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
This commit is contained in:
parent
84da0294c6
commit
76bcd020a4
9 changed files with 653 additions and 88 deletions
|
|
@ -17,7 +17,8 @@ This repository is currently a documentation and research seed. Start with:
|
|||
registered papers, currently just `CR-000` (Paper Zero, RP-000).
|
||||
|
||||
M0 ([research facility skeleton](workplans/CR-WP-0002-research-facility-skeleton.md))
|
||||
is implemented. The next implementation is
|
||||
[M1: Paper Zero v0.1 manuscript](workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md).
|
||||
and M1 ([Paper Zero v0.1 manuscript](workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md))
|
||||
are implemented. The next implementation is
|
||||
[M2: claim/evidence discipline](workplans/CR-WP-0004-claim-evidence-discipline.md).
|
||||
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.
|
||||
|
|
|
|||
12
SCOPE.md
12
SCOPE.md
|
|
@ -33,8 +33,12 @@ establish scientific validity or publication readiness.
|
|||
|
||||
## Next Work
|
||||
|
||||
M0 is implemented (`workplans/CR-WP-0002-research-facility-skeleton.md`,
|
||||
finished): the artifact convention, `RP-000`/`CR-000` skeleton, and paper
|
||||
registry exist. `workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md` owns M1
|
||||
(bringing CR-000 to a coherent v0.1 manuscript). The bootstrap workplan is
|
||||
M0 and M1 are implemented (`workplans/CR-WP-0002-research-facility-skeleton.md`,
|
||||
`workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md`, both finished): the
|
||||
artifact convention, `RP-000`/`CR-000` skeleton, paper registry, and a
|
||||
coherent CR-000 v0.1 manuscript exist. `CR-WP-0003`'s own self-criticism
|
||||
found the implementation still document-centric and only self-criticized
|
||||
(`CR-000-X001`, `CR-000-X002`); `workplans/CR-WP-0004-claim-evidence-discipline.md`
|
||||
owns M2 (independent criticism, real evidence linkage, and a response to
|
||||
the document-centrism criticism). The bootstrap workplan is
|
||||
`workplans/CR-WP-0001-statehub-bootstrap.md`.
|
||||
|
|
|
|||
|
|
@ -2,12 +2,9 @@
|
|||
|
||||
Paper-local claims for `CR-000`, addressable as `CR-000-C<NNN>`. See
|
||||
`docs/ResearchArtifactConvention.md` §1.1 for the ID convention and §4 for
|
||||
provenance requirements. Each claim below is transcribed from the M2
|
||||
example list in `seed/CoulombResearchMilestonePlan.md` — restated here as
|
||||
this paper's own claims, not yet linked to evidence or criticism (that
|
||||
linkage is M2's exit criterion, not M0's).
|
||||
provenance requirements.
|
||||
|
||||
Each entry: claim text, state, provenance, and links (currently empty).
|
||||
Each entry: claim text, state, provenance, and links.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -18,28 +15,36 @@ Each entry: claim text, state, provenance, and links (currently empty).
|
|||
|
||||
- **State:** conjectural
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-28
|
||||
- **Discussed in:** `manuscript.md` §7
|
||||
- **Evidence for/against:** none yet
|
||||
- **Criticism:** none yet
|
||||
- **Criticism:** none directly; `CR-000-X002` bears on the general standard
|
||||
of evidence this claim is held to.
|
||||
|
||||
## CR-000-C002
|
||||
|
||||
> Papers need not remain the canonical internal representation of
|
||||
> scientific knowledge.
|
||||
|
||||
- **State:** conjectural
|
||||
- **State:** contested
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-28
|
||||
- **Discussed in:** `manuscript.md` §2.1, §8, §11
|
||||
- **Evidence for/against:** none yet
|
||||
- **Criticism:** none yet
|
||||
- **Criticism:** `CR-000-X001` — the M0/M1 implementation of CR-000 itself
|
||||
is flat Markdown documents with no queryable graph, in tension with this
|
||||
claim. Updated to `contested` on 2026-09-28 per `revision-log.md`.
|
||||
|
||||
## CR-000-C003
|
||||
|
||||
> A graph of propositions, evidence, actions, and provenance can support
|
||||
> richer scientific coordination than document-centric publication alone.
