Add complete incremental well validation, exact inputs and retained failures
Browse files- README.md +16 -0
- incremental-well-validation.html +35 -0
- incremental-well-validation.js +64 -0
- incremental-well-validation.json +0 -0
- tcn-stream-validation.html +2 -0
- tspulse-preflight.html +2 -0
README.md
CHANGED
|
@@ -73,3 +73,19 @@ The original Mac audit remains FAILED. Scientific artifact revision: d1571dbacd2
|
|
| 73 |
All source/weights/outputs and the actual anonymous saved-result replay remain in
|
| 74 |
[the bound research module](https://huggingface.co/sankalpsthakur/well-production-event-causal/tree/d1571dbacd2d6ba499c5652253f84d7c095acfc0/tcn-stream-replay).
|
| 75 |
The static explorer renders saved results; no live telemetry or model inference.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
All source/weights/outputs and the actual anonymous saved-result replay remain in
|
| 74 |
[the bound research module](https://huggingface.co/sankalpsthakur/well-production-event-causal/tree/d1571dbacd2d6ba499c5652253f84d7c095acfc0/tcn-stream-replay).
|
| 75 |
The static explorer renders saved results; no live telemetry or model inference.
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
## Complete incoming well-signal path review
|
| 79 |
+
|
| 80 |
+
[The incremental saved-results explorer](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/incremental-well-validation.html)
|
| 81 |
+
shows both complete 33-record profiles, all eight filename groups, strict feature
|
| 82 |
+
and score comparisons, current missingness and packet-to-alarm timing tails.
|
| 83 |
+
All 121,325 eligible scores/checkpoint and every rolling feature match bit for
|
| 84 |
+
bit. Included CPU recovery version 2 is COMPLETE; original version 1 stays ERROR.
|
| 85 |
+
Both checkpoints still discover zero new known onset within 300 s; no model is
|
| 86 |
+
promoted. No raw reserved prediction, fitting or retuning occurs.
|
| 87 |
+
|
| 88 |
+
The browser displays saved evidence and receives no physical telemetry or camera
|
| 89 |
+
input. Physical source/calibration, target-device performance, commissioning,
|
| 90 |
+
field acceptance, adoption and qualified expert growth remain open. Scientific
|
| 91 |
+
content revision: bf3425c5cb26f5d53a60bdf5410deb70f0f27c3a .
|
incremental-well-validation.html
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!doctype html>
|
| 2 |
+
<html lang="en">
|
| 3 |
+
<head>
|
| 4 |
+
<meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1">
|
| 5 |
+
<title>Incoming well signals · Complete numerical review</title>
|
| 6 |
+
<style>
|
| 7 |
+
:root{font-family:system-ui,sans-serif;color:#162d38;background:#f2f5f4;line-height:1.5}*{box-sizing:border-box}body{margin:0}main{max-width:1120px;margin:auto;padding:28px 24px 64px}h1{font-size:clamp(2rem,5vw,3rem);line-height:1.15;max-width:760px;margin:.4em 0}h2{font-size:1.35rem;margin-top:0}h3{font-size:1rem}a{color:#085a65}p{max-width:850px}section{margin:24px 0;padding:22px;background:#fff;border:1px solid #cfdbd7;border-radius:8px}.eyebrow{font-size:.8rem;font-weight:700;letter-spacing:.08em;text-transform:uppercase;color:#42626d}.notice{border-left:5px solid #ad641d;background:#fff5e7;padding:14px 18px;margin:20px 0}.controls{display:flex;gap:18px;flex-wrap:wrap}label{display:flex;flex:1;min-width:180px;flex-direction:column;gap:6px;font-weight:600}select{font:inherit;padding:10px;width:100%;background:white;border:1px solid #647d85;border-radius:5px}.flow{display:grid;grid-template-columns:repeat(4,1fr);gap:12px}.flow>div{padding:14px;border:1px solid #cad8d2;background:#eef4f1;border-radius:4px}.flow strong{display:block}.flow span{font-size:.9rem}.facts{display:grid;grid-template-columns:repeat(3,1fr);gap:18px}.fact