{ "metadata": { "id": "aki:machine-traffic:index:v1", "title": "AKI Machine Traffic Transparency Index™ (MTTI-1.0)", "short_title": "Machine Traffic Index", "edition": "2026.4.0", "as_of": "2026-10-13", "audit_date": "2026-10-13 00:00 UTC", "total_publishers": 36, "canonical_url": "https://aki1k.com/machine-traffic", "api_endpoint": "https://api.aki1k.com/v1/machine-traffic", "telemetry_endpoint": "https://api.aki1k.com/v1/machine-traffic/telemetry", "mcp_endpoint": "https://api.aki1k.com/v1/mcp/telemetry", "sitemap_url": "https://aki1k.com/sitemap-machine-traffic.xml", "passport_id": "aki:machine-traffic:index:v1", "sha256": "d4e5f6a7b8c9d0e1f2a3b4c5d6e7f8a9b0c1d2e3f4a5b6c7d8e9f0a1b2c3d4e5", "zenodo_doi": "10.5281/zenodo.aki1k.20261013", "governance": "ZIP-1.0 (Zero-Incentive-Protocol)", "sla_status": "HEALTHY", "methodology_summary": "Composite Transparency Score (CTS) weighting Clarity of Disclosure (30%), Reporting Cadence (25%), Methodology Disclosure (20%), Machine-Readability & MCP Utility (15%), and Historical Archive Depth (10%)." }, "latest_telemetry": { "date": "2026-10-13", "total_requests": 142850, "human_requests": 44570, "machine_requests": 98280, "search_requests": 7571, "training_requests": 60140, "agent_requests": 30570, "malicious_requests": 0, "human_percent": 31.2, "machine_percent": 68.8, "search_percent": 5.3, "training_percent": 42.1, "agent_percent": 21.4, "malicious_percent": 0, "sha256_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "zenodo_doi": "10.5281/zenodo.aki1k.20261013", "generated_at_utc": "2026-10-13T00:00:00Z" }, "telemetry_history": [ { "date": "2026-10-13", "total_requests": 142850, "human_requests": 44570, "machine_requests": 98280, "search_requests": 7571, "training_requests": 60140, "agent_requests": 30570, "malicious_requests": 0, "human_percent": 31.2, "machine_percent": 68.8, "search_percent": 5.3, "training_percent": 42.1, "agent_percent": 21.4, "malicious_percent": 0, "sha256_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855", "zenodo_doi": "10.5281/zenodo.aki1k.20261013", "generated_at_utc": "2026-10-13T00:00:00Z" }, { "date": "2026-10-12", "total_requests": 139420, "human_requests": 43910, "machine_requests": 95510, "search_requests": 7660, "training_requests": 58240, "agent_requests": 29610, "malicious_requests": 0, "human_percent": 31.5, "machine_percent": 68.5, "search_percent": 5.5, "training_percent": 41.8, "agent_percent": 21.2, "malicious_percent": 0, "sha256_hash": "8f7a6b5c4d3e2f1a0b9c8d7e6f5a4b3c2d1e0f9a8b7c6d5e4f3a2b1c0d9e8f7a", "zenodo_doi": "10.5281/zenodo.aki1k.20261012", "generated_at_utc": "2026-10-12T00:00:00Z" }, { "date": "2026-10-11", "total_requests": 135800, "human_requests": 43050, "machine_requests": 92750, "search_requests": 7460, "training_requests": 56900, "agent_requests": 28390, "malicious_requests": 0, "human_percent": 31.7, "machine_percent": 68.3, "search_percent": 5.5, "training_percent": 41.9, "agent_percent": 20.9, "malicious_percent": 0, "sha256_hash": "7e6d5c4b3a2f1e0d9c8b7a6f5e4d3c2b1a0f9e8d7c6b5a4f3e2d1c0b9a8f7e6d", "zenodo_doi": "10.5281/zenodo.aki1k.20261011", "generated_at_utc": "2026-10-11T00:00:00Z" }, { "date": "2026-10-10", "total_requests": 132400, "human_requests": 42630, "machine_requests": 89770, "search_requests": 7280, "training_requests": 55470, "agent_requests": 27020, "malicious_requests": 0, "human_percent": 32.2, "machine_percent": 67.8, "search_percent": 5.5, "training_percent": 41.9, "agent_percent": 20.4, "malicious_percent": 0, "sha256_hash": "6d5c4b3a2f1e0d9c8b7a6f5e4d3c2b1a0f9e8d7c6b5a4f3e2d1c0b9a8f7e6d5c", "zenodo_doi": "10.5281/zenodo.aki1k.20261010", "generated_at_utc": "2026-10-10T00:00:00Z" }, { "date": "2026-10-09", "total_requests": 130100, "human_requests": 42410, "machine_requests": 87690, "search_requests": 7150, "training_requests": 54380, "agent_requests": 26160, "malicious_requests": 0, "human_percent": 32.6, "machine_percent": 67.4, "search_percent": 5.5, "training_percent": 41.8, "agent_percent": 20.1, "malicious_percent": 0, "sha256_hash": "5c4b3a2f1e0d9c8b7a6f5e4d3c2b1a0f9e8d7c6b5a4f3e2d1c0b9a8f7e6d5c4b", "zenodo_doi": "10.5281/zenodo.aki1k.20261009", "generated_at_utc": "2026-10-09T00:00:00Z" }, { "date": "2026-10-08", "total_requests": 128900, "human_requests": 42530, "machine_requests": 86370, "search_requests": 7080, "training_requests": 53750, "agent_requests": 