|
||||
|
||||
- **State:** conjectural
|
||||
- **State:** contested
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-28
|
||||
- **Discussed in:** `manuscript.md` §2.1, §11
|
||||
- **Evidence for/against:** none yet
|
||||
- **Criticism:** none yet
|
||||
- **Criticism:** `CR-000-X001` — same basis as `CR-000-C002`. No graph has
|
||||
been built; only ID-labeled prose files. Updated to `contested` on
|
||||
2026-09-28 per `revision-log.md`.
|
||||
|
||||
## CR-000-C004
|
||||
|
||||
|
|
@ -48,8 +53,13 @@ Each entry: claim text, state, provenance, and links (currently empty).
|
|||
|
||||
- **State:** conjectural
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-28
|
||||
- **Discussed in:** `manuscript.md` §11
|
||||
- **Evidence for/against:** none yet
|
||||
- **Criticism:** none yet
|
||||
- **Criticism:** `CR-000-X002` — the only criticism CR-000 has received so
|
||||
far is self-authored, which is a weak instance of this claim rather than
|
||||
evidence against it. Not marked `contested`, because the criticism
|
||||
concerns the strength of the evidence for the claim, not the claim's
|
||||
content.
|
||||
|
||||
## CR-000-C005
|
||||
|
||||
|
|
@ -58,13 +68,60 @@ Each entry: claim text, state, provenance, and links (currently empty).
|
|||
|
||||
- **State:** conjectural
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-28
|
||||
- **Discussed in:** `manuscript.md` §6
|
||||
- **Evidence for/against:** none yet
|
||||
- **Criticism:** none yet
|
||||
|
||||
## CR-000-C006
|
||||
|
||||
> Institutional functions should default to not existing in a given
|
||||
> implementation until a concrete research artifact demonstrates a
|
||||
> specific, load-bearing need for them.
|
||||
|
||||
- **State:** conjectural
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-29
|
||||
- **Discussed in:** `manuscript.md` §3.2
|
||||
- **Evidence for/against:** `manuscript.md` §3.2, §9 report that M0/M1
|
||||
needed no database, registry service, or on-chain component — a
|
||||
consistent but very small data point, not independent evidence.
|
||||
- **Criticism:** none yet
|
||||
|
||||
## CR-000-C007
|
||||
|
||||
> A publication adapter that treats papers as import/export containers
|
||||
> rather than the canonical internal representation allows interoperability
|
||||
> with conventional science without importing conventional science's
|
||||
> internal constraints.
|
||||
|
||||
- **State:** conjectural
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-29
|
||||
- **Discussed in:** `manuscript.md` §8
|
||||
- **Evidence for/against:** none yet — no P2/P3 adapter behavior has been
|
||||
exercised (CR-000 is P1 only).
|
||||
- **Criticism:** none yet
|
||||
|
||||
## CR-000-C008
|
||||
|
||||
> No single research signal or composite score should be treated as a
|
||||
> stand-in for epistemic support.
|
||||
|
||||
- **State:** conjectural
|
||||
- **Added by:** agent:claude-sonnet-5 — 2026-09-29
|
||||
- **Discussed in:** `manuscript.md` §10
|
||||
- **Evidence for/against:** none yet — CR-000 has no attention, influence,
|
||||
reuse, or generativity data (it has not circulated beyond this
|
||||
repository).
|
||||
- **Criticism:** none yet
|
||||
|
||||
---
|
||||
|
||||
No claim above is currently supported, contested, or superseded — all five
|
||||
are freshly transcribed conjectures with no linked evidence or criticism.
|
||||
Mapping them to evidence and criticism is explicitly M2 work
|
||||
(`seed/CoulombResearchMilestonePlan.md`, M2 exit criterion), not claimed
|
||||
here.
|
||||
Claim-state legend (per `docs/ResearchArtifactConvention.md` §4 and
|
||||
`seed/CoulombResearchKernel.md` §7): conjectural, active, contested,
|
||||
supported, contradicted, superseded, unresolved. `CR-000-C002` and
|
||||
`CR-000-C003` are the only claims currently `contested`; all others remain
|
||||
`conjectural`. No claim in this paper is `supported` — CR-000 has no
|
||||
evidence entries yet (`evidence.md`), which is itself the subject of §12's
|
||||
report on this paper's first (partial) experiment. Mapping claims to
|
||||
evidence with the discipline the M2 milestone requires
|
||||
(`seed/CoulombResearchMilestonePlan.md`, M2 exit criterion) remains
|
||||
unresolved work; see `manuscript.md` §13, Q2.
