|
|
@@ -0,0 +1,537 @@
|
|
|
+<!doctype html>
|
|
|
+<html lang="en">
|
|
|
+<head>
|
|
|
+<meta charset="utf-8">
|
|
|
+<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
|
+<title>Field-to-Model: Correction Data Pipeline</title>
|
|
|
+<style>
|
|
|
+ :root {
|
|
|
+ --bg: #F2F1E7;
|
|
|
+ --bg-alt: #E7E4D5;
|
|
|
+ --panel-line: rgba(27,36,30,0.16);
|
|
|
+ --ink: #1B241E;
|
|
|
+ --ink-dim: rgba(27,36,30,0.64);
|
|
|
+ --ink-faint: rgba(27,36,30,0.42);
|
|
|
+ --line: rgba(27,36,30,0.14);
|
|
|
+ --accent: #B9711F;
|
|
|
+ --accent-soft: rgba(185,113,31,0.12);
|
|
|
+ --accent-ink: #FBF7EE;
|
|
|
+ --green: #1F7A5C;
|
|
|
+ --green-soft: rgba(31,122,92,0.10);
|
|
|
+ --red: #A3402E;
|
|
|
+ --red-soft: rgba(163,64,46,0.10);
|
|
|
+ --mono: ui-monospace, "SF Mono", "Cascadia Code", "Roboto Mono", Consolas, "Liberation Mono", monospace;
|
|
|
+ --serif: Georgia, "Iowan Old Style", "Palatino Linotype", "Book Antiqua", serif;
|
|
|
+ --shadow: 0 1px 2px rgba(27,36,30,0.06), 0 8px 24px rgba(27,36,30,0.05);
|
|
|
+ }
|
|
|
+
|
|
|
+ @media (prefers-color-scheme: dark) {
|
|
|
+ :root {
|
|
|
+ --bg: #101B16;
|
|
|
+ --bg-alt: #17251E;
|
|
|
+ --panel-line: rgba(233,231,220,0.14);
|
|
|
+ --ink: #E9E7DC;
|
|
|
+ --ink-dim: rgba(233,231,220,0.66);
|
|
|
+ --ink-faint: rgba(233,231,220,0.42);
|
|
|
+ --line: rgba(233,231,220,0.13);
|
|
|
+ --accent: #DDA35C;
|
|
|
+ --accent-soft: rgba(221,163,92,0.14);
|
|
|
+ --accent-ink: #17130C;
|
|
|
+ --green: #55C29A;
|
|
|
+ --green-soft: rgba(85,194,154,0.12);
|
|
|
+ --red: #D97F6C;
|
|
|
+ --red-soft: rgba(217,127,108,0.12);
|
|
|
+ --shadow: 0 1px 2px rgba(0,0,0,0.3), 0 8px 28px rgba(0,0,0,0.28);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ :root[data-theme="dark"] {
|
|
|
+ --bg: #101B16; --bg-alt: #17251E; --panel-line: rgba(233,231,220,0.14);
|
|
|
+ --ink: #E9E7DC; --ink-dim: rgba(233,231,220,0.66); --ink-faint: rgba(233,231,220,0.42);
|
|
|
+ --line: rgba(233,231,220,0.13); --accent: #DDA35C; --accent-soft: rgba(221,163,92,0.14);
|
|
|
+ --accent-ink: #17130C; --green: #55C29A; --green-soft: rgba(85,194,154,0.12);
|
|
|
+ --red: #D97F6C; --red-soft: rgba(217,127,108,0.12);
|
|
|
+ --shadow: 0 1px 2px rgba(0,0,0,0.3), 0 8px 28px rgba(0,0,0,0.28);
|
|
|
+ }
|
|
|
+ :root[data-theme="light"] {
|
|
|
+ --bg: #F2F1E7; --bg-alt: #E7E4D5; --panel-line: rgba(27,36,30,0.16);
|
|
|
+ --ink: #1B241E; --ink-dim: rgba(27,36,30,0.64); --ink-faint: rgba(27,36,30,0.42);
|
|
|
+ --line: rgba(27,36,30,0.14); --accent: #B9711F; --accent-soft: rgba(185,113,31,0.12);
|
|
|
+ --accent-ink: #FBF7EE; --green: #1F7A5C; --green-soft: rgba(31,122,92,0.10);
|
|
|
+ --red: #A3402E; --red-soft: rgba(163,64,46,0.10);
|
|
|
+ --shadow: 0 1px 2px rgba(27,36,30,0.06), 0 8px 24px rgba(27,36,30,0.05);
|
|
|
+ }
|
|
|
+
|
|
|
+ * { box-sizing: border-box; }
|
|
|
+ html, body { margin: 0; padding: 0; }
|
|
|
+ body {
|
|
|
+ background: var(--bg);
|
|
|
+ color: var(--ink);
|
|
|
+ font-family: var(--serif);
|
|
|
+ font-size: 17px;
|
|
|
+ line-height: 1.65;
|
|
|
+ -webkit-font-smoothing: antialiased;
|
|
|
+ }
|
|
|
+ a { color: var(--accent); }
|
|
|
+ a:focus-visible, button:focus-visible { outline: 2px solid var(--accent); outline-offset: 3px; }
|
|
|
+
|
|
|
+ .wrap { max-width: 800px; margin: 0 auto; padding: 56px 24px 96px; }
|