strong{display:block;font-size:1.6rem}.detail{font-size:.92rem;color:#42606a}.fail{color:#912f20;font-weight:650}.pass{color:#185a48}.scroll{overflow-x:auto}table{border-collapse:collapse;width:100%;font-size:.9rem}caption{text-align:left;margin:10px 0;color:#42606a}th,td{padding:10px 9px;border-bottom:1px solid #d8e0dc;text-align:left;vertical-align:top}thead{background:#f2f6f4}code{overflow-wrap:anywhere;font-size:.85rem}.links{display:flex;gap:20px;flex-wrap:wrap}.selected{background:#fff3df}[hidden]{display:none!important}.error{color:#912f20}footer{padding-top:20px;font-size:.9rem;color:#42606a}@media(max-width:650px){main{padding:20px 16px 40px}section{padding:16px}.facts{grid-template-columns:1fr}.flow{grid-template-columns:1fr 1fr}.controls{flex-direction:column}label{min-width:0}th,td{padding:8px 7px}h1{font-size:2rem}}
|
| 8 |
+
</style>
|
| 9 |
+
<script src="incremental-well-validation.js" defer></script>
|
| 10 |
+
</head>
|
| 11 |
+
<body><main>
|
| 12 |
+
<a href="tcn-stream-validation.html">← Earlier complete score replay</a>
|
| 13 |
+
<div class="eyebrow">Well surveillance · Saved research results</div>
|
| 14 |
+
<h1>Does the incoming signal path preserve the original model inputs?</h1>
|
| 15 |
+
<p>This review follows every incoming row through a bounded history, model features, one unchanged checkpoint and its frozen alarm. Choose a checkpoint and recording to inspect the actual results.</p>
|
| 16 |
+
<div class="notice"><strong>Industrial deployment is unqualified.</strong> This explorer displays saved validation evidence. It receives no telemetry and runs no model. Physical calibration, trusted sources, useful fresh detection, target-device tests and site acceptance remain open.</div>
|
| 17 |
+
<p id="load-state" role="status">Loading the complete saved review…</p>
|
| 18 |
+
<div id="audit" hidden>
|
| 19 |
+
<section aria-labelledby="scope-title"><h2 id="scope-title">Complete scope, preserved failures</h2>
|
| 20 |
+
<div class="facts"><div class="fact"><strong id="source-rows"></strong>original source rows<div class="detail">33 recordings / eight filename groups</div></div><div class="fact"><strong id="timing-rows"></strong>accepted updates timed<div class="detail">Two separate passes over the same data</div></div><div class="fact"><strong id="execution-state"></strong>provider execution<div class="detail" id="conformance-state"></div></div></div>
|
| 21 |
+
<p id="original-failure" class="detail"></p><p class="detail">The second attempt fixes only Arrow conversion of null sensor cells. Data, weights, scalers, thresholds and strict tolerances remain unchanged. Both attempts survive; reused validation is not new independent confirmation.</p>
|
| 22 |
+
</section>
|
| 23 |
+
<section aria-labelledby="path-title"><h2 id="path-title">What the measured path includes</h2><div class="flow"><div><strong>1. Packet</strong><span>Declared sequence, time, channels and numeric availability</span></div><div><strong>2. History</strong><span>512 past samples; a 64-sample tail; no future values</span></div><div><strong>3. Model</strong><span>Eight identical copies of only the current feature input</span></div><div><strong>4. Alarm</strong><span>Unchanged threshold and streaming alarm state</span></div></div>
|
| 24 |
+
<p class="detail">Eight copies add computation and establish no new observations or model promotion. The measured packet-to-alarm timer excludes file decoding and diagnostic storage. Arrival times and units are retrospective declarations; this is not a physical acquisition or device deadline test.</p>
|
| 25 |
+
</section>
|
| 26 |
+
<section aria-labelledby="selection-title"><h2 id="selection-title">Inspect one complete recording</h2><div class="controls"><label>Checkpoint<select id="checkpoint"></select></label><label>Recording<select id="recording"></select></label></div><p id="selection-note"></p>
|
| 27 |
+