|
||||
|
|
|
|||
|
|
@ -3,15 +3,72 @@
|
|||
Paper-local criticism entries for `CR-000`, addressable as `CR-000-X<NNN>`.
|
||||
See `docs/ResearchArtifactConvention.md` §1.1 and §4.
|
||||
|
||||
No criticism has been received for this paper yet — it has not yet reached
|
||||
even collaborator review under P1 internal circulation. This file exists as
|
||||
the required artifact location (per
|
||||
`seed/CoulombResearchMilestonePlan.md` M0/M4) so that criticism has a place
|
||||
to go as soon as it is raised; it is intentionally empty rather than
|
||||
populated with anticipated or self-authored criticism standing in for real
|
||||
external criticism.
|
||||
Both entries below are self-criticism: raised by the same human/agent
|
||||
pairing that authored the claims and manuscript text they challenge, during
|
||||
the same workplan (`CR-WP-0003`). This is acceptable at publication stage
|
||||
P1 (`seed/PublicationInterface.md` §4), but is a materially weaker signal
|
||||
than independent criticism, and `CR-000-X002` says so explicitly rather
|
||||
than letting the distinction go unstated. CR-000 has not yet received
|
||||
criticism from any other actor.
|
||||
|
||||
Each future entry should record, at minimum: the criticism ID, which
|
||||
claim(s) or manuscript section it challenges, the criticism itself, the
|
||||
critic's identity (human or agent), and its resolution state (open,
|
||||
addressed, disputed, accepted).
|
||||
---
|
||||
|
||||
## CR-000-X001
|
||||
|
||||
**Challenges:** `CR-000-C002`, `CR-000-C003`
|
||||
|
||||
**Criticism:** `CR-000-C002` and `CR-000-C003` claim that papers need not
|
||||
remain the canonical representation of knowledge and that a graph of
|
||||
propositions, evidence, actions, and provenance can outperform
|
||||
document-centric publication. The M0/M1 implementation of CR-000 does not
|
||||
demonstrate this. `claims.md`, `evidence.md`, and `criticism.md` (this
|
||||
file) are flat Markdown documents. Cross-references between paper-local
|
||||
objects (e.g. this entry's own "Challenges" field, or a future evidence
|
||||
entry's "bears-on" field) are strings that a reader or script must locate
|
||||
manually or by pattern-matching — they are not edges in any queryable
|
||||
graph, and no tool in the repository traverses, validates the
|
||||
consistency of, or queries these relations as a graph.
|
||||
`scripts/validate_research_registry.py` checks registry/publication
|
||||
metadata agreement and Markdown link resolution, but nothing about
|
||||
proposition-evidence-criticism relation integrity. As built, CR-000 is
|
||||
closer to a set of cross-referenced prose documents with ID labels than to
|
||||
the graph representation §2.1 and §11 of `manuscript.md` describe as the
|
||||
alternative to document-centrism. This does not show the underlying idea
|
||||
in `CR-000-C002`/`CR-000-C003` is false — no graph implementation has been
|
||||
attempted yet, so there is no evidence against the idea itself, only
|
||||
against the claim that this paper's own construction demonstrates it.
|
||||
|
||||
- **Critic:** agent:claude-sonnet-5 (with human:bernd.worsch), self-criticism
|
||||
- **Raised:** 2026-09-29
|
||||
- **Resolution state:** open — resolving this requires either building or
|
||||
at least prototyping something that is actually graph-queryable, or
|
||||
narrowing `CR-000-C002`/`CR-000-C003` to a claim this paper's evidence
|
||||
can actually support. Neither is in scope for `CR-WP-0003`; see the
|
||||
workplan's residual handoff.
|
||||
|
||||
## CR-000-X002
|
||||
|
||||
**Challenges:** `CR-000-C004` (the strength of evidence offered for it, not
|
||||
its content)
|
||||
|
||||
**Criticism:** `CR-000-C004` claims criticism can operate continuously
|
||||
rather than as a discrete peer-review gate. The only criticism CR-000 has
|
||||
received to date — this entry and `CR-000-X001` — is self-authored by the
|
||||
same human/agent pairing that wrote the claims and manuscript text under
|
||||
criticism, during the same workplan that wrote them. This is a weak
|
||||
instance of continuous criticism, not independent validation of it:
|
||||
self-criticism is structurally biased toward surfacing objections the
|
||||
author is comfortable publishing, and `seed/ResearchSignals.md` §8 names
|
||||
discounting self-interaction as an explicit anti-gaming principle for
|
||||
criticism signals generally. Until CR-000 receives criticism from an actor
|
||||
other than the paper's own author-agent pair, `CR-000-C004` should be read
|
||||
as motivating this paper's process rather than validated by it, and this
|
||||
criticism file itself should not be cited as evidence that the continuous-
|
||||
criticism model works.