|
|
+
|
|
|
+ .eyebrow {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 12px;
|
|
|
+ letter-spacing: 0.11em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ color: var(--accent);
|
|
|
+ display: inline-flex;
|
|
|
+ align-items: center;
|
|
|
+ gap: 8px;
|
|
|
+ margin-bottom: 18px;
|
|
|
+ }
|
|
|
+ .eyebrow::before {
|
|
|
+ content: "";
|
|
|
+ width: 7px; height: 7px;
|
|
|
+ background: var(--accent);
|
|
|
+ border-radius: 50%;
|
|
|
+ display: inline-block;
|
|
|
+ }
|
|
|
+
|
|
|
+ h1 {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-weight: 600;
|
|
|
+ font-size: clamp(28px, 4.4vw, 38px);
|
|
|
+ line-height: 1.18;
|
|
|
+ letter-spacing: -0.01em;
|
|
|
+ text-wrap: balance;
|
|
|
+ margin: 0 0 18px;
|
|
|
+ color: var(--ink);
|
|
|
+ }
|
|
|
+ .subtitle {
|
|
|
+ font-family: var(--serif);
|
|
|
+ font-style: italic;
|
|
|
+ font-size: 19px;
|
|
|
+ color: var(--ink-dim);
|
|
|
+ max-width: 62ch;
|
|
|
+ text-wrap: balance;
|
|
|
+ margin: 0 0 8px;
|
|
|
+ }
|
|
|
+ .meta-row {
|
|
|
+ display: flex;
|
|
|
+ flex-wrap: wrap;
|
|
|
+ gap: 18px;
|
|
|
+ margin-top: 28px;
|
|
|
+ padding-top: 20px;
|
|
|
+ border-top: 1px solid var(--line);
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 12px;
|
|
|
+ color: var(--ink-faint);
|
|
|
+ }
|
|
|
+ .meta-row span b { color: var(--ink-dim); font-weight: 600; }
|
|
|
+
|
|
|
+ nav.toc {
|
|
|
+ margin-top: 32px;
|
|
|
+ padding: 18px 20px;
|
|
|
+ border: 1px solid var(--line);
|
|
|
+ border-radius: 10px;
|
|
|
+ background: var(--bg-alt);
|
|
|
+ }
|
|
|
+ nav.toc p {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 11px;
|
|
|
+ letter-spacing: 0.09em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ color: var(--ink-faint);
|
|
|
+ margin: 0 0 10px;
|
|
|
+ }
|
|
|
+ nav.toc ol {
|
|
|
+ margin: 0; padding: 0; list-style: none;
|
|
|
+ columns: 2;
|
|
|
+ column-gap: 24px;
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 13px;
|
|
|
+ }
|
|
|
+ nav.toc li { break-inside: avoid; margin-bottom: 8px; }
|
|
|
+ nav.toc a { text-decoration: none; color: var(--ink-dim); }
|
|
|
+ nav.toc a:hover { color: var(--accent); }
|
|
|
+ nav.toc a .n { color: var(--ink-faint); margin-right: 6px; }
|
|
|
+
|
|
|
+ section { margin-top: 64px; scroll-margin-top: 24px; }
|
|
|
+ .sec-head {
|
|
|
+ display: flex;
|
|
|
+ align-items: baseline;
|
|
|
+ gap: 12px;
|
|
|
+ border-bottom: 1px solid var(--line);
|
|
|
+ padding-bottom: 10px;
|
|
|
+ margin-bottom: 22px;
|
|
|
+ }
|
|
|
+ .sec-head .n {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 13px;
|
|
|
+ color: var(--accent);
|
|
|
+ letter-spacing: 0.04em;
|
|
|
+ }
|
|
|
+ .sec-head h2 {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 13px;
|
|
|
+ letter-spacing: 0.1em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ font-weight: 600;
|
|
|
+ color: var(--ink);
|
|
|
+ margin: 0;
|
|
|
+ }
|
|
|
+
|
|
|
+ p { margin: 0 0 16px; color: var(--ink); }
|
|
|
+ p.lead { font-size: 18px; color: var(--ink-dim); }
|
|
|
+ strong { color: var(--ink); }
|
|
|
+
|
|
|
+ ul.principles, ul.risks { list-style: none; margin: 0; padding: 0; display: grid; gap: 12px; }
|
|
|
+ ul.principles li, ul.risks li {
|
|
|
+ border: 1px solid var(--line);
|
|
|
+ background: var(--bg-alt);
|
|
|
+ border-radius: 10px;
|
|
|
+ padding: 14px 16px;
