In a single session, we executed the complete SBPI prediction pipeline from infrastructure recovery through live prediction generation. Six interdependent steps were completed: config deployment, critical source code recovery, knowledge graph expansion, W14 prediction generation, signal weight optimization, and brand intelligence card creation. The pipeline is now fully operational with a dual-config test locked for W14 evaluation.
Decompiled missing sbpi_to_rdf.py from bytecode. Resolved Oxigraph store lock via SPARQL INSERT DATA batches.
Loaded 4 weeks of data (W10–W13), growing the store from 1,672 to 4,052 triples (+142%).
Added kg_optimized as 5th prediction method. Dual-config test locked for W14.
105 predictions locked across 5 methods and 21 companies.
Optuna TPE optimizer (30 trials) achieved 66.7% appropriate rate on synthetic labels.
21 sortable company intelligence cards deployed to sbpi-brand-intel.pages.dev.
Two critical infrastructure issues were resolved before the pipeline could execute.
The source file for the RDF ETL pipeline was missing. Only a compiled .pyc existed in __pycache__. An agent decompiled the bytecode, recovering all 7 functions and 63 module-level names with exact fidelity. The reconstructed script was verified to generate 1,033 triples from W13 data.
A null-safety patch was applied for archive files with missing previous_composite fields.
The Oxigraph server (PID 2674) held an exclusive lock on the store, blocking the standard pyoxigraph file-access pattern.
The prediction experiment script was upgraded from 4 methods to 5, adding the Optuna-tuned kg_optimized configuration for a dual-config head-to-head test.
| Method | Description | W14 Predictions |
|---|---|---|
| persistence | Predicts no change (delta = 0) | 21 STABLE |
| naive_momentum | Predicts delta = last week's delta | 8 UP 8 STABLE 5 DOWN |
| mean_reversion | Predicts reversion toward tier midpoint | 21 UP |
| kg_default | Original hardcoded thresholds (untuned) | 21 STABLE |
| kg_optimized | Optuna-tuned 12-parameter config | 13 UP 8 STABLE |
kg_optimized uses the Optuna TPE-optimized parameters from best-config.json (69.9% training accuracy on W10–W12 data). It imports load_best_config() and predict_with_config() from kg_interface_optimizer.py. Falls back to default config if best-config.json is missing.
| Parameter | Default | Optimized | Change |
|---|---|---|---|
| direction_threshold | 0.500 | 1.295 | +159% |
| confidence_base | 0.600 | 0.443 | −26% |
| mean_reversion_rate | 0.100 | 0.257 | +157% |
| anomaly_contributes | false | true | enabled |
| divergence_weight | — | 0.180 | new |
| tier_proximity_weight | — | 0.096 | new |
| Method | Direction | Delta | Confidence |
|---|---|---|---|
| kg_default | STABLE | 0.00 | 0.50 |
| kg_optimized | UP | +1.99 | 0.95 |
| naive_momentum | DOWN | −2.60 | 0.55 |
| mean_reversion | UP | +0.78 | 0.45 |
| Week | Score Records | Status |
|---|---|---|
| W10-2026 | 16 | Archive |
| W11-2026 | 17 | Archive |
| W12-2026 | 21 | Archive |
| W13-2026 | 21 | Current |
| Rank | Company | Composite Score |
|---|---|---|
| 1 | DramaBox | 82.75 |
| 2 | ReelShort | 81.20 |
| 3 | Disney | 77.10 |
| 4 | iQiYi | 67.30 |
| 5 | JioHotstar | 65.40 |
| Company | Delta |
|---|---|
| Amazon | +4.05 |
| JioHotstar | +3.15 |
| COL/BeLive | +2.70 |
| Both Worlds | +2.65 |
| GammaTime | +2.35 |
21 distinct companies confirmed across the knowledge graph via SPARQL query.
Track C: Signal Weighting Research Program | Experiment 3
What parameters control the threshold between "this signal warrants a mitigation recommendation" and "this signal is expected volatility within a functioning strategy"?
| Parameter | Default | Optimized | Change |
|---|---|---|---|
| materiality_threshold | 2.000 | 2.362 | +18% |
| structural_change_weight | 1.500 | 2.286 | +52% |
| competitor_action_weight | 1.300 | 1.806 | +39% |
| tier_proximity_sensitivity | 3.000 | 5.902 | +97% |
| multi_dimension_threshold | 2 | 2 | +0 |
| trajectory_window | 4 | 8 | +4 weeks |
| volatility_dampener | 0.300 | 0.658 | +119% |
The optimizer learned to raise the materiality threshold (+18%), weight structural changes more heavily (+52%), extend the trajectory lookback window from 4 to 8 weeks, and increase the volatility dampener significantly (+119%) — meaning historically volatile companies get reduced urgency.
Tier proximity sensitivity nearly doubled (+97%), meaning the system becomes much more alert when companies approach tier boundaries.
4 sites deployed during this session, all on Cloudflare Pages.
| Site | URL | Account | Content |
|---|---|---|---|
| W13 Editorial | microco-weekly-editorial-bja-8zm.pages.dev | weareshur | 8-tab weekly report with corrected framing |
| W13 Validation | sbpi-w13-validation-3y2.pages.dev | weareshur | Prediction validation with back-to-editorial nav |
| Brand Intel Cards | sbpi-brand-intel.pages.dev | weareshur | 21 sortable company intelligence cards |
| Autoresearch Status | sbpi-autoresearch-status.pages.dev | getsteady | 13-day pipeline activity report |
The pipeline is operational. Nightly outputs and W14 evaluation cycle below.
Scheduler runs at 6:13 AM daily:
When W14 actuals are scored:
Each week adds ~800+ triples to the store. Current trajectory:
Domain-specific longitudinal data that general-purpose models lack access to.
The 75 synthetic labels bootstrap the system. As human expert labels replace synthetic ones (via the --label interactive interface), the signal weight optimizer converges on validated materiality thresholds. The 66.7% appropriate rate should improve as real expert judgment replaces synthetic labels.
The 21-card deck becomes a weekly deliverable. Each card's intelligence take updates as new data arrives, tracking structural position changes, dimension gaps closing or widening, and tier transition trajectories.