{
  "schemaVersion": 1,
  "kind": "leviathan-editorial-claim-revision",
  "scope": "The claim and its cited source cards at capture. External papers and linked project pages are not frozen by this record. A digest identifies bytes, not truth or endorsement.",
  "claim": {
    "id": "C08",
    "title": "How can shared principles stay open to challenge?",
    "statement": "Written principles and public input can influence model behavior. Which principles are shared and deserve authority is a further question.",
    "kind": "Empirical and ethical question",
    "status": "Partial evidence; governance remains open",
    "summary": "A system that carries values must keep their meaning, application, and revision open to challenge. Leviathan proposes local meaning kernels for independent structures with their own concepts and histories. The question is whether those relationships support better decisions and cooperation while allowing people to contest both the values and the system carrying them.",
    "definitions": [
      {
        "term": "Principle",
        "meaning": "A stated reason or commitment intended to guide decisions."
      },
      {
        "term": "Legitimacy",
        "meaning": "The reasons a decision process deserves acceptance by the people and interests it affects."
      },
      {
        "term": "Public input",
        "meaning": "Contributions from participants whose selection, influence and exclusions can be examined."
      },
      {
        "term": "Local meaning kernel, in this proposal",
        "meaning": "Versioned relationships among a Levi or Leviathan’s concepts, principles, rules, and history. This proposed research structure differs from the existing constitutional kernel and current forum permissions."
      }
    ],
    "values": [
      "Give affected perspectives a meaningful place in deliberation.",
      "Keep minority objections visible.",
      "Make the passage from stated values to actual behavior inspectable."
    ],
    "reasoning": [
      "Principles can be part of a model’s training and can have measurable effects. Supplying a value context during use is a different intervention from training; results cannot simply be carried across.",
      "Selecting principles involves ethical and political judgments that performance measures alone cannot resolve. Independent groups may share observations while retaining different reasons for action.",
      "We propose keeping the versions and relationships that made a concept meaningful at a decision point. Revising that concept should make dependent decisions available for reconsideration while preserving their original context.",
      "People could explore the idea with their own assistants and share selected questions or objections. Meaningful participation needs visible influence, representation, disagreement, and revision procedures as well as tests of behavior.",
      "A public standard itself must be open to criticism. We should examine who can use the review venue, whose reasons receive a response, and what resources a participant needs to be heard."
    ],
    "limits": "One public-input experiment does not establish universal agreement or validate a whole governance system. The sources do not show that any community has adopted Leviathan's proposals.",
    "strongestObjection": "Those who choose participants, translate contributions, or operate the infrastructure may retain decisive authority. A detailed kernel can give conformity the appearance of legitimacy, and an agent may repeat its values while acting otherwise. Independent structures also need ways to handle incompatible commitments without silently imposing one interpretation.",
    "whatWouldChangeOurView": "Evidence that contributions are routinely distorted or dissent has no practical route would require changing the process. Transparent revisions, preserved objections and independently assessed behavioral effects would strengthen the case.",
    "nextQuestion": "Does a contextual, versioned value structure change behavior on unfamiliar cases compared with ordinary instructions? Separately, can participants recover how their contribution affected a rule, retain objections, and challenge who may authorize action? Record what changed, what did not, and why. Better performance alone cannot establish legitimate authority.",
    "evidence": [
      {
        "sourceId": "R-GOV-01",
        "relation": "supports-part",
        "reason": "Principle-based training changes evaluated model behavior."
      },
      {
        "sourceId": "R-GOV-02",
        "relation": "supports-part",
        "reason": "A limited public-input study connects participant contributions to model principles; it is not a test of governance as a whole."
      },
      {
        "sourceId": "R-GOV-04",
        "relation": "context",
        "reason": "This philosophical account asks who can criticize, by which public standards and with what response. It does not validate a training or governance mechanism."
      },
      {
        "sourceId": "R-AG-11",
        "relation": "supports-part",
        "reason": "VeriHarness finds that consensus across rollouts can hide shared errors while minority disagreements often hold the better answer, motivating an explicit consensus challenger alongside disagreement resolution (reviewed via indexed digest)."
      }
    ],
    "history": [
      {
        "date": "2026-09-30",
        "note": "Added evidence about principles and public input while keeping effectiveness, representation and legitimacy as separate questions."
      },
      {
        "date": "2026-10-02",
        "note": "Distinguished proposed local meaning kernels from the existing constitutional kernel and from principle-based model training. Connected contextual versions and selected assistant participation to separate tests of behavior and legitimacy. No constitutional rule, forum permission, or empirical support claim changed."
      },
      {
        "date": "2026-10-04",
        "note": "Reviewed selected primary-source sections proposed in the external assessment and added scoped connections, access limits and research questions. Interlat retains its existing source ID; its reviewed preprint is distinguished from the final conference text. No experiment was reproduced, claim status promoted or governance rule adopted."
      },
      {
        "date": "2026-10-21",
        "note": "Connected VeriHarness (R-AG-11, reviewed via DAIR.AI 2026 technical digest) on consensus errors and explicit consensus-challenging mechanisms. Technical verification findings remain distinct from ethical legitimacy and community governance."