|
|
|
+ display: flex;
|
|
|
+ gap: 12px;
|
|
|
+ align-items: flex-start;
|
|
|
+ }
|
|
|
+ ul.principles li::before { content: "✓"; flex: 0 0 auto; width: 20px; color: var(--green); font-family: var(--mono); font-weight: 700; }
|
|
|
+ ul.risks li::before { content: "!"; flex: 0 0 auto; width: 20px; color: var(--red); font-family: var(--mono); font-weight: 700; text-align: center; }
|
|
|
+ ul.principles li .txt, ul.risks li .txt { flex: 1 1 auto; min-width: 0; }
|
|
|
+ ul.principles li .t, ul.risks li .t { font-weight: 700; color: var(--ink); display: block; margin-bottom: 3px; }
|
|
|
+ ul.principles li .d, ul.risks li .d { color: var(--ink-dim); font-size: 15.5px; }
|
|
|
+
|
|
|
+ .panel {
|
|
|
+ border: 1px solid var(--panel-line);
|
|
|
+ border-radius: 12px;
|
|
|
+ background: var(--bg-alt);
|
|
|
+ box-shadow: var(--shadow);
|
|
|
+ margin: 24px 0;
|
|
|
+ overflow: hidden;
|
|
|
+ }
|
|
|
+ .panel .bar {
|
|
|
+ display: flex;
|
|
|
+ align-items: center;
|
|
|
+ gap: 8px;
|
|
|
+ padding: 10px 16px;
|
|
|
+ border-bottom: 1px solid var(--panel-line);
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 11.5px;
|
|
|
+ letter-spacing: 0.06em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ color: var(--ink-faint);
|
|
|
+ }
|
|
|
+ .panel .bar .dot { width: 7px; height: 7px; border-radius: 50%; background: var(--ink-faint); opacity: 0.5; }
|
|
|
+ .panel .body { padding: 18px; overflow-x: auto; }
|
|
|
+ .panel .body .mermaid { margin: 0; display: flex; justify-content: center; min-width: 560px; }
|
|
|
+
|
|
|
+ table {
|
|
|
+ width: 100%;
|
|
|
+ border-collapse: collapse;
|
|
|
+ font-size: 15px;
|
|
|
+ }
|
|
|
+ .table-scroll { overflow-x: auto; border: 1px solid var(--line); border-radius: 10px; }
|
|
|
+ table thead th {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 11px;
|
|
|
+ letter-spacing: 0.07em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ color: var(--ink-faint);
|
|
|
+ text-align: left;
|
|
|
+ padding: 12px 16px;
|
|
|
+ background: var(--bg-alt);
|
|
|
+ border-bottom: 1px solid var(--line);
|
|
|
+ white-space: nowrap;
|
|
|
+ }
|
|
|
+ table tbody td {
|
|
|
+ padding: 13px 16px;
|
|
|
+ border-bottom: 1px solid var(--line);
|
|
|
+ vertical-align: top;
|
|
|
+ color: var(--ink-dim);
|
|
|
+ }
|
|
|
+ table tbody tr:last-child td { border-bottom: none; }
|
|
|
+ table tbody td.field { font-family: var(--mono); font-size: 13.5px; color: var(--ink); white-space: nowrap; }
|
|
|
+ table code { font-family: var(--mono); font-size: 0.92em; background: var(--accent-soft); color: var(--accent); padding: 1px 6px; border-radius: 4px; }
|
|
|
+
|
|
|
+ .pill {
|
|
|
+ display: inline-block;
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 10.5px;
|
|
|
+ letter-spacing: 0.05em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ padding: 3px 9px;
|
|
|
+ border-radius: 100px;
|
|
|
+ font-weight: 600;
|
|
|
+ }
|
|
|
+ .pill.open { background: var(--accent-soft); color: var(--accent); }
|
|
|
+ .pill.decided { background: var(--green-soft); color: var(--green); }
|
|
|
+
|
|
|
+ .boundary {
|
|
|
+ border: 1px dashed var(--panel-line);
|
|
|
+ border-radius: 12px;
|
|
|
+ padding: 20px 22px;
|
|
|
+ background: var(--bg-alt);
|
|
|
+ }
|
|
|
+ .boundary .t {
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 11px;