<div class="facts"><div class="fact"><strong id="score-failures"></strong>scores outside original tolerance<div class="detail" id="score-detail"></div></div><div class="fact"><strong id="alarm-changes"></strong>changed alarm decisions<div class="detail" id="alarm-detail"></div></div><div class="fact"><strong id="pipeline-median"></strong>eligible packet-to-alarm median<div class="detail" id="pipeline-tail"></div></div></div>
|
| 28 |
+
<p class="detail" id="missing-now"></p>
|
| 29 |
+
<div class="scroll"><table><caption>Every feature comparison stays visible. Bit differences and failures at the original tolerance are different measurements.</caption><thead><tr><th>Feature</th><th>Compared values</th><th>Outside tolerance</th><th>Different bits</th><th>Maximum finite difference</th></tr></thead><tbody id="feature-rows"></tbody></table></div>
|
| 30 |
+
<p class="detail" id="discrete-changes"></p><p class="detail" id="alarm-usefulness"></p>
|
| 31 |
+
</section>
|
| 32 |
+
<section aria-labelledby="group-title"><h2 id="group-title">All eight groups</h2><p class="detail">These are published filename groups. Independent physical-well identities are not authenticated. No group or failed recording is omitted.</p><div class="scroll"><table><thead><tr><th>Group</th><th>Historically eligible rows</th><th>Feature failures</th><th>Score failures</th><th>Alarm changes</th><th>Eligible with current missing channels</th></tr></thead><tbody id="group-rows"></tbody></table></div></section>
|
| 33 |
+
<section aria-labelledby="evidence-title"><h2 id="evidence-title">Traceable evidence</h2><p id="runtime"></p><p class="detail">The 28,672-byte ring holds numeric history only. Process-lifetime peak memory includes the reference and diagnostic harness; neither is a deployed edge memory requirement. Raw timers, first calls and outliers remain in the original output.</p><div class="links"><a id="report-link">Measured report</a><a id="output-link">Original recovery output</a><a id="rebuild-link">Saved-array replay guide</a></div><p>Immutable scientific revision: <code id="artifact-revision"></code></p><p>Recovery output SHA256: <code id="output-sha"></code></p><p class="detail">No fits, retuning or reserved-well predictions occurred. Both original and later numerical failures remain. No model is promoted, and zero alarm changes do not establish a useful detector.</p></section>
|
| 34 |
+
</div><footer>Original adaptation and author review, with AI assistance. Petrobras 3W data retain CC BY 4.0 attribution; authored methods are MIT. No independent physical or human signoff is claimed.</footer>
|
| 35 |
+
</main></body></html>
|
incremental-well-validation.js
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
'use strict';
|
| 2 |
+
const $ = id => document.getElementById(id);
|
| 3 |
+
const number = n => n.toLocaleString('en-US');
|
| 4 |
+
const ms = n => n === null ? 'Unavailable' : `${(n / 1e6).toFixed(3)} ms`;
|
| 5 |
+
const featureLabels = { raw_features: 'Raw summaries', bin_means: 'Past bin means', bin_fractions: 'Past bin availability', summary: 'Scaled summaries', temporal: 'Scaled temporal input' };
|
| 6 |
+
let saved;
|
| 7 |
+
function cell(row, value) { const td = document.createElement('td'); td.textContent = value; row.append(td); return td; }
|
| 8 |
+
function render() {
|
| 9 |
+
const profile = saved.result.profiles.find(p => p.candidate === $('checkpoint').value);
|
| 10 |
+
const checked = saved.review.profiles.find(p => p.candidate === profile.candidate);
|
| 11 |
+
const row = profile.records[Number($('recording').value)];
|
| 12 |
+
if (!row || !checked) throw new Error('Complete selected recording is absent');
|
| 13 |
+
$('selection-note').textContent = `${profile.candidate} · ${row.path} · ${number(row.rows)} accepted source rows · ${number(row.grid_rows)} decisions · ${row.state === 'PASSED' ? 'Original conformance checks pass' : 'Original conformance checks FAILED'}`;
