What Our Number-and-Unit Scorer Could Actually Detect
Deterministic quantity matching caught unsupported values and prefix changes, with question-level metric formulas and semantic blind spots kept visible.
Reviewed by Victor Sineglazov on October 27, 2026.
Our evaluation UI could show an unsupported number, but the backend needed a rule for finding one. We built a deterministic scorer that compares quantities in an answer with quantities in its cited passages. It uses no judge model.
The distinction from citation validation is essential. A citation can point to the expected page while the answer changes a unit or introduces another value. The scorer adds a bounded mechanical check; it is not a clinical validation system or a general proof that the answer follows from the source.
Numbers needed their units and boundaries
The scorer normalizes text before matching expected facts and extracting quantities. Its rules address decimal punctuation, thousands separators, Unicode variants and number boundaries. A bare substring check would let an expected number match inside a different number or identifier.
Units carry meaning that case folding can destroy. The recorded regressions distinguish milliwatts from megawatts: an answer containing 65 MW is unsupported by a passage containing 65 mW. Long-form unit spellings and several equivalent written forms can normalize to the same internal quantity, but the code preserves the important prefix distinction.
| Fixture distinction | Why literal text matching was inadequate |
|---|---|
| Decimal comma and decimal point | Formatting can differ without changing the value |
| A list or range with one shared unit | Each member still needs the unit |
| Milliwatt versus megawatt prefix | Case can change scale rather than typography |
| A citation marker such as [1] | Its number is not an answer quantity |
| An unlisted unit | Ignoring it would hide a changed parameter |
The quantity test data are parser fixtures, not treatment recommendations. The actual code compares a normalized value-unit pair. It does not claim that a number is supported merely because those digits occur somewhere on the page.
Build the supported set from the cited passages
To find unsupported numbers, the pass collects quantity pairs from the full passages attached to the answer's citations. It then walks the answer's quantities and records a written quantity when its normalized pair is absent from that set. Duplicate reported strings are collapsed while preserving their order.
supported = quantity_pairs(cited_passages)
for quantity in quantities(answer_without_citation_markers):
if quantity.normalized_pair not in supported:
report_once(quantity.written_form)The set of pairs does not bind each quantity to a particular subject, condition or causal claim. Two values can both occur in a passage and still be attached to the wrong concepts in an answer. The algorithm is not a semantic entailment check.
A question verdict is stricter than one metric
For an ordinary answer, the implementation evaluates missing expected facts, unsupported quantities and citation placement. The full passing verdict requires an answer, the complete expected fact set, a qualifying citation and no hallucination flag under its recorded rule.
The accuracy metric has a narrower formula: among completed ordinary questions, it counts those with an answer and no missing expected facts. It is not the fraction of individual fact strings found, and it is not identical to the full passing verdict. A dashboard label should not silently substitute one denominator for another.
Refusal questions use a different branch. They expect a refusal and do not require a citation. Errors and skipped results remain visible counts outside the scored completed population. A run with no applicable observations can have a null metric rather than a manufactured zero.
What the scorer fixtures measured
The implementation record reported 199 scorer tests. A separate reworded fixture set had 69 passing cases out of 71, with the remaining two recorded as accepted false alarms. Those are tests of scoring behavior against prepared text. They are not 69 correct live model answers or evidence of clinical accuracy. The feature also stored benchmark questions, run snapshots and per-question outcomes. That persistence makes a result inspectable later, but it does not establish that the benchmark represents every use case or that the reference facts are complete. A stable measurement can still measure a narrow task.
Keep the gaps beside the useful signal
Token and quantity matching can miss paraphrases, semantic negation and relationships between otherwise present values. Conversely, a valid reformulation can trigger a false alarm. We would keep the answer and cited passage available to the reviewer instead of making the score the final authority.
Keep a fixture pair showing why a normalization rule exists and what it must not merge. A prefix-case negative control belongs beside a successful long-form alias case. The code and historical tests support those mechanical distinctions; this article does not report a new evaluation run or validate the medical content.
FAQ
Quick answers to common questions about custom software development, pricing, process and technology.