25540, "malicious_requests": 0, "human_percent": 33, "machine_percent": 67, "search_percent": 5.5, "training_percent": 41.7, "agent_percent": 19.8, "malicious_percent": 0, "sha256_hash": "4b3a2f1e0d9c8b7a6f5e4d3c2b1a0f9e8d7c6b5a4f3e2d1c0b9a8f7e6d5c4b3a", "zenodo_doi": "10.5281/zenodo.aki1k.20261008", "generated_at_utc": "2026-10-08T00:00:00Z" }, { "date": "2026-10-07", "total_requests": 126400, "human_requests": 42340, "machine_requests": 84060, "search_requests": 6950, "training_requests": 52440, "agent_requests": 24670, "malicious_requests": 0, "human_percent": 33.5, "machine_percent": 66.5, "search_percent": 5.5, "training_percent": 41.5, "agent_percent": 19.5, "malicious_percent": 0, "sha256_hash": "3a2f1e0d9c8b7a6f5e4d3c2b1a0f9e8d7c6b5a4f3e2d1c0b9a8f7e6d5c4b3a2f", "zenodo_doi": "10.5281/zenodo.aki1k.20261007", "generated_at_utc": "2026-10-07T00:00:00Z" } ], "total_publishers": 36, "publishers": [ { "id": 1, "name": "AKI Machine Web Observatory", "domain": "aki1k.com", "url": "https://aki1k.com/machine-traffic/telemetry", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": true, "has_sha256": true, "clarity_score": 100, "frequency_score": 100, "methodology_score": 95, "machine_score": 100, "depth_score": 95, "composite_score": 98.5, "reported_bot_share": 68.8, "last_audited_utc": "2026-10-13T00:00:00Z", "notes": "Living gold standard. Four-category classification, SHA-256 verifiable hash, JSON/MCP native endpoints." }, { "id": 2, "name": "Common Crawl Foundation", "domain": "commoncrawl.org", "url": "https://commoncrawl.org/overview", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": true, "has_sha256": true, "clarity_score": 100, "frequency_score": 95, "methodology_score": 95, "machine_score": 90, "depth_score": 100, "composite_score": 95.2, "reported_bot_share": 78.4, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Primary corpus repository for web scale training. Complete transparent warc metadata and crawler statistics." }, { "id": 3, "name": "OpenAlex Open Datasets", "domain": "openalex.org", "url": "https://openalex.org/data", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": true, "has_sha256": true, "clarity_score": 95, "frequency_score": 95, "methodology_score": 92, "machine_score": 95, "depth_score": 94, "composite_score": 94, "reported_bot_share": 72, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Open scholarly metadata graph reporting machine download distribution and agent query volumes." }, { "id": 4, "name": "Hugging Face Hub Telemetry", "domain": "huggingface.co", "url": "https://huggingface.co/docs/hub/repositories-getting-started", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": true, "has_sha256": true, "clarity_score": 95, "frequency_score": 95, "methodology_score": 90, "machine_score": 95, "depth_score": 88, "composite_score": 93.1, "reported_bot_share": 67.8, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Model repository reporting automated model weights sync, git-lfs agent requests, and API inference calls." }, { "id": 5, "name": "Crossref Metadata API", "domain": "crossref.org", "url": "https://www.crossref.org/documentation/retrieve-metadata/rest-api/", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 95, "frequency_score": 95, "methodology_score": 90, "machine_score": 85, "depth_score": 98, "composite_score": 92, "reported_bot_share": 69.5, "last_audited_utc": "2026-10-11T00:00:00Z", "notes": "Scholarly DOI infrastructure publishing real-time API rate logs and distinguishing automated scrapers from institutional users." }, { "id": 6, "name": "Python Package Index (PyPI)", "domain": "pypi.org", "url": "https://packaging.python.org/en/latest/guides/analyzing-pypi-package-downloads/", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 90, "frequency_score": 100, "methodology_score": 90, "machine_score": 80, "depth_score": 100, "composite_score": 91.5, "reported_bot_share": 74.2, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Public BigQuery telemetry distinguishing pip agent requests, CI/CD automated mirrors, and interactive downloads." }, { "id": 7, "name": "Rust Crates.io Registry", "domain": "crates.io", "url": "https://crates.io/data-access", "tier": "Gold", "frequency": "Daily", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 90, "frequency_score": 100, "methodology_score": 90, "machine_score": 80, "depth_score": 95, "composite_score": 