|
|
|
+ letter-spacing: 0.08em;
|
|
|
+ text-transform: uppercase;
|
|
|
+ color: var(--ink-faint);
|
|
|
+ margin-bottom: 8px;
|
|
|
+ }
|
|
|
+
|
|
|
+ footer {
|
|
|
+ margin-top: 80px;
|
|
|
+ padding-top: 24px;
|
|
|
+ border-top: 1px solid var(--line);
|
|
|
+ font-family: var(--mono);
|
|
|
+ font-size: 12px;
|
|
|
+ color: var(--ink-faint);
|
|
|
+ display: flex;
|
|
|
+ justify-content: space-between;
|
|
|
+ flex-wrap: wrap;
|
|
|
+ gap: 8px;
|
|
|
+ }
|
|
|
+
|
|
|
+ @media (max-width: 640px) {
|
|
|
+ nav.toc ol { columns: 1; }
|
|
|
+ .wrap { padding: 40px 18px 72px; }
|
|
|
+ }
|
|
|
+</style>
|
|
|
+</head>
|
|
|
+<body>
|
|
|
+<div class="wrap">
|
|
|
+
|
|
|
+ <div class="eyebrow">Internal discussion draft — no implementation started</div>
|
|
|
+ <h1>Field-to-Model: a correction‑data pipeline for PalmOilAI</h1>
|
|
|
+ <p class="subtitle">Every grade a harvester corrects in the field is a labeled training example. Right now it never leaves the phone. This document proposes how it gets to us — quietly, reliably, and without asking the harvester to do anything.</p>
|
|
|
+
|
|
|
+ <div class="meta-row">
|
|
|
+ <span><b>Scope</b> — mobile app → dedicated ingestion server</span>
|
|
|
+ <span><b>Status</b> — brainstorm, pending decisions marked below</span>
|
|
|
+ <span><b>Owner</b> — palm_oil_mobile</span>
|
|
|
+ </div>
|
|
|
+
|
|
|
+ <nav class="toc" aria-label="Table of contents">
|
|
|
+ <p>Contents</p>
|
|
|
+ <ol>
|
|
|
+ <li><a href="#context"><span class="n">01</span>Why this exists</a></li>
|
|
|
+ <li><a href="#principles"><span class="n">02</span>Agreed principles</a></li>
|
|
|
+ <li><a href="#architecture"><span class="n">03</span>System architecture</a></li>
|
|
|
+ <li><a href="#flow"><span class="n">04</span>Sync flow, step by step</a></li>
|
|
|
+ <li><a href="#data"><span class="n">05</span>What actually gets sent</a></li>
|
|
|
+ <li><a href="#decisions"><span class="n">06</span>Open decisions</a></li>
|
|
|
+ <li><a href="#risks"><span class="n">07</span>Risks & mitigations</a></li>
|
|
|
+ <li><a href="#boundary"><span class="n">08</span>Out of scope</a></li>
|
|
|
+ </ol>
|
|
|
+ </nav>
|
|
|
+
|
|
|
+ <section id="context">
|
|
|
+ <div class="sec-head"><span class="n">01</span><h2>Why this exists</h2></div>
|
|
|
+ <p class="lead">The app already lets a harvester correct the AI's grading — change a class, remove a false detection, or draw a box around a bunch the model missed. That correction is never destructive: the AI's original call is kept, and the human's edit sits alongside it.</p>
|
|
|
+ <p>That pairing — <em>what the model said</em> next to <em>what was actually true</em> — is exactly the labeled data needed to train the next generation of the model. Today it's trapped in a local SQLite database on each harvester's phone and goes nowhere. This document proposes a pipeline to collect it centrally, without adding a single step to the harvester's workflow.</p>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="principles">
|
|
|
+ <div class="sec-head"><span class="n">02</span><h2>Agreed principles</h2></div>
|
|
|
+ <p>Three calls have already been made in discussion; everything downstream in this document follows from them.</p>
|
|
|
+ <ul class="principles">