|
| 14 |
+
$('selection-note').className = row.state === 'PASSED' ? 'pass' : 'fail';
|
| 15 |
+
$('score-failures').textContent = number(row.score_comparison.failed_values);
|
| 16 |
+
$('score-failures').className = row.score_comparison.failed_values ? 'fail' : '';
|
| 17 |
+
$('score-detail').textContent = `${number(row.score_comparison.finite_pairs)} finite pairs; maximum difference ${row.score_comparison.max_finite_abs_difference === null ? 'unavailable' : row.score_comparison.max_finite_abs_difference.toExponential(6)}. Atol 1e-10 / rtol 1e-9.`;
|
| 18 |
+
$('alarm-changes').textContent = number(row.alarm_changes);
|
| 19 |
+
$('alarm-changes').className = row.alarm_changes ? 'fail' : '';
|
| 20 |
+
$('alarm-detail').textContent = profile.frozen_threshold === null ? 'This checkpoint’s original alarm is disabled' : 'Unchanged original threshold and alarm semantics';
|
| 21 |
+
$('pipeline-median').textContent = ms(row.pipeline_eligible_grid.median_ns);
|
| 22 |
+
$('pipeline-tail').textContent = `P95 ${ms(row.pipeline_eligible_grid.p95_ns)}; maximum ${ms(row.pipeline_eligible_grid.max_ns)}; first eligible call ${ms(row.pipeline_eligible_grid.first_ns)}. All retained.`;
|
| 23 |
+
$('missing-now').textContent = `${number(row.supported_with_current_missing)} of ${number(row.supported_rows)} historically eligible decisions have missing current channels; ${number(row.supported_with_fewer_than_three_current_channels)} have fewer than three current channels, and ${number(row.supported_with_fewer_than_two_current_pressure_channels)} fewer than two current pressure channels. Historical eligibility is not physical sensor quality.`;
|
| 24 |
+
$('feature-rows').replaceChildren();
|
| 25 |
+
for (const [key, detail] of Object.entries(row.feature_comparisons)) {
|
| 26 |
+
const tr = document.createElement('tr'); tr.dataset.feature = key;
|
| 27 |
+
if (detail.failed_values) tr.className = 'fail';
|
| 28 |
+
for (const item of [featureLabels[key] || key, number(detail.values), number(detail.failed_values), number(detail.different_bit_values), detail.max_finite_abs_difference === null ? 'Unavailable' : detail.max_finite_abs_difference.toExponential(6)]) cell(tr, item);
|
| 29 |
+
$('feature-rows').append(tr);
|
| 30 |
+
}
|
| 31 |
+
$('discrete-changes').textContent = 'Discrete changes: ' + Object.entries(row.discrete_changes).map(([key,value]) => `${key}: ${number(value)}`).join('; ') + '.';
|
| 32 |
+
const m = profile.common_metric, c = m.counts;
|
| 33 |
+
$('alarm-usefulness').textContent = `Complete checkpoint, common eligibility: ${c.covered_episodes}/${c.episodes} episodes covered; ${c.new_known_onset_discoveries_300s} new known-onset discoveries within 300 s; ${c.false_normal_alarm_episodes ?? 0} false normal alarm episodes over ${m.eligible_normal_days.toFixed(6)} eligible normal days. These reused validation outcomes are not fresh field performance.`;
|
| 34 |
+
$('group-rows').replaceChildren();
|
| 35 |
+
for (const [name, group] of Object.entries(checked.groups)) {
|
| 36 |
+
const tr = document.createElement('tr'); tr.dataset.group = name;
|
| 37 |
+
tr.classList.toggle('selected', name === row.group);
|
| 38 |
+
if (group.feature_failures || group.score_failures || group.alarm_changes) tr.classList.add('fail');
|
| 39 |
+
for (const item of [name, number(group.supported_rows), number(group.feature_failures), number(group.score_failures), number(group.alarm_changes), number(group.supported_current_missing)]) cell(tr, item);
|
| 40 |
+
$('group-rows').append(tr);
|
| 41 |
+
}
|
| 42 |
+
}
|
| 43 |
+
fetch('incremental-well-validation.json').then(response => {
|
| 44 |
+
if (!response.ok) throw new Error(`Saved result response ${response.status}`);
|
| 45 |
+
return response.json();
|
| 46 |
+
}).then(data => {
|