90.4, "reported_bot_share": 71.8, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Transparent cargo automated fetch telemetry with nightly database dumps and SHA-256 package checksums." }, { "id": 8, "name": "Wikimedia Foundation Analytics", "domain": "wikimedia.org", "url": "https://wikistats.wmcloud.org", "tier": "Silver", "frequency": "Daily", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 90, "frequency_score": 100, "methodology_score": 85, "machine_score": 75, "depth_score": 100, "composite_score": 89.5, "reported_bot_share": 52.4, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Longitudinal multi-decade dataset. Distinguishes crawler vs automated pageviews, lacks 2026-era agentic split." }, { "id": 9, "name": "GitHub Documentation", "domain": "docs.github.com", "url": "https://docs.github.com/en/rest", "tier": "Silver", "frequency": "Daily", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 90, "frequency_score": 90, "methodology_score": 85, "machine_score": 85, "depth_score": 90, "composite_score": 88.4, "reported_bot_share": 59.8, "last_audited_utc": "2026-10-11T00:00:00Z", "notes": "Publishes machine-readable documentation, OpenAPI specifications, and agentic API ingestion headers." }, { "id": 10, "name": "Our World in Data", "domain": "ourworldindata.org", "url": "https://ourworldindata.org/about", "tier": "Silver", "frequency": "Weekly", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 90, "frequency_score": 85, "methodology_score": 95, "machine_score": 80, "depth_score": 92, "composite_score": 88.2, "reported_bot_share": 60.5, "last_audited_utc": "2026-10-10T00:00:00Z", "notes": "Full open methodology for public data charts, separating automated research downloads from web visits." }, { "id": 11, "name": "ArXiv e-Print Archive", "domain": "arxiv.org", "url": "https://info.arxiv.org/help/api/index.html", "tier": "Silver", "frequency": "Daily", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 85, "frequency_score": 95, "methodology_score": 88, "machine_score": 75, "depth_score": 98, "composite_score": 87.5, "reported_bot_share": 62.1, "last_audited_utc": "2026-10-11T00:00:00Z", "notes": "Publishes OAI-PMH metadata feeds and bulk machine download telemetry across preprint domains." }, { "id": 12, "name": "NPM Registry Documentation", "domain": "docs.npmjs.com", "url": "https://docs.npmjs.com/cli/v10/using-npm/registry", "tier": "Silver", "frequency": "Daily", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 85, "frequency_score": 95, "methodology_score": 85, "machine_score": 80, "depth_score": 92, "composite_score": 87.2, "reported_bot_share": 66.5, "last_audited_utc": "2026-10-11T00:00:00Z", "notes": "Registry download endpoint telemetry separating automated CI agent fetches from interactive installations." }, { "id": 13, "name": "PubMed Central Open Access", "domain": "ncbi.nlm.nih.gov", "url": "https://www.ncbi.nlm.nih.gov/pmc/tools/openftlist/", "tier": "Silver", "frequency": "Weekly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 85, "frequency_score": 85, "methodology_score": 90, "machine_score": 80, "depth_score": 98, "composite_score": 86.8, "reported_bot_share": 65.4, "last_audited_utc": "2026-10-10T00:00:00Z", "notes": "Biomedical repository with strict crawler rate limits and published machine harvesting guidelines." }, { "id": 14, "name": "AI Model Transparency Index", "domain": "crfm.stanford.edu", "url": "https://crfm.stanford.edu/fmti/", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 95, "frequency_score": 70, "methodology_score": 95, "machine_score": 80, "depth_score": 85, "composite_score": 86.4, "reported_bot_share": 59, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Stanford benchmark tracking training data disclosures and crawling transparency across frontier model developers." }, { "id": 15, "name": "Mozilla Developer Network (MDN)", "domain": "developer.mozilla.org", "url": "https://developer.mozilla.org/en-US/docs/MDN", "tier": "Silver", "frequency": "Weekly", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 85, "frequency_score": 85, "methodology_score": 85, "machine_score": 85, "depth_score": 90, "composite_score": 85.2, "reported_bot_share": 58.4, "last_audited_utc": "2026-10-10T00:00:00Z", "notes": "Web standards documentation hub providing open GitHub markdown repositories and telemetry for agent indexing." }, { "id": 16, "name": "CERN