{"slug": "case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91", "title": "Case study: how an AI jury scored and paid a Verdikta bounty (#139, 91%)", "summary": "A student and open source contributor completed Verdikta bounty #139, a 0.01 ETH task on Base requiring a personal bio, which was scored 91% against a 50% pass threshold by an AI jury of two models — OpenAI's gpt-5.6-sol and Anthropic's claude-sonnet-5 — each weighted 50%. The five-criterion rubric weighted personal history highest at 25%, with agent use, tools and authenticity at 20% each and geography at 15%; the submission's strongest marks came from authenticity and concrete tooling references, while a slightly brief personal history accounted for the missing points. The jury's full reasoning was published to IPFS.", "body_md": "I'm a student and open source contributor (Rust, Node.js). This is a walk-through of one completed bounty on Verdikta Bounties: what was asked, how the rubric measured it, what score it got, and how it settled. Everything below is public on the bounty page.\n\nWhat was asked\n\nBounty #139, \"Personal Bio: Tell us about yourself\", paid 0.01 ETH on Base. It was a targeted bounty: only one wallet address could submit work. The task: write a personal bio with location, personal history, experience with AI agents, tools, and anything else the author wanted to share, \"genuine and specific\".\n\nWhat the rubric measured\n\nThe evaluation had five weighted criteria:\n\nCriterion   Weight  What it checks\n\nGeographical    0.15    Includes a location or region\n\nPersonal-History    0.25    Shares background\n\nAgent-Use   0.20    Describes experience with AI agents\n\nTools   0.20    Lists tools, tech stack, capabilities\n\nAuthenticity    0.20    Feels genuine and specific, not generic\n\nThe pass threshold was 50%.\n\nWho judged it\n\nTwo models scored independently and the final score is a weighted average: one from OpenAI and one from Anthropic, 50% weight each. Using two different providers means one model's quirks can't decide the outcome alone.\n\nWhat was submitted and the score\n\nOne submission from wallet 0x589952a6cD216F6971dAc0506DD695B8E5eF69C7, approved, final score 91.0% (threshold 50%). I wrote the bio myself. The jury's full reasoning is stored on IPFS (CID Qmdn7acEBzy6Lqp9s1edQQaHidNn3uhMWSwHBcqksgczHb), so anyone can read it.\n\nWhat the jury said, in short:\n\nBoth models voted FUND: gpt-5.6-sol 959,000 vs 41,000 for DONT_FUND, and claude-sonnet-5 880,000 vs 120,000. Aggregated: 919,500 vs 80,500.\n\nStrongest points: authenticity and tools. The bio named concrete things (Node.js, Docker, GitHub CLI, MetaMask, Base, USDC) and real constraints, not generic claims.\n\nThe one soft spot: personal-history depth. One model found it slightly brief. That's where the missing ~9 points came from.\n\nLesson for my next submission: specific tools and concrete failure modes scored high; more background on how I got here would have scored higher.\n\nWhat I take from it\n\nRubrics with weights are legible. I could see exactly which parts of the answer counted most (history at 25%).\n\n\"Authenticity\" is the soft spot. It's the one criterion a model judges by feel, so generic text is the main risk.\n\nTradeoff: small payouts and AI judges mean this suits short, well-defined tasks, not open-ended work.\n\nBounty page: [https://bounties.verdikta.org/bounty/139](https://bounties.verdikta.org/bounty/139)", "url": "https://wpnews.pro/news/case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91", "canonical_source": "https://dev.to/drdz23/case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91-bi7", "published_at": "2026-10-09 01:11:28+00:00", "updated_at": "2026-10-09 01:18:04.079212+00:00", "lang": "en", "topics": ["ai-agents", "ai-products"], "entities": ["Verdikta", "OpenAI", "Anthropic", "Base", "gpt-5.6-sol", "claude-sonnet-5", "IPFS", "MetaMask"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91", "markdown": "https://wpnews.pro/news/case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91.md", "text": "https://wpnews.pro/news/case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91.txt", "jsonld": "https://wpnews.pro/news/case-study-how-an-ai-jury-scored-and-paid-a-verdikta-bounty-139-91.jsonld"}}