| 47 |
+
if (data.schema !== 'industrial.well.incremental.saved.presentation.v1' || data.result.state !== 'COMPLETE_VALIDATION_REVIEW_NOT_FIELD_ADMISSION' || data.result.profiles.length !== 2 || data.review.state !== 'VERIFIED_SAVED_ARRAY_CONFORMANCE_AND_FAILURES_NOT_FIELD_ADMISSION' || !/^[0-9a-f]{40}$/.test(data.artifact_revision)) throw new Error('Complete reviewed and pinned source required');
|
| 48 |
+
saved = data;
|
| 49 |
+
for (const profile of data.result.profiles) { const option = document.createElement('option'); option.value = profile.candidate; option.textContent = profile.candidate; $('checkpoint').append(option); }
|
| 50 |
+
for (const [index, row] of data.result.profiles[0].records.entries()) { const option = document.createElement('option'); option.value = String(index); option.textContent = row.path; $('recording').append(option); }
|
| 51 |
+
$('source-rows').textContent = number(data.result.profiles[0].accepted_rows);
|
| 52 |
+
$('timing-rows').textContent = number(data.review.accepted_row_timing_records_verified);
|
| 53 |
+
$('execution-state').textContent = data.provider.state;
|
| 54 |
+
$('conformance-state').textContent = data.result.conformance_passed ? 'Numerical conformance passes; industrial admission remains false' : 'Numerical conformance FAILED; every failure retained';
|
| 55 |
+
$('conformance-state').className = data.result.conformance_passed ? 'detail' : 'detail fail';
|
| 56 |
+
$('original-failure').textContent = `Original version 1: ${data.original_error.provider_status}, ${number(data.original_error.actual_cloud_authored_checks_passed)} authored checks passed, null-column decoder failure after ${number(data.original_error.complete_reference_source_rows)} complete reference rows; zero trained rolling predictions. Recovery version 2: ${data.provider.authored_checks} authored checks passed. No third attempt is implied.`;
|
| 57 |
+
$('artifact-revision').textContent = data.artifact_revision;
|
| 58 |
+
$('output-sha').textContent = data.provider.output_zip_sha256;
|
| 59 |
+
const base = `https://huggingface.co/sankalpsthakur/well-production-event-causal/`;
|
| 60 |
+
for (const [id,file] of [['report-link','REPORT.md'],['output-link','ORIGINAL-RECOVERY-OUTPUT.zip'],['rebuild-link','REBUILD.md']]) $(id).href = `${base}${id === 'output-link' ? 'resolve' : 'blob'}/${data.artifact_revision}/incremental-well-validation/${file}`;
|
| 61 |
+
$('runtime').textContent = `Observed Linux CPU runtime: Torch ${data.result.runtime.torch}, NumPy ${data.result.runtime.numpy}, PyArrow ${data.result.runtime.pyarrow}; two CPU threads. Child elapsed ${data.result.elapsed_seconds.toFixed(3)} s; process-lifetime peak RSS ${number(data.result.peak_rss)} ${data.result.peak_rss_unit}.`;
|
| 62 |
+
$('checkpoint').addEventListener('change',render); $('recording').addEventListener('change',render);
|
| 63 |
+
render(); $('audit').hidden = false; $('load-state').hidden = true;
|
| 64 |
+
}).catch(error => { $('audit').hidden = true; $('load-state').className = 'error'; $('load-state').textContent = `Saved results unavailable: ${error.message}. No inference is performed.`; });
|
incremental-well-validation.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tcn-stream-validation.html
CHANGED
|
@@ -6,6 +6,8 @@
|
|
| 6 |