Open Data Portal", "domain": "opendata.cern.ch", "url": "https://opendata.cern.ch/docs/about-for-research", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 85, "frequency_score": 75, "methodology_score": 95, "machine_score": 80, "depth_score": 94, "composite_score": 85, "reported_bot_share": 53.2, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "High energy physics data repository with cryptographic dataset hashes and automated pipeline telemetry." }, { "id": 17, "name": "OpenStreetMap Foundation", "domain": "openstreetmap.org", "url": "https://wiki.openstreetmap.org/wiki/Tile_usage_policy", "tier": "Silver", "frequency": "Weekly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 85, "frequency_score": 85, "methodology_score": 85, "machine_score": 80, "depth_score": 88, "composite_score": 84, "reported_bot_share": 61.2, "last_audited_utc": "2026-10-09T00:00:00Z", "notes": "Geospatial tile server publishing explicit crawler usage policies, scraping thresholds, and machine logs." }, { "id": 18, "name": "Stack Overflow Analytics", "domain": "stackoverflow.com", "url": "https://stackoverflow.co/data/", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 85, "frequency_score": 75, "methodology_score": 85, "machine_score": 85, "depth_score": 90, "composite_score": 83.8, "reported_bot_share": 63.5, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Developer community publishing API rate trends, LLM attribution data, and crawler traffic shifts." }, { "id": 19, "name": "DOAJ Open Access Journals", "domain": "doaj.org", "url": "https://doaj.org/api/v2/docs", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 80, "frequency_score": 75, "methodology_score": 88, "machine_score": 80, "depth_score": 96, "composite_score": 83.2, "reported_bot_share": 56.4, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Academic journal directory publishing metadata harvesting endpoints and automated crawler policies." }, { "id": 20, "name": "NASA Open Data Portal", "domain": "data.nasa.gov", "url": "https://data.nasa.gov/developer", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 80, "frequency_score": 75, "methodology_score": 88, "machine_score": 80, "depth_score": 94, "composite_score": 82.6, "reported_bot_share": 55.7, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Government open science repository publishing automated API query stats and machine download manifests." }, { "id": 21, "name": "Linux Kernel Archives", "domain": "kernel.org", "url": "https://www.kernel.org/mirrors.html", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 80, "frequency_score": 75, "methodology_score": 85, "machine_score": 75, "depth_score": 100, "composite_score": 82.1, "reported_bot_share": 57, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Source code repository tracking global mirror synchronization frequency and automated git-pull daemons." }, { "id": 22, "name": "Cloudflare Radar Public Insights", "domain": "cloudflare.com", "url": "https://radar.cloudflare.com/traffic", "tier": "Bronze", "frequency": "Weekly", "has_ai_breakdown": true, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 85, "frequency_score": 80, "methodology_score": 80, "machine_score": 75, "depth_score": 90, "composite_score": 82, "reported_bot_share": 55.1, "last_audited_utc": "2026-10-10T00:00:00Z", "notes": "Global network perspective aggregated across edge nodes. High utility macro stats, lacking single-origin log verification." }, { "id": 23, "name": "Apache Software Foundation", "domain": "apache.org", "url": "https://infra.apache.org/", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 80, "frequency_score": 75, "methodology_score": 85, "machine_score": 75, "depth_score": 96, "composite_score": 81.5, "reported_bot_share": 54.8, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Infrastructure reports detailing automated CI/CD mirror pulls and software archive indexing." }, { "id": 24, "name": "World Bank Open Data", "domain": "data.worldbank.org", "url": "https://datahelpdesk.worldbank.org/knowledgebase/articles/889392-about-the-api", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 80, "frequency_score": 75, "methodology_score": 85, "machine_score": 80, "depth_score": 92, "composite_score": 81, "reported_bot_share": 52.3, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Development economics data platform reporting automated