Shorten the card; keep the previous card verbatim in HISTORY.md

HISTORY.md

@@ -0,0 +1,95 @@
+# Development history
+
+This is the previous model card, kept verbatim.
+
+---
+title: Well Event Transfer Audit
+emoji: 🛢️
+colorFrom: blue
+colorTo: gray
+sdk: static
+app_file: index.html
+license: mit
+---
+# Well event transfer audit
+
+Free static browser interface for the frozen public 3W negative-result study.
+All eleven candidates, group concentration, unknown-onset and abstention limits
+are visible. No live telemetry, user upload, inference endpoint, plant connection
+or control. No deployment admission or verified field adoption.
+
+Data are derived from Petrobras 3W under CC BY 4.0; authored interface is MIT.
+Exact model/Dataset revisions and full attribution are linked from the page.
+
+## Complete-checkpoint conformance
+
+The `tspulse-preflight.html` saved-result explorer adds actual full original
+TSPulse weights, causal end-window author checks, unchanged cross-host probes,
+and original failure/recovery evidence. It runs no browser inference, receives
+no field data, and does not score any reserved well groups. Its linked replay
+kit retains Apache 2.0 pretrained weights/code and MIT authored adaptation.
+The eleven original candidate data and old publication manifest are preserved;
+this methods addition has its own `TSPULSE-CONTENT-MANIFEST.json`.
+
+
+## Separate full causal foundation validation comparison
+
+[Inspect all fifteen retained methods](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/foundation-validation.html),
+common/native eligibility, eight filename groups, all twenty-four labelled
+episodes and group uncertainty. The original included CPU first phase is
+COMPLETE; the separate Mac portability audit remains FAILED on both TCNs.
+Full pretrained TSPulse finds no new validation onset within 300 seconds at
+its selected budget. Eleven of the primary logistic's thirteen onset discoveries
+come from one filename group. No candidate is promoted.
+
+This static browser displays frozen validation results. Eight reserved groups
+remain unopened; no live inference, plant access or command path is present.
+Original confirmation results remain a separate unchanged study.
+
+[Verified foundation validation publication evidence](FOUNDATION-VALIDATION-PUBLICATION.md). Original scientific/source presentation objects are preserved.
+
+
+## Separate Linux saved-probe reproducibility controls
+
+[The immutable diagnostic report](https://huggingface.co/sankalpsthakur/well-production-event-causal/blob/f183a37536df3ca979ab36329be5244334c4e7ff/tcn-linux-diagnostic/REPORT.md)
+binds one included offline CPU job and all 96 controls. Forty runs reproduce
+all 128 original scores exactly; 56 fail the unchanged original tolerance.
+MKLDNN-enabled tested batches 8/32/64/128/256 pass; batch 1 and all disabled
+backend conditions fail. The original Mac aggregate audit stays FAILED.
+No fit, retuning, reserved predictions or model promotion occurred. Complete
+validation-stream construction and single-window inference remain unqualified.
+The static page shows these saved results and links exact source/outputs/receipts.
+
+
+The separate Linux notice has verified publication/readback evidence in [LINUX-REPLAY-PUBLICATION.md](LINUX-REPLAY-PUBLICATION.md); all original scientific UI/data bytes remain preserved.
+
+
+## Complete validation numerical replay
+
+The [six-profile full-stream explorer](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/tcn-stream-validation.html)
+retains both unchanged TCN checkpoints, all 121,325 eligible validation decisions,
+eight groups and every cloud call time. Native batches and a fixed current-only
+eight-copy adaptation reproduce every eligible score exactly; ordinary one-row
+inference preserves both original-tolerance failures. No frozen alarm changes,
+model promotion, new fitting/retuning, reserved predictions or device qualification.
+The original Mac audit remains FAILED. Scientific artifact revision: d1571dbacd2d6ba499c5652253f84d7c095acfc0 .
+
+All source/weights/outputs and the actual anonymous saved-result replay remain in
+[the bound research module](https://huggingface.co/sankalpsthakur/well-production-event-causal/tree/d1571dbacd2d6ba499c5652253f84d7c095acfc0/tcn-stream-replay).
+The static explorer renders saved results; no live telemetry or model inference.
+
+
+## Complete incoming well-signal path review
+
+[The incremental saved-results explorer](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/incremental-well-validation.html)
+shows both complete 33-record profiles, all eight filename groups, strict feature
+and score comparisons, current missingness and packet-to-alarm timing tails.
+All 121,325 eligible scores/checkpoint and every rolling feature match bit for
+bit. Included CPU recovery version 2 is COMPLETE; original version 1 stays ERROR.
+Both checkpoints still discover zero new known onset within 300 s; no model is
+promoted. No raw reserved prediction, fitting or retuning occurs.
+
+The browser displays saved evidence and receives no physical telemetry or camera
+input. Physical source/calibration, target-device performance, commissioning,
+field acceptance, adoption and qualified expert growth remain open. Scientific
+content revision: bf3425c5cb26f5d53a60bdf5410deb70f0f27c3a .

