A gate that fails
hangs red.

Every print on this line is machine-generated from a gate's own artifact, never hand-typed. Self-reports, seals, and predictions hang on the same dated wire, newest first. One red print is the control: the check that proves the checker can say no. The rest are what the record says.

36 passed12 mixed04 failed (01 control)07 sealed13 latent

grades on the wire ·self-report a script of mine says my pages match ·reproducible a number with a command that re-derives it ·sealed a signature in a public log

Walk one artifact down the bench, measurement to record to seal: /verification

  1. operant-j · gemini-3.1-pro-high+v1.1operantj/ref-window-backup · 2026-08-19SEALED · T2
  2. operant-j · deepseek-v4-flash-free+v1.1operantj/ref-window-backup · 2026-08-19FAILED · SEALED · T2
  3. operant-j · nemotron-3-ultra-free+v1.1operantj/ref-window-backup · 2026-08-19FAILED · SEALED · T2
  4. operant-j · qwen3:8b+v1.1operantj/ref-window-backup · 2026-08-19SEALED · T2
  5. operant-j · claude-sonnet-4-6+v1.1operantj/ref-window-backup · 2026-08-19FAILED · SEALED · T2
  6. harnessbench-semantic-clean-roomguard/destructive-execution · 2026-08-16SEALED · T2
  7. field-manualreview/rights-gate · 2026-08-05SEALED · T1
  8. portfolio-index6/7 checks · 2026-07-11PASSED
  9. Synthetic Portfolio Repo Fixture5/7 checks · 2026-07-07MIXED
  10. agent-bridge5/7 checks · 2026-07-07PASSED
  11. APIReverse1/7 checks · 2026-07-07PASSED
  12. bridge-db5/7 checks · 2026-07-07PASSED
  13. Calibrate4/7 checks · 2026-07-07MIXED
  14. Cartograph4/7 checks · 2026-07-07MIXED
  15. Chromafield4/7 checks · 2026-07-07MIXED
  16. ConvictionMapper5/7 checks · 2026-07-07PASSED
  17. cost-tracker5/7 checks · 2026-07-07PASSED
  18. egress-guard-oss6/7 checks · 2026-07-07PASSED
  19. GhostRoutes4/7 checks · 2026-07-07MIXED
  20. GithubRepoAuditor6/7 checks · 2026-07-07PASSED
  21. harness-scorecard5/7 checks · 2026-07-07PASSED
  22. HowMoneyMoves5/7 checks · 2026-07-07PASSED
  23. ink1/7 checks · 2026-07-07PASSED
  24. ITServiceHealth6/7 checks · 2026-07-07PASSED
  25. Liminal4/7 checks · 2026-07-07MIXED
  26. mcp-trust6/7 checks · 2026-07-07PASSED
  27. MCPAudit6/7 checks · 2026-07-07PASSED
  28. mcpforge6/7 checks · 2026-07-07PASSED
  29. ModelColosseum3/7 checks · 2026-07-07PASSED
  30. NetworkDecoder3/7 checks · 2026-07-07PASSED
  31. NeuralNetwork5/7 checks · 2026-07-07PASSED
  32. Nocturne4/7 checks · 2026-07-07MIXED
  33. notification-hub5/7 checks · 2026-07-07PASSED
  34. Notion5/7 checks · 2026-07-07PASSED
  35. operant-public5/7 checks · 2026-07-07PASSED
  36. OrbitMechanic5/7 checks · 2026-07-07PASSED
  37. portfolio-health5/7 checks · 2026-07-07PASSED
  38. portfolio-mcp6/7 checks · 2026-07-07PASSED
  39. Pressfield6/7 checks · 2026-07-07PASSED
  40. proof-pr5/7 checks · 2026-07-07PASSED
  41. Redact4/7 checks · 2026-07-07MIXED
  42. ScreenshottoDataSelect5/7 checks · 2026-07-07PASSED
  43. signal-noise5/7 checks · 2026-07-07PASSED
  44. sovereign5/7 checks · 2026-07-07PASSED
  45. thought-trails3/7 checks · 2026-07-07PASSED
  46. Content parity: HTML pages and Markdown mirrors2026-07-03PASSED
  47. By 2028-07-03, Anthropic or OpenAI will be p…90% · resolves by 2028-07-03LATENT
    resolution criterion

    A company announcement, investor letter, or reporting from an established financial outlet (citing company-provided figures) states annualized revenue or run-rate above $20B for either company on or before the resolve date.

