Last updated 4 months ago
News articles are abundant but trust is scarce. Polarized coverage, opaque biases, and AI fakes make it hard to check facts or origin across outlets especially in Argentina’s intense media environment
Mobile-first platform cluster sources, extracts “consensus facts,” maps outlet bias, and anchors each summary’s origin on Cardano for open, tamper-evident verification.
Please provide your proposal title
AI News Summaries + Source & Bias traceability-For Argentina
Enter the amount of funding you are requesting in ADA
139000
Please specify how many months you expect your project to last
12
Please indicate if your proposal has been auto-translated
No
Original Language
en
What is the problem you want to solve?
News articles are abundant but trust is scarce. Polarized coverage, opaque biases, and AI fakes make it hard to check facts or origin across outlets especially in Argentina’s intense media environment
Supporting links
Does your project have any dependencies on other organizations, technical or otherwise?
No
Describe any dependencies or write 'No dependencies'
No dependencies
Will your project's outputs be fully open source?
No
Please provide details on the intellectual property (IP) status of your project outputs, including whether they will be released as open source or retained under another licence.
The project is not open source, but we are commited to sharing comprehencive reports along the way, plus a complete closeout report that includes findings for similar enterprises to learn from
Please choose the most relevant theme and tag related to the outcomes of your proposal
Connected Community
Describe what makes your idea innovative compared to what has been previously launched in the market (whether by you or others).
We pair AI news synthesis with public, tamper-evident records on Cardano. Each summary links to its source list and a content hash anchored on-chain (transaction metadata and Cardano Improvement Proposal (CIP)-68). Rather than claim neutrality, we reveal how claims were formed, highlight narrative differences, and invite community participation through wallet-based reactions and bias-perception voting. Argentina’s high-pressure news cycle is an ideal stress test for a template that can later be replicated.
Describe what your prototype or MVP will demonstrate, and where it can be accessed.
A working web MVP will show: (1) story clustering across ~40 Argentine/international sources; (2) Consensus facts vs Narrative differences; (3) outlet/journalist profiles with bias indicators and community perception; (4) a Verify on Cardano link to view the on-chain record (metadata and CIP-68 “Story Token”). Access: public URL with repositories for contracts, verification tooling, and documented pre-prod/testnet transactions.
Describe realistic measures of success, ideally with on-chain metrics.
By project end: ≥100 anchored summaries; ≥150 on-chain events (hashes or tokens); ≥50 unique wallets using Verify. Off-chain: ≥40 outlet/journalist profiles with indicators; ≥200 user reactions to summaries; ≥200 bias-perception votes on profiles; conversion from closed-alpha to public MVP achieved.
Please describe your proposed solution and how it addresses the problem
We will deliver a prototype that ingests diverse news sources, clusters related coverage, extracts claims, estimates cross-source consensus, and publishes a transparent summary that is cryptographically anchored on Cardano.
Argentina blends vibrant independent journalism with strong corporate interests, state intervention, and designed narratives. Citizens face a daily crossfire of claims. Our mission is to shrink the gap between people and verifiable facts by showing what multiple sources agree on, what they dispute, and how perspectives diverge—then anchoring each summary’s origin so quiet edits are detectable. We aim to promote independent journalism and truth-seeking with a mechanism that increases transparency, traceability of facts, and diversity of sources without depending on a single gatekeeper that could be compromised. Cardano provides the backbone: public records anyone can check.
1. Data & Story Engine (~40 sources). We ingest RSS/APIs/crawlers for major Argentine outlets, independent journalists/newsletters, and select international references. We normalize metadata (outlet, author when available, timestamps, topics, geography). Using multilingual embeddings and entity/event extraction, we cluster articles into story bundles, detect wire duplication to avoid over-weighting reposts, and maintain a source graph distinguishing primary from derivative reporting.
2. Bias & Profile Layer (transparent indicators). Each outlet/journalist has a public profile with bias indicators (e.g., political orientation, establishment stance, factual reliability) derived from clearly described criteria, AI-assisted analysis, and community input. Votes do not auto-flip indicators; they are shown as perception trends and feed a human review queue.
**3. Consensus Facts & Narrative Differences. **For each story we extract claims (who/what/where/when; numbers; quotes), label each as verifiable fact, attributed statement, or interpretation, align semantically equivalent claims across outlets, compute a transparent consensus score (including cross-ideology agreement), and present two sections: Consensus facts and Narrative differences with representative quotes/headlines. Sensitive stories receive human review during the pilot.
**4. Cardano Anchoring & Verification. **Each published summary is serialized as off-chain JSON (e.g., InterPlanetary File System (IPFS)) containing the summary, full source list, model versions, and pipeline configuration. We write its content hash plus descriptors (story ID, timestamp, language) to Cardano via transaction metadata and, for selected high-salience stories, a non-transferable CIP-68 token whose datum stores the same hash and descriptors. A “Verify on Cardano” button links users to the corresponding record and a proof page.
5. Community Feedback & Participation.
**Tech stack and security. **Backend services (TypeScript/Go/Python) orchestrate ingestion, clustering, claim alignment, and anchoring. An indexer tracks story transactions for analytics. The mobile-first UI emphasizes clarity: story cards lead with Consensus facts, then Narrative differences and bias context. Security includes static analysis, dependency scanning, least-privilege keys, audit logs, and privacy-aware handling of user input.
Openness & replication. We open-source smart contracts and verification tooling, publish indicator criteria and methods, and document replication guidelines so other regions can adopt the approach with localized source packs.
Please define the positive impact your project will have on the wider Cardano community
For citizens and civil society.
