Skip to content
Skip article header Engineering

Source Weights After the Cutoff: The Limits of Our First Retrieval Policy

Weights of 0.10 to 5.00 reordered surviving results but could not rescue a source outside raw top-k or below the similarity cutoff in our first retrieval policy

Updated 5 min read 44 views
An engineer adjusting source preferences while checking a retrieval trace and candidate list.

Technically reviewed by Victor Sineglazov on .

We gave administrators a source-weight setting, but it could not promote every document they might expect it to promote. In our first retrieval policy, weighting happened after the raw candidate limit and similarity cutoff. A preferred source absent from that surviving set remained absent, even at the highest allowed weight.

The ordering was explicit in our September 24 R&D record. It is a useful example of why a ranking control needs a precise contract. On a professional learning platform for aesthetic medicine, a source preference can look like an authority rule. Our weight was narrower: a numeric preference applied to candidates that had already qualified.

The sequence was part of the policy

The retriever first requested the raw top-k candidates from vector search. It then removed candidates below the raw similarity threshold. Only after those steps did it multiply surviving scores by the source weight and reorder them.

That final reordering should not be confused with running a separate learned reranker. The policy described a score multiplication. Its inputs remained the fragments returned by the earlier search, with the earlier cutoff already enforced.

Stage Question answered Can a larger weight change it?
Active-source filter Is the fragment eligible for this search? No; lifecycle eligibility is a hard filter
Raw top-k retrieval Did vector search return the fragment? No; weighting has not run
Raw similarity cutoff Did the returned fragment pass the threshold? No; rejected fragments are already removed
Score multiplication and ordering Which surviving fragments receive preference? Yes; this is the control's actual scope

The allowed document weight ran from 0.10 to 5.00, with 1.00 as the default. That range described configuration, not calibrated probabilities or a validated measure of scientific authority. Multiplying a similarity score by a document preference did not turn the result into a confidence estimate.

Two absences that a weight could not repair

Consider a preferred source that would rank just outside the raw candidate limit. The multiplier never sees it. Increasing its weight can change the order of other returned fragments but cannot bring that source into the set. Diagnosing this case requires inspecting the raw search result before looking at the weighted order.

A second source might appear in the raw results but fall below the cutoff. It is removed before weighting. Here, increasing the weight also has no effect, but for a different reason. The candidate was retrieved and then rejected; the first source was never returned at all.

These examples follow directly from the recorded operation order. They are not benchmark observations or measurements of how often either failure occurred. They show why a report saying only "the preferred source did not appear" is insufficient to choose a fix.

Why the metadata did not resolve authority by itself

The source-administration work added fields such as tier, author, publication date and an external identifier. Those fields made provenance more explicit. They did not mean every attribute automatically affected retrieval, nor did a tier label substitute for deciding whether a fragment supported the question.

The active-status filter was different. A retired or superseded fragment was ineligible regardless of its weight. Our source-versioning account explains that lifecycle boundary. Allowing a ranking preference to bypass it would have changed the meaning of retirement.

We therefore needed to describe the control in terms an administrator could verify: it preferred qualifying results from a source. It did not guarantee that the source would be retrieved, and it did not establish that an answer based on that source was correct.

What a useful ranking investigation records

A retrieval trace printout with candidate tables before filtering and after source weighting.

For an unexpected result, I would retain the source version and eligibility state alongside the raw similarity and the configured weight. The comparison also needs the candidate limit and cutoff used for that request. A weighted final score without those earlier decisions hides whether the control had any opportunity to act.

A diagnostic view could show the raw candidate list, the survivors and their final order. That is a recommendation derived from the policy, rather than a claim that our historical interface already displayed every stage. It would let a developer distinguish a retrieval miss from a threshold rejection before changing source preferences.

Evaluation should likewise separate candidate coverage from final ordering. A test that checks only whether a favored document moves upward among survivors leaves the two absence cases untested. Conversely, raising candidate limits to make a weight effective changes the retrieval workload and the set being evaluated.

The limit we chose to leave visible

Our first policy accepted that a strong weight could not rescue a source outside raw top-k or below the raw cutoff. That constraint made the initial calculation easier to trace. It also meant the setting could not fulfill a broader promise such as always considering the highest-priority source.

Changing that promise would require revisiting candidate generation or the order of operations and evaluating the resulting system. It is a separate decision from the cutoff calibration problem described earlier in this series. One concerns which candidates survive; the other concerns how a source preference acts on the survivors.

Evidence scope: the September 24 retrieval-policy update and the September 23 document-administration specification with its weight clarification. The examples explain the recorded policy; no new experiment or clinical authority assessment is asserted.

FAQ

Last updated:

Quick answers to common questions about custom software development, pricing, process and technology.

  • 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.

Dmytro Ihnatov is the Lead Backend Developer at Pharos Production. He documents backend architecture and research experiments from the team's work on a professional learning platform for aesthetic medicine.

Dmytro Nasyrov, Founder and CTO at Pharos Production
Dmytro Nasyrov Founder & CTO Let's work together!

Your business results matter

Achieve them with minimized risk through our bespoke innovation capabilities

Your contact details
Please enter your name
Please enter a valid email address
Please enter your message

We use your details only to reply to your request. Data Privacy and Legal Notice

We typically reply within 24 hours

What happens next?

  1. Contact us

    Contact us today to discuss your project. We're ready to review your request promptly and guide you on the best next steps for collaboration

    Same day
  2. NDA

    We're committed to keeping your information confidential, so we'll sign a Non-Disclosure Agreement

    1 day
  3. Plan the Goals

    After we chat about your goals and needs, we'll craft a comprehensive proposal detailing the project scope, team, timeline and budget

    3-5 days
  4. Finalize the Details

    Let's connect on Google Meet to go through the proposal and confirm all the details together!

    1-2 days
  5. Sign the Contract

    As soon as the contract is signed, our dedicated team will jump into action on your project!

    Same day