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">A dedicated, standalone ingestion server</span>
|
|
|
+ <span class="d">Not bolted onto <code>server-desktop</code> or any operational service. If it's slow or down, nothing a harvester relies on in the field is affected — the data simply queues on-device until it's reachable again.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">Fully silent, background sync</span>
|
|
|
+ <span class="d">No "sync now" button, no progress bar, no prompt. The harvester's job is to scan and correct; getting that data to us is entirely the app's problem, running only when connectivity allows.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">The app tracks its own upload state</span>
|
|
|
+ <span class="d">Every record knows locally whether it's been sent. No handshake with the server is needed to know what's still pending — a local flag is the source of truth, which makes the whole thing resumable after any interruption.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ </ul>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="architecture">
|
|
|
+ <div class="sec-head"><span class="n">03</span><h2>System architecture</h2></div>
|
|
|
+ <p>The phone is the only place data is created. Everything after that is designed so a slow or offline server never blocks a harvester from scanning.</p>
|
|
|
+ <div class="panel">
|
|
|
+ <div class="bar"><span class="dot"></span>figure 1 — data path from bunch to model</div>
|
|
|
+ <div class="body">
|
|
|
+<pre class="mermaid">
|
|
|
+flowchart LR
|
|
|
+ classDef device fill:#00000000,stroke-width:1px;
|
|
|
+ classDef server fill:#00000000,stroke-width:1px;
|
|
|
+ classDef future stroke-dasharray: 4 3;
|
|
|
+
|
|
|
+ H(["Harvester"]) --> P["Phone: scan + correct"]
|
|
|
+ P --> L[("Local SQLite\nscans + corrections\n+ upload state")]
|
|
|
+ L -- "background sync\nWi-Fi / connectivity trigger" --> S["Dedicated Ingestion Server"]
|
|
|
+ S --> R[("Raw Store\nimages + AI result + correction")]
|
|
|
+ R --> T["Retraining Pipeline\n(offline, periodic — future work)"]
|
|
|
+ T --> M["New Model Version"]
|
|
|
+ M -.-> P
|
|
|
+
|
|
|
+ class P,L device
|
|
|
+ class S,R server
|
|
|
+ class T,M future
|
|
|
+</pre>
|
|
|
+ </div>
|
|
|
+ </div>
|
|
|
+ <p>The dashed link back to the phone is deliberately out of scope for this document — how a new model version reaches devices is a separate rollout question for later.</p>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="flow">
|
|
|
+ <div class="sec-head"><span class="n">04</span><h2>Sync flow, step by step</h2></div>
|
|
|
+ <p>The harvester only ever sees the left-most lane. Everything else happens whenever the phone next has connectivity, with no user-visible state.</p>
|
|
|
+ <div class="panel">
|
|
|
+ <div class="bar"><span class="dot"></span>figure 2 — from a correction to an uploaded record</div>
|
|
|
+ <div class="body">
|
|
|
+<pre class="mermaid">
|
|
|
+sequenceDiagram
|
|
|
+ participant H as Harvester
|
|
|
+ participant App as App
|
|
|
+ participant DB as Local DB
|
|
|
+ participant Sync as Background Sync
|
|
|
+ participant Srv as Ingestion Server
|
|
|
+
|
|
|
+ H->>App: Scan bunch, correct a grade
|
|
|
+ App->>DB: Save record (uploadedAt = none)
|
|
|
+ Note right of DB: Sits queued.<br/>Nothing for the harvester to do.