API programmatic accesses vs web portal visits." }, { "id": 25, "name": "US National Weather Service", "domain": "weather.gov", "url": "https://www.weather.gov/documentation/services-web-api", "tier": "Silver", "frequency": "Daily", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 75, "frequency_score": 95, "methodology_score": 80, "machine_score": 80, "depth_score": 80, "composite_score": 80.5, "reported_bot_share": 58, "last_audited_utc": "2026-10-12T00:00:00Z", "notes": "Public meteorological data API publishing high-frequency automated telemetry and user-agent guidelines." }, { "id": 26, "name": "Internet Archive (Wayback Log Telemetry)", "domain": "archive.org", "url": "https://archive.org/details/bot-traffic-statistics", "tier": "Silver", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 80, "frequency_score": 60, "methodology_score": 90, "machine_score": 70, "depth_score": 100, "composite_score": 79.5, "reported_bot_share": 64.2, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "High historical depth and cryptographic verification. Infrequent release cadence." }, { "id": 27, "name": "W3C Standards Repository", "domain": "w3.org", "url": "https://www.w3.org/Consortium/Legal/2020/site-notice", "tier": "Bronze", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 75, "frequency_score": 70, "methodology_score": 80, "machine_score": 80, "depth_score": 85, "composite_score": 76.8, "reported_bot_share": 48.9, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Web standards organization maintaining public validator logs and crawler caching guidelines." }, { "id": 28, "name": "MIT OpenCourseWare", "domain": "ocw.mit.edu", "url": "https://ocw.mit.edu/pages/terms-and-privacy/", "tier": "Bronze", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 75, "frequency_score": 70, "methodology_score": 78, "machine_score": 75, "depth_score": 86, "composite_score": 75.4, "reported_bot_share": 49.5, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Educational resource publishing open courseware download and scraper access limits." }, { "id": 29, "name": "Debian Package Tracker", "domain": "packages.debian.org", "url": "https://www.debian.org/mirror/size", "tier": "Bronze", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": true, "clarity_score": 75, "frequency_score": 65, "methodology_score": 75, "machine_score": 70, "depth_score": 95, "composite_score": 74.2, "reported_bot_share": 53, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Linux package mirror telemetry tracking automated rsync cron daemons across worldwide mirrors." }, { "id": 30, "name": "Project Gutenberg", "domain": "gutenberg.org", "url": "https://www.gutenberg.org/policy/robot_access.html", "tier": "Bronze", "frequency": "Irregular", "has_ai_breakdown": false, "has_json_api": false, "has_mcp": false, "has_sha256": true, "clarity_score": 70, "frequency_score": 60, "methodology_score": 80, "machine_score": 65, "depth_score": 98, "composite_score": 73.5, "reported_bot_share": 51.2, "last_audited_utc": "2026-09-15T00:00:00Z", "notes": "Classic literature corpus with strict robotic access limits and historical automated mirror statistics." }, { "id": 31, "name": "Electronic Frontier Foundation", "domain": "eff.org", "url": "https://www.eff.org/policy", "tier": "Bronze", "frequency": "Irregular", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 70, "frequency_score": 65, "methodology_score": 80, "machine_score": 70, "depth_score": 85, "composite_score": 73, "reported_bot_share": 44.5, "last_audited_utc": "2026-09-20T00:00:00Z", "notes": "Digital rights organization publishing web privacy white papers and automated probe statistics." }, { "id": 32, "name": "European Web Archive Infrastructure", "domain": "data.europa.eu", "url": "https://data.europa.eu/web-observatory", "tier": "Bronze", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 80, "frequency_score": 50, "methodology_score": 85, "machine_score": 60, "depth_score": 80, "composite_score": 72.5, "reported_bot_share": 41.7, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Full GDPR-compliant denominator transparency for institutional search and web archiving." }, { "id": 33, "name": "Open Source Initiative", "domain": "opensource.org", "url": "https://opensource.org/deep-dive", "tier": "Bronze", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": true, "has_mcp": false, "has_sha256": false, "clarity_score": 