Type to filter questions and answers. Use Topic to narrow the list.
Showing all 14
No matches
Try a different keyword, change the topic or clear filters
-
How long have you been in business?
Pharos Production has been in business since 2013, with over 13 years of experience in custom software development. During this time, we have delivered over 110 applications for 200+ clients across 28 industries, including FinTech, healthcare, crypto and e-commerce. We are rated 5/5 on Clutch based on 107 verified reviews (2026).
-
What services do you provide?
Pharos Production provides six core service categories: AI Development (LLM applications, AI agents, machine learning and computer vision), Blockchain and Web3 (smart contracts, DeFi, tokenization on Ethereum, Solana, TON and other chains), FinTech Development (payment platforms, digital banking, KYC and AML integration), Software Development (mobile apps, web platforms, database design, UI/UX), Security and QA (code audits, penetration testing, smart contract audits, manual and automated testing) and Consulting (architecture design, MVP validation, startup consulting).
-
Where is Pharos Production located?
Pharos Production is headquartered in Las Vegas, Nevada, USA (5348 Vegas Dr, Las Vegas, NV 89108), with an engineering office in Kyiv, Ukraine (44-B Eugene Konovalets Str. Suite 201, Kyiv 01133). We work with clients worldwide and provide remote collaboration across all time zones. Visit our contact page for directions and scheduling options.
-
How big is your team?
Pharos Production has a team of 90+ engineers, including software developers, blockchain specialists, QA engineers, DevOps experts, UI/UX designers, project managers and solution architects. Our founder, Dr. Dmytro Nasyrov, holds a PhD in Artificial Intelligence and leads the technical direction of all projects.
-
What types of customers do you serve?
We serve a wide range of clients, from startups and product companies to mid-sized enterprises and large institutions. Our clients include crypto exchanges, FinTech providers (like Pleenk), healthcare organizations, sportsbook operators (like Pro Gambling), e-commerce platforms and SaaS companies. Pharos Production has worked with 200+ clients across 28 industries since 2013, adapting engagement models to match each client's stage, whether it is MVP validation for a startup or enterprise-scale development for an established business.
-
How is a custom software development company different from an agency?
A custom software development company like Pharos Production assigns one dedicated engineering team that owns your product across multiple release cycles, instead of handing it off once a contract ends. Agencies more often rotate staff between clients and optimize for fast delivery over long-term product ownership.
Pharos Production keeps the same team on your codebase through 2-week sprints, so there is no re-onboarding cost each time you request a new feature.
-
How much does custom software development cost?
Custom software development costs vary based on project scope and complexity. At Pharos Production, typical project ranges are: MVP development ($10,000-$25,000), suitable for startups validating a product idea; full-fledged production ($25,000-$50,000), for established businesses scaling a proven concept; and full-cycle development ($50,000-$80,000+), for complex enterprise-grade systems. These ranges include architecture design, development, QA testing and deployment. Hourly rates range from $50 to $99 depending on role and seniority. Final pricing depends on technology stack, number of integrations and engagement model (staff augmentation, dedicated team or project outsourcing).
-
How long does it take to develop a custom software application?
Development timelines depend on scope and complexity. At Pharos Production, a typical MVP takes 2-4 months, a production-ready application takes 4-8 months and a complex enterprise system can take 8-12+ months. We use an agile methodology with 2-week sprints, delivering working increments after each sprint. Every sprint includes a retrospective, progress report and planning session for the next iteration. This approach ensures transparency and allows businesses to launch faster by prioritizing high-impact features first. Get a timeline estimate for your project.
-
What industries does Pharos Production serve?
Pharos Production serves 28 industries: FinTech, MiCA Compliance, Banking, Insurance, Crypto, Healthcare, Fitness, E-Commerce, Food & Restaurant, On-Demand, Manufacturing, Automotive, Energy, Oil & Gas, Supply Chain, Construction, Real Estate, Gaming, Streaming, Media, Telecom, Education, Aviation, Travel, Logistics, Marketing, Agriculture and Recommender Systems. Our deepest expertise is in FinTech, blockchain and healthcare, where we have delivered compliance-ready platforms (HIPAA, PCI DSS, GDPR) and high-load systems handling thousands of concurrent users. For the latest industry insights, read our guides on FinTech trends in 2026 and the Web3 technology stack.