|
||||
|
||||
- **Critic:** agent:claude-sonnet-5 (with human:bernd.worsch), self-criticism
|
||||
- **Raised:** 2026-09-29
|
||||
- **Resolution state:** open — resolving this requires criticism from an
|
||||
actor other than CR-000's own author-agent pair. Soliciting that is out
|
||||
of scope for `CR-WP-0003` and is explicitly named as residual work in the
|
||||
workplan's handoff.
|
||||
|
|
|
|||
|
|
@ -1,17 +1,42 @@
|
|||
# CR-000 — Coulomb Research: A Minimal Self-Improving Architecture for Human-AI Co-Creation Science
|
||||
|
||||
> **Draft state:** This is an M0 outline skeleton, not a coherent M1 v0.1
|
||||
> manuscript. Sections marked `[CONJECTURE]` state an unverified position
|
||||
> this paper intends to argue for. Sections marked `[MISSING]` are
|
||||
> acknowledged gaps with no content yet — they are not silently skipped.
|
||||
> No results, citations, or evidence are asserted below; all evidentiary
|
||||
> support belongs in `evidence.md`, linked by ID, once it exists.
|
||||
> **Draft state:** This is an M1 v0.1 internal-circulation manuscript. It is
|
||||
> a coherent draft, not a finished or externally validated paper. Sections
|
||||
> marked `[CONJECTURE]` state a position this paper argues for but that is
|
||||
> not yet backed by evidence in `evidence.md` (which remains empty — see
|
||||
> §11 and §12). Every claim numbered `CR-000-C<NNN>` below is tracked in
|
||||
> `claims.md`; several are marked `contested` there following the
|
||||
> self-criticism recorded in `criticism.md` (§11 summarizes why). No
|
||||
> results, external citations, or fabricated evidence are asserted below.
|
||||
|
||||
## Abstract
|
||||
|
||||
`[MISSING]` — cannot be honestly written before §§1–13 have real content to
|
||||
summarize. A placeholder abstract would misrepresent the paper's current
|
||||
state.
|
||||
Coulomb Research proposes reducing scientific knowledge production to a
|
||||
small cybernetic kernel — actors, propositions, evidence, actions,
|
||||
resources, and criticism, arranged in a recursive object-level and
|
||||
meta-level loop (`seed/CoulombResearchKernel.md`) — and treating
|
||||
conventional research institutions (journals, venues, review boards) as
|
||||
interoperability surfaces at the boundary of that kernel rather than as
|
||||
internal necessities (`seed/PublicationInterface.md`). This paper, CR-000,
|
||||
is that architecture's own first experiment: it is written using the
|
||||
artifact conventions (`docs/ResearchArtifactConvention.md`) the kernel
|
||||
prescribes, inside the program (`RP-000`) whose subject is Coulomb Research
|
||||
itself. We state the design objective (institutional minimality,
|
||||
co-creation science), summarize the kernel and its publication and signal
|
||||
layers, and report the paper's own construction as its first initial
|
||||
experiment (§12). The central finding at this stage is negative and
|
||||
self-directed: the current implementation, despite arguing that documents
|
||||
should not remain the canonical representation of research (`CR-000-C002`,
|
||||
`CR-000-C003`), is itself built from flat Markdown documents with no
|
||||
queryable graph behind the ID references — a tension recorded as
|
||||
self-criticism `CR-000-X001` and reflected in `claims.md` by marking
|
||||
`CR-000-C002` and `CR-000-C003` `contested`. We treat this as evidence that
|
||||
institutional minimality is easy to state and hard to build without first
|
||||
reintroducing the very document-centric scaffolding it argues against. The
|
||||
paper's central research question — whether the kernel actually supports
|
||||
real scientific coordination, or merely restates document-centric practice
|
||||
under new vocabulary — remains open and is the subject of the M2 milestone
|
||||
that follows this one.