      }
    ],
    "projectLinks": [
      {
        "label": "Local kernels and independent structures",
        "href": "/what-is"
      },
      {
        "label": "Open conversations",
        "href": "/conversations"
      },
      {
        "label": "Explore and contribute with your assistant",
        "href": "/participate"
      }
    ]
  },
  "sources": [
    {
      "id": "R-GOV-01",
      "title": "Constitutional AI: Harmlessness from AI Feedback",
      "url": "https://arxiv.org/abs/2212.08073",
      "authors": "Yuntao Bai and co-authors; Anthropic",
      "publishedAt": "2022-12-15",
      "version": "arXiv paper and original research announcement",
      "type": "Preprint",
      "reviewLevel": "Abstract and author summary",
      "finding": "Written principles guide self-critique, revision and training with AI feedback, changing evaluated helpfulness and harmlessness behavior.",
      "limitations": "The choice of principles and evaluations embeds human judgments. The method does not establish universal ethics or the legitimacy of decentralized governance.",
      "changes": "The effects of a principle on behavior can be measured; choosing which principles deserve authority requires a further ethical argument.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback"
      ]
    },
    {
      "id": "R-GOV-02",
      "title": "Collective Constitutional AI: Aligning a Language Model with Public Input",
      "url": "https://www.anthropic.com/research/collective-constitutional-ai-aligning-a-language-model-with-public-input",
      "authors": "Anthropic and the Collective Intelligence Project",
      "publishedAt": "2023-10-17",
      "version": "Research announcement: 17 October 2023",
      "type": "Research report",
      "reviewLevel": "Selected sections",
      "finding": "Input from roughly one thousand US participants is translated into model principles and used to compare two models. Some measured bias outcomes differ.",
      "limitations": "The sample, editorial choices and single study cannot represent every community. The work does not directly test federated governance or lasting legitimacy.",
      "changes": "The findings concern one public-input process and its effects. Broader claims about legitimate shared governance require further evidence.",
      "checkedAt": "2026-09-30",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": []
    },
    {
      "id": "R-GOV-04",
      "title": "Subjects, Power, and Knowledge: Description and Prescription in Feminist Philosophies of Science",
      "url": "https://thehangedman.com/teaching-files/gender/longino.pdf",
      "authors": "Helen E. Longino",
      "publishedAt": "1993",
      "version": "Chapter 5 in Feminist Epistemologies, edited by Linda Alcoff and Elizabeth Potter, Routledge, first edition, 1993, pp. 101–120",
      "type": "Philosophical book chapter",
      "reviewLevel": "Selected sections",
      "finding": "Longino argues that knowledge depends on critical interaction among differently situated participants. She proposes public places for criticism, responsiveness to criticism, public evaluative standards and equality of intellectual authority. Plural communities can refine, reject and share models without universal consensus; empirical adequacy and reasoned criticism still constrain acceptable claims.",
      "limitations": "These are normative epistemological arguments, not experimental evidence that an organizational design works. Longino describes the criteria as prescriptions rather than satisfied descriptions. Inclusion faces unequal resources and power; she offers no simple formula for distinguishing marginalized criticism from claims that fail public standards.",
      "changes": "Read the 1993 chapter in a teaching-copy PDF, especially sections III–V. Publisher metadata identifies the edition; publisher-hosted full text was unavailable. Cited works were not separately checked.",
      "checkedAt": "2026-10-04",
      "verificationStatus": "Primary source reviewed",
      "relatedUrls": [
        "https://www.routledge.com/Feminist-Epistemologies/Alcoff-Potter/p/book/9780415904513"
      ]
    },
    {
      "id": "R-AG-11",
      "title": "VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks",
      "url": "https://academy.dair.ai/papers/veriharness-scaling-agentic-verification-for-long-horizon-tasks-2610.00972",
      "authors": "Google researchers (as indexed by DAIR.AI)",
      "publishedAt": "2026-10",
      "version": "arXiv:2610.00972; indexed in DAIR.AI Papers of the Week (Sep 28–Oct 4, 2026)",
      "type": "Preprint",
      "reviewLevel": "Indexed technical digest (DAIR.AI Papers of the Week 2026)",
      "finding": "Across parallel long-horizon agent rollouts, consensus agreement can mask shared systematic errors, whereas disagreement often contains the correct alternative. VeriHarness combines a disagreement resolver with an explicit consensus challenger that searches for failure modes even when candidate outputs agree.",
      "limitations": "Reviewed via the curated DAIR.AI technical summary; primary benchmark runs were not reproduced. Verification gains on bounded coding, math, and web tasks do not establish ethical legitimacy or prove that a challenge mechanism prevents all shared blind spots.",
      "changes": "Supports separating agreement from correctness and motivates explicit consensus-challenging procedures in multi-agent and plural review workflows.",
      "checkedAt": "2026-10-21",
      "verificationStatus": "Indexed technical summary reviewed (DAIR.AI 2026); primary full text and experiments not independently reproduced",
      "relatedUrls": [
        "https://github.com/dair-ai/AI-Papers-of-the-Week/blob/main/years/2026.md"
      ]
    }
  ]
}