:root{color-scheme:light;--ink:#17272c;--muted:#52666d;--paper:#f4f5ef;--line:#d9dfd7;--red:#a72b25;--blue:#165c70}*{box-sizing:border-box}body{margin:0;background:var(--paper);color:var(--ink);font:16px/1.55 system-ui,-apple-system,sans-serif}main{max-width:1180px;margin:auto;padding:30px 28px 60px}a{color:var(--blue);text-underline-offset:3px}h1{font:clamp(2rem,4vw,3.35rem)/1.13 Georgia,serif;margin:14px 0;max-width:900px}h2{font:1.7rem/1.2 Georgia,serif;margin:30px 0 12px}p{max-width:920px}.small{color:var(--muted);font-size:.86rem}.eyebrow{color:var(--blue);font-size:.76rem;letter-spacing:.1em;text-transform:uppercase;font-weight:700;margin-top:16px}header{padding-bottom:20px;border-bottom:1px solid var(--line)}.badges{display:flex;gap:8px;flex-wrap:wrap}.badge{padding:5px 10px;border:1px solid var(--line);background:white;font-size:.82rem}.badge.fail{color:var(--red);background:#f8e4df;border-color:#e9bab1}.notice{padding:18px 20px;background:#fffaf4;border-left:4px solid var(--red);margin:22px 0}.controls{display:flex;gap:20px;flex-wrap:wrap;align-items:end;margin:24px 0}label{display:block;font-size:.85rem;font-weight:650;margin-bottom:7px}select{font:inherit;padding:11px;background:white;color:var(--ink);border:1px solid #83969b;max-width:100%;border-radius:4px}a:focus-visible,select:focus-visible,summary:focus-visible{outline:3px solid var(--blue);outline-offset:3px}.cards{display:grid;grid-template-columns:repeat(4,1fr);gap:14px}.card{border:1px solid var(--line);background:white;padding:18px}.value{font-size:1.9rem;font-weight:650;line-height:1.25;margin:8px 0}.value.fail{color:var(--red)}.scroll{overflow-x:auto;border:1px solid var(--line);background:white}table{border-collapse:collapse;width:100%;font-size:.85rem;min-width:720px}th,td{padding:11px 13px;text-align:left;border-bottom:1px solid var(--line);vertical-align:top}th{background:#edf0e9;color:var(--muted);font-size:.76rem}tr.selected{background:#e9f0ef}tr.fail{color:var(--red)}caption{text-align:left;padding:12px;color:var(--muted);font-size:.82rem}.bar{height:6px;background:#edf0e9;margin-top:6px;max-width:150px}.fill{height:100%;background:var(--red)}details{margin-top:24px;border-top:1px solid var(--line);padding-top:18px}summary{cursor:pointer;font-weight:650}.links{display:flex;gap:12px 22px;flex-wrap:wrap;margin:22px 0}.digest{overflow-wrap:anywhere;font-size:.8rem;color:var(--muted)}footer{margin-top:32px;padding-top:20px;border-top:1px solid var(--line);color:var(--muted);font-size:.86rem}[hidden]{display:none!important}@media(max-width:760px){main{padding:24px 18px}.cards{grid-template-columns:1fr 1fr}.controls>div{width:100%}select{width:100%}.value{font-size:1.6rem}}
|
| 7 |
</style></head><body><main>
|
| 8 |
<header><a href="foundation-validation.html">← Fifteen-method validation comparison</a><div class="eyebrow">Reproducibility · Public well-event research</div><h1>Replaying every validation decision.</h1><p class="small">33 recordings, eight filename groups and 121,325 eligible decisions. Compare original offline scores with two ways to process one available input.</p><div class="badges"><span class="badge">One included cloud CPU job</span><span class="badge">4 exact profiles · 2 failed profiles</span><span class="badge fail">Industrial use unqualified</span></div></header>
|
|
|
|
|
|
|
| 9 |
<div class="notice"><strong>The current-only eight-copy method matches every examined score.</strong><br>Ordinary single-reading inference fails the unchanged numerical tolerance. Eight copies of the same current input reproduce the original scores, with extra computation. This finite validation result promotes no model; all eight reserved groups remain unopened.</div>
|
| 10 |
<noscript><p>JavaScript displays saved results here. <a href="https://huggingface.co/sankalpsthakur/well-production-event-causal/tree/main/tcn-stream-replay">Read the report and original outputs</a>.</p></noscript>
|
| 11 |
<div id="load-state" role="status">Loading the frozen replay results…</div>
|
|
|
|
| 6 |
