FOLLOWINGorder-01 · Billingat the dock
ATOMIZE / FACTORY PLAY
Cut. Sort. Prove. Ship.
Run the line. Fix what gets withheld.
Wording
How matching scores work
Choosing Meaning or Shared words chooses how scores are computed, not a high or low score. The highest score ranks first; it does not prove the answer.
Meaning (semantic matching) compares the question and each piece as vectors. A model learned text-pattern representations; this example uses frozen 768-dimensional embeddings from the same model. Cosine ranges from -1 to 1 and compares their directions: closer to 1 means more similar directions, 0 means perpendicular, and -1 means opposite directions. Opposite directions do not necessarily mean logical contradiction. There is no universal good-score cutoff or confidence percentage.
Shared words (lexical matching) counts the fraction of distinct eligible question words found in each piece, after common words are excluded. That fraction and cosine use different scales. Do not compare them as accuracy scores.
For example, the Returns question asks about “broken earphones”; its source says “faulty headphones”. Meaning can match related text even when Shared words finds no eligible words in common.
Choices apply when cutting starts.
Ready. Run the line or step one tick.
Follow an order
Receiving dock → Cutter → Semantic sorter → Evidence inspection → Output dispatch · withheld orders drop to the rework bin
BillingReturnsPetsWithheldFollowed
Choose a station or order
Line settingsWorkers per station and batch size. Simulation ticks, not production latency.
Cutter workers 1–3
Sorter workers 1–3
Inspectors 1–2
Orders per source 1–4 · max 12 orders
Workers change concurrency, not evidence. Service ticks: dock 1 · cutter 1 (Large) or 2 (small) · sorter 2 or 3 · inspector 1. Illustrative, not measured.
Behind the machinesHow each station maps to the Atomize reference architecture.
| Station | In Atomize |
|---|---|
| Receiving dock | A BullMQ queue stored in Redis holds jobs until a worker pulls one. |
| Cutter | The chunking step inside a long-running Node worker. |
| Semantic sorter | Embedding plus vector ranking. Here the vectors are frozen; nothing is computed by a model. |
| Evidence inspection | An authored rule, separate from retrieval. Not entailment and not a generated answer. |
| Output dispatch | The response returned to the caller. |
| Rework bin | A retry with changed settings, not a dead-letter queue. |
Long-running workers run on Railway in the reference architecture; nothing here contacts Railway, Redis or BullMQ. A finished-answer application cache is separate from a model's KV cache, which holds attention state during generation and may be reused across requests when serving supports prefix caching. Neither cache is simulated.
Spatial placement is illustrative. Rankings are computed in the original 768-dimensional vector space, and no camera or view change touches them.
Run the line to load the frozen example and its model digest.