|
||||
|
||||
## 1. Motivation
|
||||
|
||||
|
|
@ -26,11 +51,24 @@ principle this paper is built on.
|
|||
|
||||
### 2.1 Institutional inheritance in digital science
|
||||
|
||||
`[MISSING]` — requires a literature pass on prior attempts at post-journal
|
||||
or open-science infrastructure (e.g. preprint servers, open review
|
||||
platforms) and where they retained legacy structure. No such survey has
|
||||
been conducted yet; nothing here should be read as asserting what that
|
||||
survey would find.
|
||||
`[CONJECTURE]` This subsection is an impression, not a literature review —
|
||||
no formal survey has been conducted, and no specific system's claims,
|
||||
dates, or figures are asserted here as verified fact. With that caveat: a
|
||||
recurring pattern in prior digital-science infrastructure (preprint
|
||||
repositories, open-review platforms, academic social networks) is that they
|
||||
digitize the *distribution* of a research institution's outputs — faster
|
||||
copies of papers, faster commentary threads — while leaving the
|
||||
institution's *unit of knowledge* unchanged. The paper, as a fixed
|
||||
document with a single version of record and a small number of named
|
||||
authors, survives the migration to digital infrastructure largely intact.
|
||||
What changes is speed and reach, not the underlying representation.
|
||||
`CR-000-C002` and `CR-000-C003` are this paper's attempt to state an
|
||||
alternative directly: that the paper need not be the canonical internal
|
||||
unit, and that a graph of typed propositions, evidence, and provenance
|
||||
could support richer coordination. §11 records why the current
|
||||
implementation does not yet demonstrate this and instead illustrates how
|
||||
easily the pattern above reasserts itself even when explicitly
|
||||
argued against.
|
||||
|
||||
### 2.2 AI changes the cost structure of research
|
||||
|
||||
|
|
@ -44,88 +82,315 @@ foregone conclusions.
|
|||
|
||||
### 3.1 Co-creation science
|
||||
|
||||
Restates `INTENT.md`'s mission in paper form: `[MISSING]`.
|
||||
`INTENT.md` states the mission this paper operationalizes: to improve the
|
||||
rate and quality at which humans and artificial intelligences can create,
|
||||
criticize, test, combine, and reuse knowledge, as a minimal system for
|
||||
co-creation science rather than a digital replica of existing research
|
||||
institutions. Co-creation, in that framing, is not a claim that human and
|
||||
AI contributions are interchangeable or equally weighted in every case — it
|
||||
is a claim that the kernel should not structurally privilege one actor
|
||||
class over the other (`seed/CoulombResearchKernel.md` §2.1: "the kernel
|
||||
does not assign epistemic authority based on actor class"). This paper's
|
||||
own `publication.yaml` contribution record (§7) is a direct, if small,
|
||||
instance of that design objective in practice rather than only in
|
||||
principle.
|
||||
|
||||
### 3.2 Institutional minimality
|
||||
|
||||
Restates `INTENT.md` principle 9 (Institutional minimality) and
|
||||
`seed/CoulombResearchKernel.md` §10 in paper form: `[MISSING]`.
|
||||
`INTENT.md` principle 9 states that a function should not become an
|
||||
institution if it can be performed reliably by protocol, software, agents,
|
||||
markets, or voluntary coordination. `seed/CoulombResearchKernel.md` §10
|
||||
sharpens this into a falsifiable-in-spirit test: a proposed feature belongs
|
||||
in the kernel only if removing it prevents the core research loop from
|
||||
functioning; everything else — convenience, discovery, prestige,
|
||||
publishing, governance, monetization, presentation — belongs outside the
|
||||
kernel. `CR-000-C006` states this paper's operational reading of that
|
||||
principle: institutional functions should default to *not existing* in a
|
||||
given implementation until a concrete research artifact demonstrates a
|
||||
specific, load-bearing need for them, rather than being built in advance
|
||||
on the expectation that they will eventually be needed. M0
|
||||
(`workplans/CR-WP-0002-research-facility-skeleton.md`) applied this
|
||||
directly: no database, registry service, or authentication layer was built
|
||||
because a Git-versioned YAML registry and Markdown files were sufficient
|
||||
for one paper (§9, §5 of `seed/CoulombResearchMilestonePlan.md` M5, makes
|
||||
the same argument for the registry specifically). Whether this discipline
|
||||
holds as the number of papers, programs, and contributors grows is untested
|
||||
by a single-paper facility and is explicitly out of scope for what this
|
||||
paper can claim.