|
|
|
+ loop Whenever the OS wakes it
|
|
|
+ Sync->>DB: Which records are unsynced?
|
|
|
+ alt connectivity available
|
|
|
+ Sync->>Srv: Upload batch (image + AI result + correction)
|
|
|
+ Srv-->>Sync: Acknowledged
|
|
|
+ Sync->>DB: Mark uploadedAt = now
|
|
|
+ else no connectivity
|
|
|
+ Sync->>Sync: Do nothing, try again next wake
|
|
|
+ end
|
|
|
+ end
|
|
|
+</pre>
|
|
|
+ </div>
|
|
|
+ </div>
|
|
|
+ <p>One edge case worth naming: a harvester can correct a scan <em>after</em> it already uploaded — reviewing a batch a few days later, say. So "synced" needs to track the correction separately from the original scan, or a late correction silently never makes it off the device.</p>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="data">
|
|
|
+ <div class="sec-head"><span class="n">05</span><h2>What actually gets sent</h2></div>
|
|
|
+ <p>Per scan, the payload pairs the model's original call with whatever the harvester changed it to — that pairing is the entire point of the exercise.</p>
|
|
|
+ <div class="table-scroll">
|
|
|
+ <table>
|
|
|
+ <thead>
|
|
|
+ <tr><th>Field</th><th>Where it comes from</th><th>Why it matters for training</th></tr>
|
|
|
+ </thead>
|
|
|
+ <tbody>
|
|
|
+ <tr><td class="field">image</td><td>Camera capture</td><td>The actual training input</td></tr>
|
|
|
+ <tr><td class="field">ai_detections[]</td><td>On-device inference</td><td>The model's original boxes, classes, confidence — what it got right or wrong</td></tr>
|
|
|
+ <tr><td class="field">human_correction[]</td><td>Harvester review</td><td>The corrected boxes/classes, or a removed false positive — the actual label</td></tr>
|
|
|
+ <tr><td class="field">model_version</td><td>App build</td><td>Which model produced the AI call, so improvement can be measured generation over generation</td></tr>
|
|
|
+ <tr><td class="field">captured_at</td><td>App</td><td>Chronological + seasonal context for the dataset</td></tr>
|
|
|
+ <tr><td class="field">device_id</td><td>App</td><td>Coarse debugging / dedup, not tied to a personal identity</td></tr>
|
|
|
+ <tr><td class="field">uploaded_at</td><td>Sync engine, local only</td><td>Never sent — this is the idempotency marker that makes sync resumable</td></tr>
|
|
|
+ </tbody>
|
|
|
+ </table>
|
|
|
+ </div>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="decisions">
|
|
|
+ <div class="sec-head"><span class="n">06</span><h2>Open decisions</h2></div>
|
|
|
+ <p>Three things still need a call before this can move from brainstorm to plan.</p>
|
|
|
+ <div class="table-scroll">
|
|
|
+ <table>
|
|
|
+ <thead>
|
|
|
+ <tr><th>Question</th><th>Leaning</th><th>Trade-off</th><th></th></tr>
|
|
|
+ </thead>
|
|
|
+ <tbody>
|
|
|
+ <tr>
|
|
|
+ <td class="field">Wi-Fi only, or any connection?</td>
|
|
|
+ <td>Wi-Fi only to start</td>
|
|
|
+ <td>Slower data arrival, but no surprise mobile-data cost for a harvester who never asked for this</td>
|
|
|
+ <td><span class="pill open">Open</span></td>
|
|
|
+ </tr>
|
|
|
+ <tr>
|
|
|
+ <td class="field">Upload every scan, or only corrected ones?</td>
|
|
|
+ <td>Every reviewed scan</td>
|
|
|
+ <td>More storage, but "the AI was right, no correction needed" is itself a useful training signal, not noise</td>
|
|
|
+ <td><span class="pill open">Open</span></td>
|
|
|
+ </tr>
|
|
|
+ <tr>
|
|
|
