{ "schema": "cortist.accountability.readiness.v1", "date_utc": "2026-10-27", "editorial_state": "documented_prelock_readiness_audit", "independently_certified": false, "baseline": { "topicCount": 13, "numericDraftCount": 8, "unquantifiedResearchTopics": 5, "milestoneResearchCandidates": 5, "externalLockedForecasts": 0, "independentlyResolvedOutcomes": 0, "brierMean": null, "verifiedFoundingManifestSnapshots": 2, "foundingManifestScope": "The original /data/forecasts/manifest.json SHA-256 workflow currently verifies the founding F-001 and F-002 snapshots; registry v4 documents six additional subjective forecast drafts separately. These are not extra independently verified locked forecasts." }, "forecastHistorySource": "/data/forecasts/history/registry-v4-thirteen-topics-20261026.json", "foundingManifest": "/data/forecasts/manifest.json", "forecastRows": [ { "id": "F-001", "label": "Artificial General Intelligence", "topic": "agi", "detail": "/forecast/agi-by-2030/", "valuePercent": 38, "recordedDate": "2026-10-22", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-001/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2030-12-31T23:59:00Z", "sha256": "5e4416bf7b6c6b3caf63c4926998cf1f5ceb3c5f81ea6d07f6859373238c618b" }, { "id": "F-002", "label": "Superintelligence", "topic": "superintelligence", "detail": "/forecast/superintelligence-by-2040/", "valuePercent": 24, "recordedDate": "2026-10-22", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-002/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2040-12-31T23:59:00Z", "sha256": "cb742c65cfd5c6b51a28cdfa9e655e096c77b2d6d2658f8aaac91d57ffd061b7" }, { "id": "F-003", "label": "AI & Robotics", "topic": "ai-and-robotics", "detail": "/forecast/robotics-autonomous-shift-2035/", "valuePercent": 35, "recordedDate": "2026-10-26", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-003/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2035-12-31T23:59:00Z", "sha256": null }, { "id": "F-004", "label": "AI & Cybersecurity", "topic": "ai-cybersecurity", "detail": "/forecast/autonomous-cyber-agents-2030/", "valuePercent": 45, "recordedDate": "2026-10-26", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-004/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2030-12-31T23:59:00Z", "sha256": null }, { "id": "F-005", "label": "AI Chips & Compute", "topic": "ai-chips-and-compute", "detail": "/forecast/ai-chips-and-compute-2030/", "valuePercent": 55, "recordedDate": "2026-10-26", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-005/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2030-12-31T23:59:00Z", "sha256": null }, { "id": "F-006", "label": "AI & Science", "topic": "ai-and-science", "detail": "/forecast/ai-and-science-2035/", "valuePercent": 40, "recordedDate": "2026-10-26", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-006/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2035-12-31T23:59:00Z", "sha256": null }, { "id": "F-007", "label": "AI & Economy", "topic": "ai-and-economy", "detail": "/forecast/ai-and-economy-2035/", "valuePercent": 35, "recordedDate": "2026-10-26", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-007/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2035-12-31T23:59:00Z", "sha256": null }, { "id": "F-008", "label": "AI & Governance", "topic": "ai-and-governance", "detail": "/forecast/ai-and-governance-2032/", "valuePercent": 60, "recordedDate": "2026-10-26", "version": "v0.1", "originalSnapshot": "/data/forecasts/F-008/v0.1.json", "state": "provisional_draft", "locked": false, "scorable": false, "deadline": "2032-12-31T23:59:00Z", "sha256": null } ], "holdGates": [ { "gate": "g1", "requirement": "Versioned public snapshot with SHA-256", "passedAsOfOriginalReview": true, "evidenceOrBlocker": "https://cortist.com/data/forecasts/manifest.json" }, { "gate": "g2", "requirement": "Separate R2 archive with snapshot retention", "passedAsOfOriginalReview": true, "evidenceOrBlocker": "Cloudflare R2 bucket cortist-forecast-archive; snapshots/ prefix; 20-year age-based retention; admin can alter/remove rules" }, { "gate": "g3", "requirement": "Evidence rules and numerical thresholds independently reviewed", "passedAsOfOriginalReview": false, "evidenceOrBlocker": "Rulebook proposals only; no independent evaluation or approval" }, { "gate": "g4", "requirement": "Two independent conflict-cleared reviewer signoffs", "passedAsOfOriginalReview": false, "evidenceOrBlocker": "No reviewers appointed" }, { "gate": "g5", "requirement": "An independent external cryptographic timestamp anchor verified", "passedAsOfOriginalReview": false, "evidenceOrBlocker": "Not configured: R2 upload time and Pages deployment times are controlled by the same provider" }, { "gate": "g6", "requirement": "A prospectively issued and publicly confirmed lock snapshot", "passedAsOfOriginalReview": false, "evidenceOrBlocker": "None. Prior drafts remain ineligible." }, { "gate": "g7", "requirement": "Public resolution and scoring workflow", "passedAsOfOriginalReview": true, "evidenceOrBlocker": "https://cortist.com/forecast/protocol/ and https://cortist.com/forecast/results/ (zero adjudications)" } ], "milestoneRows": [ { "id": "CM-001", "question": "Will an AI coding agent resolve 90% of SWE-bench Pro V2 private tasks by October 2027?", "slug": "private-coding-agent-90-percent-2027", "url": "/milestones/private-coding-agent-90-percent-2027/", "topic": "AI Agents", "deadline": "2027-10-27", "status": "research-draft", "probability": null, "scorable": false, "prelockBlocker": "Freeze a permanent private-split identifier, task denominator and official archive before probability issuance.", "evidenceRuleYes": "The benchmark owner publishes a qualifying audited result on