模態映射：<code>I–V → 聲音潛在向量</code>：語意秩序僅保留在編碼器端，解碼器端映射依藝術／作曲語境決定

=== 可驗證語意空間 (VSP) ===
根據 Jha 等人 (2025)，語意穩定性依賴三個核心約束：
# 重建性：轉換後的表徵能映射回來源
# 循環一致性：往返轉換能保持意義
# 向量空間保存 (VSP)：嵌入間的成對距離在映射後仍被保存

<gallery widths=500px heights=250px> File:latent VSP comparison.png|這張圖將目前流程與包含向量空間保存 (VSP) 的理想化設計進行了比較。左側實現了可重複性：每個 DSSC 都對應到潛在空間中的穩定位置，從而允許身份驗證，但無法在單元之間建立有意義的關係。右側，VSP 確保潛在空間中的成對距離反映了光伏特徵的差異，不僅提供了可重複性，還提供了關係意義。從這個角度來看，預言機從驗證真實性的守門人演變為揭示能量曲線在共享語義結構中如何關聯的「占卜機器」。 </gallery>

== 智慧合約驗證系統 ==

=== 概述 ===
Solar Oracle Walkman 的智慧合約部署於以太坊[https://sepolia.etherscan.io/address/0xeF19a90e5786dd0e89264F38f52CF81102db938e sepolia測試網]（合約地址：<code>0xeF19a90e5786dd0e89264F38f52CF81102db938e</code>）。合約作為去中心化的數位公證人，負責：
- 驗證簽名與資料完整性（EIP-712）
- 以 panel_id 為鍵管理提交
- 儲存並發佈與 I–V 聲紋關聯的承諾值（commitment）與中繼資料

注意：模糊提取（Fuzzy Extraction）與金鑰 K 的導出均在鏈下完成；本合約不執行 FE。

=== 驗證流程（鏈上） ===
輸入（由鏈下提交）：
# code>panel_id</code>：鏈下以 <code>panel_id = keccak256("panel-id" || K)</code> 生成
# <code>commitment</code>：鏈下以 <code>commitment = keccak256(K || salt)</code> 計算
# 簽名：依 [[EIP-712]] 標準對提交資料簽名
# <code>timestamp</code>、<code>nonce</code>
#（可選）7 維聲紋 <code>[FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, curvature_sum, area]</code>，用於可視化或研究

合約責任：
# 驗證 EIP-712 簽名、<code>timestamp</code> 與 <code>nonce</code>
# 以 <code>panel_id</code> 為索引管理提交，檢查 <code>commitment</code> 與既有紀錄的一致性（或依業務規則更新）
# 儲存 <code>panel_id</code>、<code>commitment</code>、時間戳與（可選）7 維聲紋；發佈事件以供訂閱

=== Panel ID 與身份管理（鏈上觀點） ===
# 來源（鏈下）：<code>panel_id = keccak256("panel-id" || K)</code>
# 鏈上歸檔：以 <code>panel_id</code> 為鍵歸檔與查詢測量紀錄
# 身份驗證：鏈下重建 <code>K'</code> 後計算 <code>keccak256(K' || salt)</code> 與鏈上 <code>commitment</code> 比對；合約僅接受比對結果所需之提交並進行存證

=== 安全機制 ===

==== EIP-712 結構化簽名 ====
合約實作 [[EIP-712]] 標準，為提交的測量資料提供可驗證的結構化簽名：

<syntaxhighlight lang="solidity">
struct IVMeasurement {
uint256 timestamp;
bytes32 panelId;
bytes32 commitment;
uint256[7] voiceprint;
bytes32 nonce;
}
</syntaxhighlight>

==== 數據完整性檢查 ====
# 時間戳驗證：防止重放攻擊
# Nonce 機制：確保每筆交易唯一性
# 聲紋範圍檢查：若提供 7 維聲紋則檢查範圍合理性
# 承諾一致性：對同一 panel_id 的 <code>commitment</code> 進行一致性檢查

=== 儲存結構 ===

==== 測量記錄 ====
每筆驗證通過的測量記錄包含：
# Panel ID：DSSC 的匿名化識別碼（鏈下導出）
# Commitment：Keccak-256 承諾雜湊（鏈下計算）
# Timestamp：測量時間戳
# Voiceprint（可選）：7 維 I–V 聲紋特徵
# Verification Status：驗證狀態

=== 神諭機制（鏈上角色） ===
合約作為[[區塊鏈神諭]]的一端，對鏈下送來的簽名資料進行鏈上驗證與存證：
# 數據驗證：簽名、時間戳、nonce 與資料完整性
# 身份確認：以 <code>panel_id</code> 比對 <code>commitment</code>
# 狀態更新：更新鏈上資料結構
# 事件觸發：驗證成功後發佈事件

