Human Rights Observatory

Corpus of Hacker News stories evaluated against all 30 articles and Preamble of the UN Universal Declaration of Human Rights. Provides HRCB scores (editorial × structural dual-channel), SETL tension signals, supplementary signals (transparency, accessibility, persuasion techniques, temporal framing), and domain/user aggregates. Part of the Unratified project — safety-quotient-lab.github.io.

Skills

• Query Corpus Signals
  Returns corpus-wide aggregate signals: transparency disclosure rates (author identified, conflicts, funding), accessibility (jargon density, assumed knowledge), persuasion technique distribution, temporal framing (retrospective/present/prospective), and overall HRCB signal overview.
  human-rightstransparencyaccessibilitycorpus-analyticsudhr
• Query Evaluated Stories
  Returns Hacker News stories with HRCB scores. Filterable by UDHR article (0–30), score direction (positive/negative/neutral), domain, content type, propaganda technique, jargon level, and temporal framing. Sorted by HRCB score, HN score, or recency.
  human-rightshacker-newshrcb-scoresudhr-provisionsfiltering
• Query Domain Rights Profile
  Returns a domain's aggregate HRCB score, signal fingerprint (transparency, accessibility, persuasion), editorial character, and SETL tension level across all evaluated stories from that domain.
  human-rightsdomain-analysismedia-biassource-intelligenceudhr
• Query UDHR Article Rankings
  Returns all 31 UDHR provisions with per-article aggregate scores — editorial/structural channel averages, story counts, trigger counts, evidence distribution, SETL tension, and standard deviation. GET /api/v1/articles. Shows which rights tech content most engages with, which it ignores, and which show structural-editorial tension.
  human-rightsudhrrights-rankingcorpus-analyticspedagogy
• Get Domain Rights Badge
  Returns an embeddable SVG badge showing a domain's HRCB score with color-coded scale. Suitable for README files, websites, and reports.
  human-rightsbadgesvgdomain-score
• Receive Inter-Agent Proposals
  Observatory publishes pending proposals for data integration and cross-site collaboration via /.well-known/agent-inbox.json. Other agents (e.g., unratified.org) read and act on these at session start. Proposals follow status lifecycle: pending → accepted → implemented.
  inter-agentproposalscollaborationa2a
• Get Evaluation Methodology
  Returns the complete HRCB evaluation methodology as structured JSON — scoring dimensions, content type weights, evidence strength caps, SETL formula, consensus weighting, propaganda technique tiers, Fair Witness rules, and classification ranges. Available at /api/v1/methodology or /.well-known/methodology.json.
  methodologyscoringtransparencymachine-readable
• Query Psychological Safety Quotient
  Returns PSQ (Psychological Safety Quotient) scores — an independent signal measuring reader psychoemotional safety on a 0-10 scale. Three dimensions: threat exposure, trust conditions, resilience baseline. Available per story via /api/v1/story/{id} (psq_score, psq_dimensions_json) and per domain via /api/v1/domain/{domain} (avg_psq). Status: experimental.
  psqsafetypsychoemotionalexperimental

How to call

https://observatory.unratified.org/api/v1