README.md

@@ -7,85 +7,35 @@ sdk: static
 app_file: index.html
 license: mit
 ---
-# Well event transfer audit
-
-Free static browser interface for the frozen public 3W negative-result study.
-All eleven candidates, group concentration, unknown-onset and abstention limits
-are visible. No live telemetry, user upload, inference endpoint, plant connection
-or control. No deployment admission or verified field adoption.
-
-Data are derived from Petrobras 3W under CC BY 4.0; authored interface is MIT.
-Exact model/Dataset revisions and full attribution are linked from the page.
-
-## Complete-checkpoint conformance
-
-The `tspulse-preflight.html` saved-result explorer adds actual full original
-TSPulse weights, causal end-window author checks, unchanged cross-host probes,
-and original failure/recovery evidence. It runs no browser inference, receives
-no field data, and does not score any reserved well groups. Its linked replay
-kit retains Apache 2.0 pretrained weights/code and MIT authored adaptation.
-The eleven original candidate data and old publication manifest are preserved;
-this methods addition has its own `TSPULSE-CONTENT-MANIFEST.json`.
-
-
-## Separate full causal foundation validation comparison
-
-[Inspect all fifteen retained methods](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/foundation-validation.html),
-common/native eligibility, eight filename groups, all twenty-four labelled
-episodes and group uncertainty. The original included CPU first phase is
-COMPLETE; the separate Mac portability audit remains FAILED on both TCNs.
-Full pretrained TSPulse finds no new validation onset within 300 seconds at
-its selected budget. Eleven of the primary logistic's thirteen onset discoveries
-come from one filename group. No candidate is promoted.
-
-This static browser displays frozen validation results. Eight reserved groups
-remain unopened; no live inference, plant access or command path is present.
-Original confirmation results remain a separate unchanged study.
-
-[Verified foundation validation publication evidence](FOUNDATION-VALIDATION-PUBLICATION.md). Original scientific/source presentation objects are preserved.
-
-
-## Separate Linux saved-probe reproducibility controls
-
-[The immutable diagnostic report](https://huggingface.co/sankalpsthakur/well-production-event-causal/blob/f183a37536df3ca979ab36329be5244334c4e7ff/tcn-linux-diagnostic/REPORT.md)
-binds one included offline CPU job and all 96 controls. Forty runs reproduce
-all 128 original scores exactly; 56 fail the unchanged original tolerance.
-MKLDNN-enabled tested batches 8/32/64/128/256 pass; batch 1 and all disabled
-backend conditions fail. The original Mac aggregate audit stays FAILED.
-No fit, retuning, reserved predictions or model promotion occurred. Complete
-validation-stream construction and single-window inference remain unqualified.
-The static page shows these saved results and links exact source/outputs/receipts.
-
-
-The separate Linux notice has verified publication/readback evidence in [LINUX-REPLAY-PUBLICATION.md](LINUX-REPLAY-PUBLICATION.md); all original scientific UI/data bytes remain preserved.
 
+# Well event transfer audit
 
-## Complete validation numerical replay
+A browser explorer for well-event detectors trained on Petrobras 3W 2.0 and tested on well
+groups they never saw. It shows saved results only: no live telemetry, no uploads, no
+model inference.
 
-The [six-profile full-stream explorer](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/tcn-stream-validation.html)
-retains both unchanged TCN checkpoints, all 121,325 eligible validation decisions,
-eight groups and every cloud call time. Native batches and a fixed current-only
-eight-copy adaptation reproduce every eligible score exactly; ordinary one-row
-inference preserves both original-tolerance failures. No frozen alarm changes,
-model promotion, new fitting/retuning, reserved predictions or device qualification.
-The original Mac audit remains FAILED. Scientific artifact revision: d1571dbacd2d6ba499c5652253f84d7c095acfc0 .
+## Pages
 
-All source/weights/outputs and the actual anonymous saved-result replay remain in
-[the bound research module](https://huggingface.co/sankalpsthakur/well-production-event-causal/tree/d1571dbacd2d6ba499c5652253f84d7c095acfc0/tcn-stream-replay).
-The static explorer renders saved results; no live telemetry or model inference.
+- [Transfer audit](index.html): all eleven candidates on fresh confirmation data, with
+  coverage, onset delay, false alarms and where the failures concentrate
+- [15-method validation comparison](foundation-validation.html): compact models, tree
+  ensembles, conventional references and IBM's pretrained TSPulse. TSPulse finds no new
+  onset within 300 seconds, and 11 of the logistic model's 13 onset discoveries come from
+  one recording group.
+- [TSPulse preflight](tspulse-preflight.html): the full pretrained checkpoint run causally,
+  end to end
+- [Full-stream replay](tcn-stream-validation.html): every one of 121,325 validation
+  decisions, replayed exactly
+- [Incremental signal path](incremental-well-validation.html): packet-by-packet features,
+  scores and alarm timing. Both TCNs still find no new known onset within 300 s.
 
+No model is ready for deployment. The models, reports and audit data are in
+[well-production-event-causal](https://huggingface.co/sankalpsthakur/well-production-event-causal)
+and the [3W audit dataset](https://huggingface.co/datasets/sankalpsthakur/3w-causal-real-group-audit).
 
-## Complete incoming well-signal path review
+## License
 
-[The incremental saved-results explorer](https://sankalpsthakur-well-event-transfer-audit.static.hf.space/incremental-well-validation.html)
-shows both complete 33-record profiles, all eight filename groups, strict feature
-and score comparisons, current missingness and packet-to-alarm timing tails.
-All 121,325 eligible scores/checkpoint and every rolling feature match bit for
-bit. Included CPU recovery version 2 is COMPLETE; original version 1 stays ERROR.
-Both checkpoints still discover zero new known onset within 300 s; no model is
-promoted. No raw reserved prediction, fitting or retuning occurs.
+Data are derived from Petrobras 3W under CC BY 4.0; authored interface is MIT.
+Exact model/Dataset revisions and full attribution are linked from the page.
 
-The browser displays saved evidence and receives no physical telemetry or camera
-input. Physical source/calibration, target-device performance, commissioning,
-field acceptance, adoption and qualified expert growth remain open. Scientific
-content revision: bf3425c5cb26f5d53a60bdf5410deb70f0f27c3a .
+The full release log is in [HISTORY.md](HISTORY.md).