'''太陽能神諭隨身聽 v2 — 概覽'''
<pre>
[光]
▼
[具圖案的 DSSC「迷你碟」]
▼
[連續 I–V 掃描 / ESP32-S3 測試器]
▼
[I–V 編碼器（在 Colab 以 Conv1D 訓練）— 鏈下]
輸入：7 維序列 [FF, Vmpp/Voc, Impp/Isc, Rs*, Rsh*, 曲率總和, 面積]
輸出：潛在向量 z = (z1, z2, …, zn)
訓練：triplet loss + 先驗匹配
增強：增益縮放 / 噪音 / 時序抖動
▼
[模糊提取器 — 鏈下]
z → 正規化 / 量化
→ ECC + 輔助資料 → 穩定金鑰 K
→ commit = keccak256(K || salt)
註冊：panel_id = keccak256("panel-id" || K)
驗證：新 K′ → keccak256(K′ || salt) → 與儲存的承諾值比對
│
├───────────────► [Oracle / 鏈上路徑]
│ 打包 {pubkey, panel_id, commitment, timestamp, nonce, signature}
│ 智慧合約：驗證 EIP-712 簽章、時間戳、nonce
│ 智慧合約：檢查 keccak256(K′ || salt) == commitment（於 verify 呼叫時）
│ 智慧合約：儲存 panel_id、commitment、metadata；發出事件
│ 回饋：OK / FAIL
│
▼
[輸入 RAVE nn~ 解碼器]
▼
即時聲音輸出
跨模態映射：I–V 潛在向量 → 聲音潛在向量
（映射依藝術 / 作曲語境決定）
</pre>

= 討論 =
# '''目前的狀態''' 神諭隨身聽作為一件簡單的藝術雕塑，能即時將 DSSC 的 I–V 曲線聲音化。經過正規化後，七個特徵的聲紋在光照變化下依然穩定。映射設計刻意保持極簡，使得可重現性的評估變得直接明瞭。在 Max/MSP 中已經建立了一條從感測到聲音的受控流程。感知與人工智慧被視為同一生成機制的兩個面向。此處「幻覺」的工作定義是：生成過程漂移到可接受證據與先驗之外。大腦會進行預測與修正；幻覺則是預測失配的極端情況。oracle 提供了外部錨點，使生成保持在可驗證的範圍內，同時保留創造性變異的空間。
# '''理論目前的作用''' Stinson 的「通用機制觀」激發我們將 DSSC–RAVE 與人類感知視為同一生成架構的不同實現。Feigl 的「對應模型」則驅動我們設計從觀測到潛在變數的明確橋接，讓每一個設計步驟都能追溯至可測痕跡。這些理論視角本身不是最終目標，而是資料集建立的設計指南映射的先驗假設偏移與變異的評估指標目前的限制在於缺乏向量空間保存 (VSP)；沒有 VSP，潛在空間只能作為身份的穩定註冊，卻無法保證不同電池之間的關聯意義。因此，oracle 主要只是一個驗證真偽的守門人，卻提供不了太多語意解釋。然而，若能引入 VSP，oracle 則可能演化成為一台真正的「神諭機」：不僅能驗證真實，還能揭示不同能量曲線之間的關係，將物理差異轉譯為另一領域中可解釋的結構。
# '''下一步''' 建立一個小而乾淨的 DSSC 聲紋訓練集，控制光照與溫度，並測試單調性與局部平滑性的先驗條件。原型化 vec2vec 式的約束：簡單的循環檢查與距離保持，並在保留測試集中記錄當「聲音鄰域」無法對應「能量曲線鄰域」的情況。研究輕量化推論目標與壓縮方法，以便未來能應用於行動裝置。探索能否將可追溯的能源紀錄註冊為來自聲紋的可驗證雜湊，並評估失效模式與防偽極限。「oracle」不僅指區塊鏈上的鏈外數據橋接機制，也回應了其古代語源——神廟的「神諭」或「占卜」。當 DSSC 聲紋僅用於驗證時，oracle 只是守門人；但當其承載語意結構，能揭示不同能量曲線之間的關聯並轉譯至聲音領域時，它就超越了驗證，開始運作如同一部「占卜機」，將物理世界的跡象轉換為另一個世界的訊息。

= 參考 =
#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.
#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.
#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.
#https://www.hackteria.org/wiki/A_RAVE_and_starvation_synth_based_generative_sonic_device_powered_by_dye_sensitized_solar_cell
#https://github.com/shihweichieh2023/IVcurve_tester
#https://github.com/rjha18/vec2vec
#https://github.com/shihweichieh2023/solar-oracle-walkman