:root{color-scheme:light;--ink:#17272c;--muted:#52666d;--paper:#f4f5ef;--line:#d9dfd7;--red:#a72b25;--blue:#165c70}*{box-sizing:border-box}body{margin:0;background:var(--paper);color:var(--ink);font:16px/1.55 system-ui,-apple-system,sans-serif}main{max-width:1180px;margin:auto;padding:30px 28px 60px}a{color:var(--blue);text-underline-offset:3px}h1{font:clamp(2rem,4vw,3.35rem)/1.13 Georgia,serif;margin:14px 0;max-width:900px}h2{font:1.7rem/1.2 Georgia,serif;margin:30px 0 12px}p{max-width:920px}.small{color:var(--muted);font-size:.86rem}.eyebrow{color:var(--blue);font-size:.76rem;letter-spacing:.1em;text-transform:uppercase;font-weight:700;margin-top:16px}header{padding-bottom:20px;border-bottom:1px solid var(--line)}.badges{display:flex;gap:8px;flex-wrap:wrap}.badge{padding:5px 10px;border:1px solid var(--line);background:white;font-size:.82rem}.badge.fail{color:var(--red);background:#f8e4df;border-color:#e9bab1}.notice{padding:18px 20px;background:#fffaf4;border-left:4px solid var(--red);margin:22px 0}.controls{display:flex;gap:20px;flex-wrap:wrap;align-items:end;margin:24px 0}label{display:block;font-size:.85rem;font-weight:650;margin-bottom:7px}select{font:inherit;padding:11px;background:white;color:var(--ink);border:1px solid #83969b;max-width:100%;border-radius:4px}a:focus-visible,select:focus-visible,summary:focus-visible{outline:3px solid var(--blue);outline-offset:3px}.cards{display:grid;grid-template-columns:repeat(4,1fr);gap:14px}.card{border:1px solid var(--line);background:white;padding:18px}.value{font-size:1.9rem;font-weight:650;line-height:1.25;margin:8px 0}.value.fail{color:var(--red)}.scroll{overflow-x:auto;border:1px solid var(--line);background:white}table{border-collapse:collapse;width:100%;font-size:.85rem;min-width:720px}th,td{padding:11px 13px;text-align:left;border-bottom:1px solid var(--line);vertical-align:top}th{background:#edf0e9;color:var(--muted);font-size:.76rem}tr.selected{background:#e9f0ef}tr.fail{color:var(--red)}caption{text-align:left;padding:12px;color:var(--muted);font-size:.82rem}.bar{height:6px;background:#edf0e9;margin-top:6px;max-width:150px}.fill{height:100%;background:var(--red)}details{margin-top:24px;border-top:1px solid var(--line);padding-top:18px}summary{cursor:pointer;font-weight:650}.links{display:flex;gap:12px 22px;flex-wrap:wrap;margin:22px 0}.digest{overflow-wrap:anywhere;font-size:.8rem;color:var(--muted)}footer{margin-top:32px;padding-top:20px;border-top:1px solid var(--line);color:var(--muted);font-size:.86rem}[hidden]{display:none!important}@media(max-width:760px){main{padding:24px 18px}.cards{grid-template-columns:1fr 1fr}.controls>div{width:100%}select{width:100%}.value{font-size:1.6rem}}
|
| 7 |
</style></head><body><main>
|
| 8 |
<header><a href="foundation-validation.html">← Fifteen-method validation comparison</a><div class="eyebrow">Reproducibility · Public well-event research</div><h1>Replaying every validation decision.</h1><p class="small">33 recordings, eight filename groups and 121,325 eligible decisions. Compare original offline scores with two ways to process one available input.</p><div class="badges"><span class="badge">One included cloud CPU job</span><span class="badge">4 exact profiles · 2 failed profiles</span><span class="badge fail">Industrial use unqualified</span></div></header>
|
| 9 |
+
<div class="notice" id="incremental-well-note"><strong>Complete incoming-signal software review is now available.</strong> <a href="incremental-well-validation.html">Inspect all 33 recordings, rolling inputs and full packet-to-alarm timings</a>. Features and eligible scores match bit for bit; both checkpoints still find no new known onset within 300 s. Original failures remain, all eight reserved groups stay sealed and industrial deployment is unqualified.</div>
|
| 10 |
+
|
| 11 |
<div class="notice"><strong>The current-only eight-copy method matches every examined score.</strong><br>Ordinary single-reading inference fails the unchanged numerical tolerance. Eight copies of the same current input reproduce the original scores, with extra computation. This finite validation result promotes no model; all eight reserved groups remain unopened.</div>
|
| 12 |