-
Why hire a software development company instead of building in-house?
Hiring a software development company offers faster time-to-market, lower upfront costs and access to specialized expertise without long-term employment commitments. According to Deloitte's 2024 Global Outsourcing Survey, 57% of companies outsource software development to access skills they cannot hire internally.
Factor In-house team Software development company Time to assemble 3-6 months (recruiting + onboarding) 1-2 weeks Upfront cost High (salaries, benefits, equipment) Lower (project-based pricing) Specialized expertise Limited to who you can hire locally Access to 90+ engineers across blockchain, AI, FinTech Scalability Slow (each new hire takes months) Fast (scale up or down per sprint) Long-term commitment Full-time employment contracts Flexible engagement models Risk High if key engineers leave Company ensures continuity and knowledge transfer For businesses that need blockchain, AI or high-load architecture expertise, outsourcing to a specialized firm like Pharos Production reduces risk and accelerates delivery.
-
What projects does Pharos Production not take on?
Pharos Production focuses on mid-to-large custom software projects with budgets starting at $10,000. We do not take on template-based websites, WordPress theme customization or short-term contracts under one month. We also do not provide non-technical staffing (marketing, sales or design-only roles). Our strongest fit is blockchain, FinTech and healthcare projects where security, compliance and high-load architecture are critical. For smaller projects or MVPs under $10,000, we recommend exploring freelance platforms or no-code tools as a more cost-effective starting point.
-
Why does Pharos Production use agile methodology?
We use agile with 2-week sprints because it reduces the risk of building features that miss the mark. Each sprint ends with a working demo, a retrospective and a plan for the next iteration.
This means clients see progress every 14 days and can adjust priorities based on real results, not assumptions. We chose this approach after years of experience showing that rigid, fixed-scope contracts lead to scope creep, missed deadlines and products that do not match market needs by launch day.
-
When should you NOT hire a custom software development company?
Custom development is not the right choice in every situation. You should not hire a custom software company if: your problem is fully solved by an existing SaaS product (e.g. Shopify for e-commerce, Salesforce for CRM); your budget is under $10,000 and timeline is under 4 weeks; you need a simple landing page or marketing website (WordPress or Webflow is faster and cheaper); or you are still validating the idea and have not spoken to potential users yet.
In these cases, off-the-shelf tools or no-code platforms offer better ROI. Custom development makes sense when you need unique workflows, regulatory compliance, high-load architecture or competitive differentiation that packaged software cannot provide.
-
What kind of projects has Pharos Production delivered?
Here are three anonymized examples from our recent delivery history:
FinTech startup - payment platform (MVP)
Scope: mobile app + backend API with bank-grade encryption. Team: 4 engineers, 1 QA. Timeline: 10 weeks. Budget: $38,000. Result: launched on schedule, processed $2M+ in transactions within the first quarter.Healthcare provider - patient portal (Full product)
Scope: HIPAA-aligned web platform with EHR integration, appointment scheduling and telemedicine. Team: 6 engineers, 1 DevOps, 2 QA. Timeline: 6 months. Budget: $120,000. Result: 15,000+ active patients, zero compliance violations in two annual audits.Crypto exchange - trading engine (Complex)
Scope: high-load matching engine handling 50,000+ orders per second, multi-chain wallet infrastructure on Ethereum and Solana. Team: 8 engineers, 2 QA, 1 security auditor. Timeline: 11 months. Budget: $340,000. Result: 99.97% uptime, passed three independent security audits.See more projects: NoMoreBets, Pulse, Sagas, Gambit Stream and Pleenk. For the full portfolio, visit our case studies. Learn more about the technology behind these projects in our guide to stablecoins and crypto infrastructure.
Stas Rysin is the Lead Frontend Developer at Pharos Production. His work covers the design system, reader interfaces and administration workflows of a professional learning platform for aesthetic medicine.