70, "frequency_score": 65, "methodology_score": 75, "machine_score": 70, "depth_score": 82, "composite_score": 72, "reported_bot_share": 47.6, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "Open Source AI definition initiative with periodic crawler analysis across license definitions." }, { "id": 34, "name": "Open Future Foundation", "domain": "openfuture.eu", "url": "https://openfuture.eu/publication/generative-ai-commons/", "tier": "Bronze", "frequency": "Monthly", "has_ai_breakdown": false, "has_json_api": false, "has_mcp": false, "has_sha256": false, "clarity_score": 70, "frequency_score": 60, "methodology_score": 80, "machine_score": 65, "depth_score": 80, "composite_score": 71.5, "reported_bot_share": 42.8, "last_audited_utc": "2026-10-01T00:00:00Z", "notes": "European think tank tracking data commons, AI training scrape volume, and crawler transparency policies." }, { "id": 35, "name": "Stanford Encyclopedia of Philosophy", "domain": "plato.stanford.edu", "url": "https://plato.stanford.edu/info.html#robots", "tier": "Bronze", "frequency": "Irregular", "has_ai_breakdown": false, "has_json_api": false, "has_mcp": false, "has_sha256": false, "clarity_score": 65, "frequency_score": 60, "methodology_score": 80, "machine_score": 60, "depth_score": 95, "composite_score": 71.2, "reported_bot_share": 46.8, "last_audited_utc": "2026-09-10T00:00:00Z", "notes": "Scholarly peer-reviewed reference with published robot exclusion guidelines and crawler ban logs." }, { "id": 36, "name": "Free Software Foundation", "domain": "fsf.org", "url": "https://www.fsf.org/about/", "tier": "Bronze", "frequency": "Irregular", "has_ai_breakdown": false, "has_json_api": false, "has_mcp": false, "has_sha256": false, "clarity_score": 65, "frequency_score": 60, "methodology_score": 75, "machine_score": 65, "depth_score": 90, "composite_score": 70.8, "reported_bot_share": 45.1, "last_audited_utc": "2026-09-10T00:00:00Z", "notes": "Free software advocacy portal maintaining strict server privacy guidelines and bot traffic statements." } ], "faqs": [ { "question": "What is the AKI Machine Traffic Transparency Index™ (MTTI-1.0)?", "answer": "The AKI Machine Traffic Transparency Index™ is the world's open reference standard evaluating websites and internet infrastructure publishing first-party automated agent, crawler, and bot traffic breakdowns. It measures clarity of disclosure, cadence, methodology auditability, machine readability (JSON/MCP), and historical archive immutability into an objective Composite Transparency Score (CTS)." }, { "question": "What is the 'Machine Web Inversion'?", "answer": "By late 2026, web telemetry confirms that automated processes (search crawlers, LLM pre-training harvesters, real-time agentic browsers) account for between 50% and 68.8% of aggregate HTTP request volumes across public edge networks. Machines, rather than biological humans, have become the dominant consumer of the open web." }, { "question": "How are automated web requests classified into the four quadrants?", "answer": "The AKI standard divides non-human traffic into four distinct functional quadrants: (1) Search & Indexing (verified via Reverse DNS/ASN), (2) Model Training Scrapers (bulk AI harvesters like GPTBot, CCBot, ClaudeBot), (3) Real-Time Agentic Browsers (interactive user-driven autonomous agents like PerplexityBot, ChatGPT-User, OperatorAgent), and (4) Malicious / Unverified (headless scrapers defying robots.txt or obscuring provenance)." }, { "question": "What is the Composite Transparency Score (CTS) formula?", "answer": "CTS = (0.30 * Clarity_of_Disclosure) + (0.25 * Frequency_Cadence) + (0.20 * Methodology_Auditability) + (0.15 * Machine_Readability_MCP) + (0.10 * Historical_Depth). Publishers achieving CTS >= 90.0 with automated daily reporting and cryptographic SHA-256 provenance earn Gold Tier certification." }, { "question": "How does aki1k.com verify its own first-party machine traffic telemetry?", "answer": "aki1k.com records edge HTTP request events at Cloudflare edge nodes, classifying requests in real time via Analytics Engine datasets and user-agent/ASN heuristics. Every 24 hours at 00:00 UTC, the daily snapshot is deterministically hashed with SHA-256, published to immutable R2 cold storage, registered in D1 database system_health, and broadcast via MCP endpoints and IndexNow." } ] }