<noscript><p>JavaScript displays saved results here. <a href="https://huggingface.co/sankalpsthakur/well-production-event-causal/tree/main/tcn-stream-replay">Read the report and original outputs</a>.</p></noscript>
|
| 13 |
<div id="load-state" role="status">Loading the frozen replay results…</div>
|
tspulse-preflight.html
CHANGED
|
@@ -7,6 +7,8 @@
|
|
| 7 |
</style></head><body><main>
|
| 8 |
<nav><a href="index.html">← Well-event transfer audit</a><span>Saved experiment · October 2026</span></nav>
|
| 9 |
<header><div><div class="eyebrow">Complete pretrained checkpoint · Causal end-window adaptation</div><h1>A small model’s causal preflight</h1><p class="muted">The full time/frequency network was executed on authored histories. Explore what its masks, timestamps and reloads establish before a new well-data comparison.</p></div><div class="stamp">1,084,330 parameters<span>278 tensors · 4.37 MB original weights<br>Strict full load; no fitting or ignored keys</span></div></header>
|
|
|
|
|
|
|
| 10 |
<div class="notice"><strong>Conformance passed. Industrial qualification remains open.</strong><br>This page displays saved results. It runs no model in your browser, accepts no uploads and receives no telemetry. There is no calibrated alarm or well-event performance result for this adapter.</div>
|
| 11 |
<noscript><p>Enable JavaScript to inspect saved probes, or read the linked complete report.</p></noscript>
|
| 12 |
<div class="controls"><div><label for="scenario">Saved authored input</label><select id="scenario"><option value="periodic">Periodic analytic history</option><option value="missing">Partial missingness + one absent channel</option><option value="zero">Zero history</option><option value="constant">Constant history</option></select></div><div><label for="end">Past-window end (nominal seconds)</label><select id="end"></select></div></div>
|
|
|
|
| 7 |
</style></head><body><main>
|
| 8 |
<nav><a href="index.html">← Well-event transfer audit</a><span>Saved experiment · October 2026</span></nav>
|
| 9 |
<header><div><div class="eyebrow">Complete pretrained checkpoint · Causal end-window adaptation</div><h1>A small model’s causal preflight</h1><p class="muted">The full time/frequency network was executed on authored histories. Explore what its masks, timestamps and reloads establish before a new well-data comparison.</p></div><div class="stamp">1,084,330 parameters<span>278 tensors · 4.37 MB original weights<br>Strict full load; no fitting or ignored keys</span></div></header>
|
| 10 |
+
<div class="notice" id="incremental-well-note"><strong>Complete incoming-signal software review is now available.</strong> <a href="incremental-well-validation.html">Inspect all 33 recordings, rolling inputs and full packet-to-alarm timings</a>. Features and eligible scores match bit for bit; both checkpoints still find no new known onset within 300 s. Original failures remain, all eight reserved groups stay sealed and industrial deployment is unqualified.</div>
|
| 11 |
+
|
| 12 |
<div class="notice"><strong>Conformance passed. Industrial qualification remains open.</strong><br>This page displays saved results. It runs no model in your browser, accepts no uploads and receives no telemetry. There is no calibrated alarm or well-event performance result for this adapter.</div>
|
| 13 |
<noscript><p>Enable JavaScript to inspect saved probes, or read the linked complete report.</p></noscript>
|
| 14 |
<div class="controls"><div><label for="scenario">Saved authored input</label><select id="scenario"><option value="periodic">Periodic analytic history</option><option value="missing">Partial missingness + one absent channel</option><option value="zero">Zero history</option><option value="constant">Constant history</option></select></div><div><label for="end">Past-window end (nominal seconds)</label><select id="end"></select></div></div>
|