2026-09-28 18:25:31 +02:00
|
|
|
# Coulomb Research
|
2026-09-28 13:15:51 +00:00
|
|
|
|
2026-09-28 18:25:31 +02:00
|
|
|
A self-improving research network where humans and artificial intelligences
|
|
|
|
|
create, criticize, test, and reuse knowledge.
|
|
|
|
|
|
|
|
|
|
This repository is currently a documentation and research seed. Start with:
|
|
|
|
|
|
|
|
|
|
- [Intent](INTENT.md) — mission and constitutional principles.
|
|
|
|
|
- [Scope](SCOPE.md) — current state and implementation boundaries.
|
|
|
|
|
- [Design seed](seed/README.md) — kernel, publication interface, signals, and charts.
|
|
|
|
|
- [Milestone plan](seed/CoulombResearchMilestonePlan.md) — artifact-driven development.
|
|
|
|
|
- [Work records](WORK-RECORDS.md) — implementation tracking through State Hub.
|
|
|
|
|
- [Agent instructions](AGENTS.md) — repository workflow and sync commands.
|
2026-09-28 20:15:18 +02:00
|
|
|
- [Artifact convention](docs/ResearchArtifactConvention.md) — program/paper/
|
|
|
|
|
claim identifier and file-layout conventions.
|
|
|
|
|
- [Paper registry](research/registry/papers.yaml) — authoritative index of
|
|
|
|
|
registered papers, currently just `CR-000` (Paper Zero, RP-000).
|
2026-09-28 18:25:31 +02:00
|
|
|
|
Implement M2: claim/evidence discipline for CR-000 (CR-WP-0004)
Obtain CR-000's first independent criticism via a freshly spawned,
context-isolated agent instance with no prior authorship context
(CR-000-X003-X007 in criticism.md). It found two internal-consistency
violations self-criticism had missed: CR-000-C006's cited evidence was
circular (X003) and conflated manuscript assertion with a real Evidence
object (X004), so C006 is now contested and its evidence withdrawn. It
also flagged that self-criticism had concentrated on infrastructure while
leaving substantive claims unchallenged (X005), an unlabeled overreach in
the Abstract (X006, now fixed), and a provenance-field ambiguity (X007).
Add evidence.md's first two entries (CR-000-E001, CR-000-E002), both
explicitly assessed as weak and left conjectural rather than inflated to
supported. Add scripts/query_paper_graph.py, a minimal read-only script
answering claim/evidence/criticism relation queries without manual
grepping, as a partial response to CR-000-X001 (which remains open: it is
a query layer over flat files, not a real graph).
Revise manuscript.md (Abstract, SS11-14) and questions.md to reflect all of
the above; Q2 gets a provisional "mixed" answer.
Close CR-WP-0004 and hand off CR-WP-0005 (resolving remaining open
criticism, and obtaining organizationally- rather than only
procedurally-independent review) rather than starting M3, which this
workplan judges premature while CR-000 still has open internal-consistency
findings.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: sonnet
Assistant-Process: 228422@bnt-lap001
Assistant-Session: 49089735-86e1-4d29-8a6e-74c26947f8c4
2026-09-28 20:37:35 +02:00
|
|
|
M0 ([research facility skeleton](workplans/CR-WP-0002-research-facility-skeleton.md)),
|
|
|
|
|
M1 ([Paper Zero v0.1 manuscript](workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md)),
|
|
|
|
|
and a first pass of M2 ([claim/evidence discipline](workplans/CR-WP-0004-claim-evidence-discipline.md))
|
Implement M1: CR-000 v0.1 manuscript (CR-WP-0003)
Replace all [MISSING] sections in manuscript.md with real content
(motivation/problem framing, design objective, kernel presentation,
cybernetic loops, human-AI participation, publication interoperability,
decentralization, signals, failure modes, initial experiments, open
questions, conclusion, abstract). Add three new claims (CR-000-C006-C008).
Add two self-criticism entries (CR-000-X001, CR-000-X002): the
implementation is itself document-centric Markdown rather than a queryable
graph, contradicting CR-000-C002/C003 (now marked contested); and all
criticism received so far is self-authored, weakening the evidentiary
basis for CR-000-C004. Both are carried forward as residuals.
Close CR-WP-0003 and hand off M2 (claim/evidence discipline, independent
criticism, and a response to the document-centrism criticism) as
CR-WP-0004, per the workplan's residual-handoff requirement.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: claude-sonnet-5-5
Assistant-Process: 228422@bnt-lap001
Assistant-Session: 49089735-86e1-4d29-8a6e-74c26947f8c4
2026-09-28 20:25:32 +02:00
|
|
|
are implemented. The next implementation is
|
Implement M2: claim/evidence discipline for CR-000 (CR-WP-0004)
Obtain CR-000's first independent criticism via a freshly spawned,
context-isolated agent instance with no prior authorship context
(CR-000-X003-X007 in criticism.md). It found two internal-consistency
violations self-criticism had missed: CR-000-C006's cited evidence was
circular (X003) and conflated manuscript assertion with a real Evidence
object (X004), so C006 is now contested and its evidence withdrawn. It
also flagged that self-criticism had concentrated on infrastructure while
leaving substantive claims unchallenged (X005), an unlabeled overreach in
the Abstract (X006, now fixed), and a provenance-field ambiguity (X007).
Add evidence.md's first two entries (CR-000-E001, CR-000-E002), both
explicitly assessed as weak and left conjectural rather than inflated to
supported. Add scripts/query_paper_graph.py, a minimal read-only script
answering claim/evidence/criticism relation queries without manual
grepping, as a partial response to CR-000-X001 (which remains open: it is
a query layer over flat files, not a real graph).
Revise manuscript.md (Abstract, SS11-14) and questions.md to reflect all of
the above; Q2 gets a provisional "mixed" answer.
Close CR-WP-0004 and hand off CR-WP-0005 (resolving remaining open
criticism, and obtaining organizationally- rather than only
procedurally-independent review) rather than starting M3, which this
workplan judges premature while CR-000 still has open internal-consistency
findings.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Assistant: claude-code
Assistant-Model: sonnet
Assistant-Process: 228422@bnt-lap001
Assistant-Session: 49089735-86e1-4d29-8a6e-74c26947f8c4
2026-09-28 20:37:35 +02:00
|
|
|
[resolving CR-000's outstanding criticism](workplans/CR-WP-0005-resolve-outstanding-criticism.md)
|
|
|
|
|
before M3 is judged ready.
|
2026-09-28 18:25:31 +02:00
|
|
|
There is no application to install, test, build, or run yet. For documentation
|
|
|
|
|
changes, run `git diff --check` and review links, YAML, and work-record structure.
|