+ <td class="field">Silent upload, or an opt-in toggle?</td>
|
|
|
+ <td>Depends on device ownership</td>
|
|
|
+ <td>Opt-in adds friction and drop-off; silent upload only sits right if these are company-managed devices</td>
|
|
|
+ <td><span class="pill open">Open</span></td>
|
|
|
+ </tr>
|
|
|
+ <tr>
|
|
|
+ <td class="field">Dedicated, standalone server</td>
|
|
|
+ <td>Decided</td>
|
|
|
+ <td>Keeps ingestion downtime from ever touching the app's core detection features</td>
|
|
|
+ <td><span class="pill decided">Decided</span></td>
|
|
|
+ </tr>
|
|
|
+ <tr>
|
|
|
+ <td class="field">Fully background, no harvester-facing sync UI</td>
|
|
|
+ <td>Decided</td>
|
|
|
+ <td>Zero added burden on the harvester's workflow</td>
|
|
|
+ <td><span class="pill decided">Decided</span></td>
|
|
|
+ </tr>
|
|
|
+ </tbody>
|
|
|
+ </table>
|
|
|
+ </div>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="risks">
|
|
|
+ <div class="sec-head"><span class="n">07</span><h2>Risks & mitigations</h2></div>
|
|
|
+ <ul class="risks">
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">Ingestion server is down or slow</span>
|
|
|
+ <span class="d">No effect on scanning or correcting — records simply stay queued locally and upload on the next successful sync. This is the entire reason it's a separate server.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">Bandwidth cost on a harvester's personal data plan</span>
|
|
|
+ <span class="d">Addressed by the Wi-Fi-only decision above, once confirmed.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">A correction made after the scan already synced gets missed</span>
|
|
|
+ <span class="d">Track correction-sync state separately from scan-sync state, so an edit made days later still gets picked up on the next background pass.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ <li>
|
|
|
+ <div class="txt">
|
|
|
+ <span class="t">Raw storage grows indefinitely</span>
|
|
|
+ <span class="d">Not a phone-side concern, but worth flagging for the server design — periodic archival into a proper training dataset, rather than an ever-growing inbox.</span>
|
|
|
+ </div>
|
|
|
+ </li>
|
|
|
+ </ul>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <section id="boundary">
|
|
|
+ <div class="sec-head"><span class="n">08</span><h2>Out of scope</h2></div>
|
|
|
+ <div class="boundary">
|
|
|
+ <div class="t">Where this document stops</div>
|
|
|
+ <p style="margin-bottom:0;">The app's responsibility ends at <strong>reliably getting corrected data to the server</strong>. Aggregating uploads into a training dataset, running retraining, evaluating a new model, and distributing it back to devices are separate initiatives — worth planning, but deliberately not decided here.</p>
|
|
|
+ </div>
|
|
|
+ </section>
|
|
|
+
|
|
|
+ <footer>
|
|
|
+ <span>Field-to-Model — correction data pipeline</span>
|
|
|
+ <span>Discussion draft, no code changes made</span>
|
|
|
+ </footer>
|
|
|
+
|
|
|
+</div>
|
|
|
+
|
|
|
+<script src="https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.min.js"></script>
|
|
|
+<script>
|
|
|
+ var prefersDark = window.matchMedia && window.matchMedia('(prefers-color-scheme: dark)').matches;
|
|
|
+ mermaid.initialize({ startOnLoad: true, theme: prefersDark ? 'dark' : 'default' });
|
|
|
+</script>
|
|
|
+</body>
|
|
|
+</html>
|
