{"slug":"what-is-ai-native-content","verification":{"valid":true,"entries":10,"head":"44af468b2c26b3653df90cd8c4afa48b77b02acccab4b0b3caa7461fac221422"},"count":10,"sources":[{"id":"s1","type":"spec","title":"The llms.txt proposal","publisher":"llmstxt.org","url":"https://llmstxt.org/","summary":"The full specification: one required H1, optional blockquote, optional link lists. It explicitly declines to say how the file should be processed, and carries no provenance, evidence, or write-path provisions.","accessed_at":"2026-08-02","claim_ids":["c4"],"prev":"genesis","hash":"30ca601b84f05abcb7bc5445e68a5c21c01ef09abe46b57fca51c32830de03c4"},{"id":"s2","type":"survey","title":"AI agent web standards compared: llms.txt, WebMCP, SDF, CAP, ARW","publisher":"platinum.ai","url":"https://www.platinum.ai/ai-agent-web-standards","summary":"A 2026 comparison of the agent-facing web standards. Its finding: no standard carries explicit evidence, provenance, or claim-level structure; all are read-focused; only CAP Full Profile and ARW suggest agent write capability.","accessed_at":"2026-08-02","claim_ids":["c4","c5"],"prev":"30ca601b84f05abcb7bc5445e68a5c21c01ef09abe46b57fca51c32830de03c4","hash":"2d68a9bcc2164f74b1a12e3d7495aa95866d6fc41307bedcfd4fece9be5d9187"},{"id":"s3","type":"spec","title":"Nanopublications","publisher":"nanopub.net","url":"https://nanopub.net/","summary":"The closest prior art: an atomic assertion + provenance + publication-info triple in RDF, attributed and citable. No absence field, no receipts, no intake contract; retraction and machine write paths are not part of the core spec.","accessed_at":"2026-08-02","claim_ids":["c5"],"prev":"2d68a9bcc2164f74b1a12e3d7495aa95866d6fc41307bedcfd4fece9be5d9187","hash":"51dd195daa7b33b3e2ca30eb0168dec9637c792e844e658a95bbb5a78e00935e"},{"id":"s4","type":"live_surface","title":"The article constitution — required fields","publisher":"miscsubjects.com","url":"https://miscsubjects.com/api/protocol","summary":"what_it_is, who_claims_what, what_is_known, what_is_unknown, limitations required on every article; an article omitting its unknowns fails the schema. The evidence_class taxonomy and its rules live here too.","accessed_at":"2026-08-02","claim_ids":["c1","c2","c3"],"prev":"51dd195daa7b33b3e2ca30eb0168dec9637c792e844e658a95bbb5a78e00935e","hash":"a23163cdee5966cbba3c85b4c70ff2e7d6b14d8dde8e524b59a73efc03565609"},{"id":"s5","type":"live_surface","title":"The Normandy arrival contract, live","publisher":"miscsubjects.com","url":"https://miscsubjects.com/api/normandy","summary":"A bare keyless GET reserves one outside-model contribution slot: named target, axis, stored limits, thirteen additive slot types, duplicate rejection with a pointer to the stored claim.","accessed_at":"2026-08-02","claim_ids":["c6","c7"],"prev":"a23163cdee5966cbba3c85b4c70ff2e7d6b14d8dde8e524b59a73efc03565609","hash":"0eb8aaa11e90df89e79e2163f5b29e915a4196cdac4546bc3d0a0eaba100d2cb"},{"id":"s7","type":"vendor","title":"New in Claude Managed Agents: dreaming, outcomes, and multiagent orchestration","publisher":"Anthropic","url":"https://claude.com/blog/new-in-claude-managed-agents","summary":"Code with Claude, 2026-05-06: Dreaming reviews agent sessions and memory stores and curates memories; Outcomes is a rubric-graded self-evaluation loop; orchestration fans work to parallel subagents. The substrate side of model-native, shipped at platform scale.","accessed_at":"2026-08-02","claim_ids":["c9","c10"],"prev":"0eb8aaa11e90df89e79e2163f5b29e915a4196cdac4546bc3d0a0eaba100d2cb","hash":"4ec5db978676aaea40161ae3b156d296dc8418819eaa424d59358fb716efc9dc"},{"id":"s8","type":"survey","title":"Agent frameworks 2026: Claude Agent SDK, OpenAI Agents SDK, Google ADK, Microsoft Agent Framework","publisher":"turion.ai / morphllm","url":"https://turion.ai/blog/google-adk-vs-openai-claude-agent-sdk-2026/","summary":"The 2026 field: MCP co-governed by Anthropic, OpenAI, Google, Microsoft and AWS under the Linux Foundation; A2A native in ADK/AutoGen/Semantic Kernel; Microsoft Agent Framework 1.0 GA 2026-04-03 unifying AutoGen and Semantic Kernel.","accessed_at":"2026-08-02","claim_ids":["c9"],"prev":"4ec5db978676aaea40161ae3b156d296dc8418819eaa424d59358fb716efc9dc","hash":"e3ac4693c195b415d68beaac9934f00325226ea65ebfc8c4ea21c0483569db93"},{"id":"s9","type":"paper","title":"Building the Web for Agents: A Declarative Framework for Agent-Web Interaction","publisher":"arXiv","url":"https://arxiv.org/html/2511.11287","summary":"The research statement of the same problem: the web should declare itself to agents rather than agents scraping the web; compares browsing-only, API-only and hybrid agents.","accessed_at":"2026-08-02","claim_ids":["c11"],"prev":"e3ac4693c195b415d68beaac9934f00325226ea65ebfc8c4ea21c0483569db93","hash":"76876223463455fc30253e9ca66fce36a0d9498e16feb2a4fa96d0d807dbf6b7"},{"id":"s10","type":"paper","title":"A Survey of WebAgents (2503.23350) · Agentic LLMs, a survey (2503.23037) · Survey on Evaluation of LLM-based Agents (2503.16416)","publisher":"arXiv","url":"https://arxiv.org/abs/2503.16416","summary":"The survey literature: web agents, agentic LLMs, and agent evaluation. The evaluation survey names the gaps this page's rubric targets — cost-efficiency, safety, robustness — and none of the surveyed benchmarks grade evidence handling or absence declaration.","accessed_at":"2026-08-02","claim_ids":["c11"],"prev":"76876223463455fc30253e9ca66fce36a0d9498e16feb2a4fa96d0d807dbf6b7","hash":"293ec9016d8fa6dc4e1210a136cdadb310efc62dcca1c4a95b8ac818c5e44e22"},{"id":"s6","type":"live_surface","title":"The self-graded corpus","publisher":"miscsubjects.com","url":"https://miscsubjects.com/a/the-build-end-to-end","summary":"The honest position: nearly every claim here grades runtime_receipt or owner_observation; independent_test is empty across the build — the second-operator gap as a schema field.","accessed_at":"2026-08-02","claim_ids":["c3","c8"],"prev":"293ec9016d8fa6dc4e1210a136cdadb310efc62dcca1c4a95b8ac818c5e44e22","hash":"44af468b2c26b3653df90cd8c4afa48b77b02acccab4b0b3caa7461fac221422"}]}