  48. By 2028-07-03, a peer-reviewed paper or majo…75% · resolves by 2028-07-03LATENT
    resolution criterion

    A publicly available paper (arXiv or peer-reviewed venue) or official lab report shows, in its own tables, the same model scoring >=10 points higher on SWE-bench Verified, Terminal-Bench, or an equivalent standard benchmark under a modified harness/scaffold.

  49. The official MCP registry (registry.modelcon…50% · resolves by 2027-01-03LATENT
    resolution criterion

    The official MCP registry's public API or web UI reports a total server count above 10,000 on or before the resolve date; a dated archive capture or API response screenshot suffices.

  50. By 2028-07-03, at least three venture-funded…60% · resolves by 2028-07-03LATENT
    resolution criterion

    Public funding announcements (company posts, Crunchbase, or press) show three distinct companies, each with a primary product described as MCP/agent-tool security or trust scanning, each with a disclosed round >=$10M announced on or before the resolve date.

  51. By 2027-07-03, the MCP specification will in…45% · resolves by 2027-07-03LATENT
    resolution criterion

    The MCP specification at modelcontextprotocol.io (or its changelog/commit history) contains normative RFC-2119 MUST language whose stated purpose is mitigating tool-description injection or tool poisoning, merged on or before the resolve date.

  52. By 2027-07-03, at least three major coding h…85% · resolves by 2027-07-03LATENT
    resolution criterion

    Official public documentation for three of the listed products, live or archived on or before the resolve date, describes spawning multiple concurrent agents/subagents on one task as a GA (non-beta, non-waitlist) feature.

  53. GitHub's 2026 Octoverse report will state th…55% · resolves by 2027-01-03LATENT
    resolution criterion

    The published Octoverse 2026 report (github.blog or octoverse.github.com) contains a headline or body claim that >50% of code written/pushed by developers in its data or survey involved AI assistance; exact framing may vary but the majority claim must be explicit.

  54. By 2028-07-03, an open-weights model that ru…55% · resolves by 2028-07-03LATENT
    resolution criterion

    A model with publicly downloadable weights appears at >70% on the SWE-bench Verified leaderboard, and its model card or a reproducible community report documents inference (possibly quantized) within 32GB VRAM on a single consumer card.

  55. By 2027-01-03, at least two of Anthropic, Op…45% · resolves by 2027-01-03LATENT
    resolution criterion

    Public pricing pages (verifiable via Wayback Machine captures dated on or before 2027-01-03) show two such companies each offering an individual-plan tier at >=$300/month whose marketing copy centers agents or autonomous task execution.

  56. By 2027-01-03, at least two frontier labs wi…70% · resolves by 2027-01-03LATENT
    resolution criterion

    Two distinct frontier labs' official model release blog posts, published on or before the resolve date, each cite a score on one identical third-party agentic/terminal benchmark; the posts are publicly readable.

  57. By 2028-07-03, a publicly listed model will …88% · resolves by 2028-07-03LATENT
    resolution criterion

    The official SWE-bench leaderboard (swebench.com or its successor) shows any model entry at >=90.0% on the Verified split on or before the resolve date; archived leaderboard snapshots count.

  58. By 2028-07-03, a software company with 5 or …50% · resolves by 2028-07-03LATENT
    resolution criterion

    Public statements from the company (blog, interview, or verified social post) claim >=$10M ARR and <=5 employees and primary AI-agent authorship, corroborated by coverage in two established tech publications on or before the resolve date.

  59. PortfolioCommandCenter7/8 checks · 2026-06-27MIXED
  60. MCP live readback: saagarpatel-portfolio7/8 checks · 2026-06-27MIXED
  61. MCPAudit report: sample_audit_report2/6 checks · 2026-06-27 · the controlFAILED · CONTROL
  62. OPERANT self-serve result: heuristic-baseline3/5 checks · 2026-06-27MIXED
  63. OPERANT public lab calibration profiles3/3 checks · 2026-06-27PASSED
  64. SARIF report: sarif-sample-report2/4 checks · 2026-06-27MIXED

source commit 9d06aafd7a25 · generated at build · never hand-typed · seals verify on their own print's page