|
||||
|
||||
## 4. The Coulomb Research kernel
|
||||
|
||||
This section will restate, for a reader unfamiliar with the repository, the
|
||||
kernel primitives defined authoritatively in `seed/CoulombResearchKernel.md`
|
||||
§2. It is a presentation of existing design content, not new argument, and
|
||||
is deferred to M1 to avoid duplicating the seed document prematurely.
|
||||
This is a condensed presentation of `seed/CoulombResearchKernel.md` §2 for
|
||||
a reader unfamiliar with the repository; it restates existing design
|
||||
content rather than arguing a new position, and the seed document remains
|
||||
authoritative over this summary.
|
||||
|
||||
### 4.1 Actors
|
||||
|
||||
`[MISSING]`
|
||||
An addressable participant capable of research-related action — human,
|
||||
agent, collective, or organization. The kernel does not assign epistemic
|
||||
authority based on actor class (§2.1).
|
||||
|
||||
### 4.2 Propositions
|
||||
|
||||
`[MISSING]`
|
||||
An addressable assertion, conjecture, prediction, explanation,
|
||||
question-framing, or model statement, which may be uncertain, contested,
|
||||
superseded, or unresolved (§2.2). This paper's own `claims.md` entries are
|
||||
an implementation-level approximation of propositions, scoped to one paper
|
||||
rather than the full research graph (`docs/ResearchArtifactConvention.md`
|
||||
§1.1) — see §11 for why that approximation is currently weaker than the
|
||||
kernel's own model.
|
||||
|
||||
### 4.3 Evidence
|
||||
|
||||
`[MISSING]`
|
||||
An observation or artifact that bears on one or more propositions,
|
||||
preserving provenance and content-addressable where practical (§2.3). CR-000
|
||||
currently has none (`evidence.md` is empty by design — see §12).
|
||||
|
||||
### 4.4 Actions
|
||||
|
||||
`[MISSING]`
|
||||
An intervention intended to reduce uncertainty, test a proposition,
|
||||
produce evidence, or create a reusable research artifact (§2.4). Writing
|
||||
this manuscript, and the M0/M1 workplans that structured that writing, are
|
||||
themselves actions in this sense.
|
||||
|
||||
### 4.5 Resources
|
||||
|
||||
`[MISSING]`
|
||||
A scarce capability consumed, reserved, or transferred to perform actions —
|
||||
money, compute, equipment, data access, attention, agent runtime,
|
||||
permissions (§2.5). At this scale, the only resources this paper has
|
||||
consumed are human review attention and agent (LLM) runtime, both
|
||||
unmeasured; no formal resource allocation exists yet, consistent with the
|
||||
institutional-minimality argument in §3.2 (no allocator has been built
|
||||
because none has been needed).
|
||||
|
||||
## 5. Cybernetic research loop
|
||||
|
||||
`[MISSING]` — presentation of `seed/CoulombResearchKernel.md` §1.
|
||||
`seed/CoulombResearchKernel.md` §1 defines an object-level loop (observe →
|
||||
model → criticize → intervene → observe consequences → update model) and a
|
||||
meta-level loop that observes the research process itself and modifies
|
||||
tools, incentives, or protocol in response. This paper is an attempt to run
|
||||
one object-level cycle explicitly and visibly: M0 produced a model (the
|
||||
draft skeleton), this M1 workplan intervened on it (real content, plus a
|
||||
deliberate self-criticism pass in §11), and the result is a paper that
|
||||
states, in its own claims table, where that criticism landed. The cycle is
|
||||
not closed yet — "update model" in response to *external* criticism has not
|
||||
happened, because no external criticism has been solicited (§11, §12).
|
||||
|
||||
## 6. Recursive self-improvement
|
||||
|
||||
`[MISSING]` — presentation of the meta-level loop in
|
||||
`seed/CoulombResearchKernel.md` §1, plus this paper's own role as an
|
||||
instance of it (RP-000 studying Coulomb Research using Coulomb Research).
