Benchmarks & Positioning

All numbers below are from frozen regression datasets and a public benchmark, measured end-to-end against the running engine. Dev and heldout splits are kept separate; nothing is tuned against heldout.


Against a Production Baseline

The Argus-faithful dataset (200 production-shaped surveillance records: telegraphic enums, NA sparsity) compares PrismDB against the production system’s substring comparator under a protocol deliberately generous to the baseline (free keyword decomposition, precision-rewarding scoring, corpus-aware queries):

SystemScore
PrismDB37/50
Production substring baseline34/50

The natural-language suite is where the gap opens (15/25, with age-vocabulary queries won via automatic enum projection: 60-plus → elderly, 20s → young). Zero manual aliases were declared; the automatic tiers covered everything. The baseline’s failures are a structural ceiling (substring matching cannot bridge vocabulary); PrismDB’s remaining failures have identified mechanisms and roadmaps.


ESCI (public e-commerce benchmark)

Amazon’s ESCI product-search benchmark, ~7.6M NLI pairs at full scale:

MetricBeforeAfter corpus-derived query understanding
nDCG@10 (all-200)0.5040.557
nDCG@10 (frozen test half)n/a0.568 (+0.066 vs round baseline; test gain exceeded dev, no overfitting)
Recall@500.6380.804
Warm latencyn/a~5ms (release build)

The gap to a monolithic hybrid retriever (0.663) closed ~33%, entirely via corpus-derived query understanding: zero domain hardcodes.


Regression Suites

DatasetShapeScore
Catalog30 records, 19 queries19/19
Large catalog250 records, 56 queries (dev/heldout)52/56 (26/28 + 26/28)
Surveillance proxy200 vision-LLM records, 12 dims30/50
Argus-faithful200 production-shaped records37/50 vs baseline 34/50
Workspace temporal15 tracks, 51 timestamped chunks11/16

Remaining workspace failures are documented honest boundaries: NLI correctly refusing weak-evidence matches, one measured dense-prefilter limit, one cross-track re-identification query that is out of scope.


Honest Positioning

Where PrismDB wins: attribute-decomposed queries over structured records, meaning queries whose terms map to independent record fields ("blue leather shoes", "elderly person carrying a red bag"). Per-dimension routing plus write-time vocabulary expansion is structurally better there than substring matching or one monolithic embedding.

Known structural boundaries:

  • Title-phrase decomposition: queries that are one long noun phrase against one long title field don’t decompose into dimensions; monolithic retrieval keeps an edge.
  • Reranker ceiling: a cross-encoder reranker over the same candidates reaches 0.694 nDCG@10 on ESCI’s test half; closing that gap requires a rerank stage, which is on the cost ladder to be weighed like every other tier.
  • Interpretive leaps invisible to dense retrieval (portfolio → document): beyond the current lexicon-projection tier’s reach; the query-log learning tier is the identified path.

Next public benchmark, STaRK-Amazon (NeurIPS 2024, planned): multi-attribute conversational product queries over structured entities (1.03M products), exactly the attribute-decomposed shape PrismDB is built for. Dense baseline is 39.16 Hit@1 with LLM-based SOTA at 61.73. ESCI shows where PrismDB loses (title-phrase); STaRK-Amazon is expected to show where it wins. Together, the honest story.

Every score above is reproducible from the frozen datasets in the repository (testdata/, tools/smoke, tools/benchmark).