Clear Consensus facts reduce uncertainty; Narrative differences reveal how agendas shape coverage; on-chain records make silent edits detectable. Community reactions surface blind spots; perception voting shows where audiences detect bias.
For journalists and independent media.
A neutral infrastructure—not a centralized arbiter—helps reporters compare how a story travels across outlets, cite source trails, and discover overlooked primary sources. Independent outlets gain visibility when their reporting anchors widely agreed facts.
For Cardano.
This prototype demonstrates public-interest utility: verifiable knowledge trails, wallet-based participation, and auditable community signals. By anchoring summaries and aggregate feedback hashes, Cardano becomes a trust-minimized backbone for media transparency. Argentina first; then replication with localized source packs and indicator criteria.
Broader outcomes.
Datasets and open code enable research on misinformation dynamics, media bias, and content integrity. The project creates a reusable pattern for civic technology that aligns with Cardano’s mission to deliver transparent, verifiable systems.
What is your capability to deliver your project with high levels of trust and accountability? How do you intend to validate if your approach is feasible?
Team Roles. Product lead; AI/NLP engineer; smart-contract/anchoring engineer; full-stack developer; DevOps/SRE; data PM; media/bias research lead; UX researcher in Argentina; legal/compliance advisor.
Feasibility. Scope focuses on delivering end-to-end value: ingest ~40 sources → cluster → extract/align claims → compute consensus → publish with indicators and source references → anchor a content hash on Cardano. Community modules (reactions, perception voting) use wallet standards, off-chain storage, and periodic on-chain anchoring for auditability.
Compliance. Funds are for future work; deliverables are publicly verifiable; final deployment targets a public testnet/mainnet MVP and required close-out artifacts (report and video).
Milestone Title
Whitepaper & Planning
Milestone Outputs
Acceptance Criteria
Evidence of Completion
Delivery Month
2
Cost
17850
Progress
10 %
Milestone Title
Data Pipeline & Clustering Core
Milestone Outputs
Acceptance Criteria
Evidence of Completion
Delivery Month
5
Cost
23800
Progress
30 %
Milestone Title
Alignment, Consensus & Community Reactions
Milestone Outputs
Acceptance Criteria
Evidence of Completion
Delivery Month
8
Cost
23800
Progress
60 %
Milestone Title
Bias-Perception Voting & Beta Hardening
Milestone Outputs
Acceptance Criteria
Evidence of Completion
Delivery Month
11
Cost
33800
Progress
80 %
Milestone Title
Public MVP, Testing, Feedback & Close-Out
Milestone Outputs
Acceptance Criteria
Evidence of Completion
Delivery Month
12
Cost
39750
Progress
100 %
Please provide a cost breakdown of the proposed work and resources
Total ₳119,000 (future work only).
• Engineering (AI/NLP, full-stack, anchoring): ₳72,000
• Data ops & labeling (evaluation sets): ₳17,000
• UX research & testing (Argentina): ₳8,000
• Infrastructure (ingestion, storage, analytics, pre-prod ops): ₳9,500
• Security & audit (contracts/app), QA: ₳8,500
• Legal/compliance review (sources, privacy, T&Cs): ₳5,500
• Community participation & expert panel stipends: ₳6,000
• Contingency (~6.3%): ₳8,000
Milestone split: M1 15% ₳17,850; M2 20% ₳23,800; M3 20% ₳23,800; M4 20% ₳23,800; Final 25% ₳29,750.
How does the cost of the project represent value for the Cardano ecosystem?
The MVP delivers a credible public-interest application of Cardano: verifiable knowledge trails, wallet-based participation, and auditable community signals. Open contracts and verification tooling enable reuse across regions. Focusing on Argentina yields measurable results with clear on-chain metrics and user engagement, allowing the community to verify impact and decide on future scaling. A precise Statement of Milestones and Close-Out deliverables ensures accountability and alignment with Cardano priorities.
I confirm that evidence of prior research, whitepaper, design, or proof-of-concept is provided.
Yes
I confirm that the proposal includes ecosystem research and uses the findings to either (a) justify its uniqueness over existing solutions or (b) demonstrate the value of its novel approach.
Yes
I confirm that the proposal demonstrates technical capability via verifiable in-house talent or a confirmed development partner (GitHub, LinkedIn, portfolio, etc.)
Yes
I confirm that the proposer and all team members are in good standing with prior Catalyst projects.
Yes
I confirm that the proposal clearly defines the problem and the value of the on-chain utility.
Yes
I confirm that the primary goal of the proposal is a working prototype deployed on at least a Cardano testnet.
Yes
I confirm that the proposal outlines a credible and clear technical plan and architecture.
Yes
I confirm that the budget and timeline (≤ 12 months) are realistic for the proposed work.
Yes
I confirm that the proposal includes a community engagement and feedback plan to amplify prototype adoption with the Cardano ecosystem.
Yes
I confirm that the budget is for future development only; excludes retroactive funding, incentives, giveaways, re-granting, or sub-treasuries.
Yes
I Agree
Yes
• Product Lead (news workflows, roadmap)
• Smart-Contract/Anchoring Engineer (metadata anchoring, CIP-68, audits)
• Full-Stack Developer (web UI, APIs, admin tools)
• Media/Bias Research Lead (indicator design, expert panel)
• UX Researcher (Argentina-based tests, accessibility)
Particularly, the proposer ( https://www.linkedin.com/in/alex-b-g/ ) has before developed blockchain based projects in argentina, as well as co-founding the argentine blockchain foundation. With said foundation, we were funded during Catalyst fund 14, and are currently developing said projects. During fund 14, the proposer is not part of any of the projets proposed by said foundation, and has created 2 distinct individual proposals that will not share any team members and will have no overlap whatsoever.