the frozen private V2 task set no later than the deadline.", "evidenceRuleNo": "No qualifying result after an official dated archive review.", "primarySources": [ "https://labs.scale.com/blog/swe-bench-pro-v2", "https://labs.scale.com/leaderboard/swe_bench_pro_public_v2" ] }, { "id": "CM-002", "question": "Will a robot complete at least 50% of five-object LADDER tasks by October 2027?", "slug": "ladder-five-object-robot-2027", "url": "/milestones/ladder-five-object-robot-2027/", "topic": "AI & Robotics", "deadline": "2027-10-27", "status": "research-draft", "probability": null, "scorable": false, "prelockBlocker": "Freeze exact five-object subset, trial counts, evaluation protocol and result archival before locking.", "evidenceRuleYes": "A benchmark-owner or independent evaluator publishes 50% or higher end-to-end real-robot success on a pre-registered identical five-object task subset.", "evidenceRuleNo": "A complete dated archive of the agreed task split shows less than 50% at deadline.", "primarySources": [ "https://insait.ai/ladder-a-new-benchmark-for-evaluating-ai-on-complex-robot-tasks/", "https://ladderrobotics.ai/" ] }, { "id": "CM-003", "question": "Will the European Commission impose an Article 101 GPAI fine by October 2027?", "slug": "first-eu-gpai-article-101-fine-2027", "url": "/milestones/first-eu-gpai-article-101-fine-2027/", "topic": "AI & Governance", "deadline": "2027-10-27", "status": "research-draft", "probability": null, "scorable": false, "prelockBlocker": "Independently check baseline for earlier decisions and decide how to handle adoption versus publication timing.", "evidenceRuleYes": "The Commission formally adopts an Article 101 fine between 27 October 2026 and 27 October 2027 inclusive, evidenced by an official decision or register.", "evidenceRuleNo": "No qualifying decision after review of the official legal decisions record and publication delays.", "primarySources": [ "https://ai-act-service-desk.ec.europa.eu/en/ai-act/article-101", "https://digital-strategy.ec.europa.eu/en/policies/enforcement-ai-act" ] }, { "id": "CM-004", "question": "Will paid, driverless Waymo rides launch in Munich by October 2027?", "slug": "waymo-munich-paid-driverless-rides-2027", "url": "/milestones/waymo-munich-paid-driverless-rides-2027/", "topic": "AI & Robotics", "deadline": "2027-10-27", "status": "research-draft", "probability": null, "scorable": false, "prelockBlocker": "Freeze definition of Munich service area and evidence standard for paid publicly available service.", "evidenceRuleYes": "Waymo or the responsible regulator confirms that members of the public can book and pay for a Munich passenger ride with no in-vehicle safety driver by deadline.", "evidenceRuleNo": "No such service in Munich before deadline after operator and regulator records are checked.", "primarySources": [ "https://waymo-prod.appspot.com/blog/2026/08/waymo-in-munich/", "https://waymo.com/blog/2025/12/2025-year-in-review/" ] }, { "id": "CM-005", "question": "Will verified AI inference performance per watt double by October 2027?", "slug": "mlperf-inference-efficiency-double-2027", "url": "/milestones/mlperf-inference-efficiency-double-2027/", "topic": "AI Chips & Compute", "deadline": "2027-10-27", "status": "research-draft", "probability": null, "scorable": false, "prelockBlocker": "Critical: freeze 2026 baseline, comparable power normalization, model/tokenizer, quality tier, latency and reviewer-approved rules.", "evidenceRuleYes": "MLCommons verifies an Available, Standardized GPT-OSS-120B system with at least twice the pre-registered 2026 reference output tokens per watt at matching latency and quality.", "evidenceRuleNo": "Official comparable results remain below the locked 2x threshold at cutoff.", "primarySources": [ "https://mlcommons.org/benchmarks/endpoints/", "https://docs.mlcommons.org/endpoints-submission-docs/understand/what-is-mlperf-endpoints/" ] } ], "qualityRule": "No new probability and no Brier score without prospective independently verifiable lock, stable event definition, named resolution evidence, independent adjudication, documented time and public append-only version. Editorial candidate audits are not external certification.", "auditNotes": [ "The original review of F-001/F-002 is an as-of 22 October checklist: passed gates have not been independently re-certified by this new summary.", "This dated record is an editorial status crosswalk between public existing forecast registry and milestone candidates. It does not constitute a new forecast vintage or resolution result.", "On 27 October, Scale Labs official documentation disclosed public/private SWE-bench Pro V2 differences and a changing private task denominator across materials. Freeze a specific private set, pass@1 protocol and archived result source before giving CM-001 any probability.", "LADDER is a real-robot benchmark introduced by INSAIT on 26 October, but a future binary lock needs a precise five-object trial protocol and denominator.", "An Article 101 fine requires a formally adopted European Commission decision; proposals, warnings, and requests for information do not count.", "Commercial paid driverless ride definition and a stable MLPerf power / latency baseline remain unapproved.", "The existing Evidence Pulse 2.0 client-side mapping surfaces topic links but does not independently validate the direction, novelty or strength of scientific evidence." ], "methodology": "/forecast/protocol/", "statusPage": "/forecast/results/", "milestoneHub": "/milestones/", "previousVersions": "/forecast/history/", "scope": "Audited 27 October 2026 against two existing public dataset registries; future changes require new dated audit record, not overwrite." }