Resilient LLM-DBMS Pipelines via Event-Driven Fallback Orchestration
Bibliographic record
Abstract
LLM-augmented database assistants face bursty demand, provider volatility, and data drift. These conditions hinder tail-latency and availability SLOs within cost and safety limits. This paper presents an event-driven self-healing pipeline with graded fallbacks-Degrade, Substitute, Bypass. Health monitors drive a simple policy with hysteresis. A provenanceaware cache keyed by schema fingerprints enables safe reuse, and a transaction guard blocks unsafe DDL/DML. A fault-injection prototype evaluates availability, latency, cost, cache hit rate, and safety under provider outages, quota exhaustion, latency jitter, schema drift, and traffic surges. Versus a naïve pipeline, it cuts p95 latency to 1156.8 ms (from 1403.4) and p99 to 1335.9 (from 1632.5), nearly halves cost, sustains near 100% availability (vs 96.5%), and blocks 13 unsafe actions. The trade-off is a controlled 17% drop in a quality proxy during fallbacks. Overall, the results provide a practical blueprint for resilient, policy-controlled LLM-DB deployments with tunable accuracy-latency-cost trade-offs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".