|
||||
`CR-000-C005` (research institutions can recursively experiment on their
|
||||
own coordination mechanisms) is this section's subject. The meta-level loop
|
||||
in `seed/CoulombResearchKernel.md` §1 asks whether the research *process*
|
||||
itself — not just its object-level conclusions — is observed, compared
|
||||
against outcomes, and revised. RP-000
|
||||
(`research/programs/RP-000-researching-research/INTENT.md`) is this paper's
|
||||
program-level instance of that loop: it exists specifically to hold Coulomb
|
||||
Research's own design to the same evidentiary standard it proposes for
|
||||
everything else, rather than exempting the facility's own architecture from
|
||||
criticism because it motivated the repository. Concretely, this manuscript
|
||||
already records one small meta-level correction: `CR-WP-0002` scoped the
|
||||
paper as an "honest draft skeleton" and explicitly deferred a coherent
|
||||
manuscript to M1; this workplan (`CR-WP-0003`) is that deferral being
|
||||
honored rather than silently dropped. Whether this pattern — plan, defer
|
||||
what cannot yet be done honestly, revisit — actually produces better
|
||||
research outcomes than doing everything in one pass is itself an open
|
||||
question this program has not yet accumulated enough cycles to answer.
|
||||
|
||||
## 7. Human-AI research participation
|
||||
|
||||
`[MISSING]` — this section should discuss this very paper's own
|
||||
human/agent contribution record (`publication.yaml`) as a working example,
|
||||
once there is enough revision history to say something concrete.
|
||||
This paper's own contribution record (`publication.yaml`) is a concrete,
|
||||
if minimal, instance of the co-creation-science objective in §3.1:
|
||||
|
||||
```yaml
|
||||
contributors:
|
||||
- actor: human:bernd.worsch
|
||||
contributions: [conceptualization]
|
||||
- actor: agent:claude-sonnet-5
|
||||
contributions: [scaffolding, literature-analysis]
|
||||
```
|
||||
|
||||
At M0/M1, the agent's role has been drafting and structuring text against
|
||||
explicit human-authored source material (`INTENT.md`, the `seed/` design
|
||||
documents, and the workplan tasks that scope each writing pass); the
|
||||
human's role has been setting direction, commissioning the workplans, and
|
||||
retaining approval over what gets committed. This division is not
|
||||
prescribed by the kernel (`seed/CoulombResearchKernel.md` §2.1 explicitly
|
||||
declines to assign epistemic authority by actor class) — it reflects how
|
||||
this particular paper happened to be produced, not a claim about how
|
||||
human/agent contribution should generally divide. `revision-log.md`
|
||||
records each substantive change with its acting actor, so this division is
|
||||
independently checkable rather than only asserted here. `CR-000-C001` (AI
|
||||
reduces the need for several historically human-mediated coordination
|
||||
functions) is directly at issue in this section's own production process,
|
||||
but one paper's authorship split is far too small a sample to bear on
|
||||
`CR-000-C001` as stated — no claim of support is made here.
|
||||
|
||||
## 8. Interoperability with conventional science
|
||||
|
||||
`[MISSING]` — presentation of `seed/PublicationInterface.md`.
|
||||
`seed/PublicationInterface.md` states the governing rule: the living
|
||||
research graph is canonical, and papers are import/export containers,
|
||||
allowing Coulomb to interoperate with traditional science without making
|
||||
the paper the primary internal unit of knowledge. `CR-000-C007` restates
|
||||
this as a claim this paper argues for: a publication adapter that treats
|
||||
papers as import/export containers, rather than as the canonical internal
|
||||
representation, should in principle allow interoperability with
|
||||
conventional venues (journals, preprint servers, ORCID/DOI/ROR/CRediT
|
||||
identity systems — `seed/PublicationInterface.md` §7) without importing
|
||||
those venues' internal constraints (fixed authorship models, single-version
|
||||
gatekeeping, human-only authorship assumptions) into Coulomb's own
|
||||
representation. CR-000 itself is currently only at publication stage P1
|
||||
(internal circulation, `publication.yaml`); no P2/P3 adapter behavior has
|
||||
been exercised, so `CR-000-C007` is argued here but not yet tested against
|
||||
an actual external target. This mirrors §2.1's observation about the field
|
||||
generally: it is easy to state that a system avoids document-centrism at
|
||||
the boundary while the internal representation itself remains
|
||||
document-centric (§11).
|
||||
|
||||
## 9. Decentralization and programmable resources
|
||||
|
||||
`[MISSING]` — presentation of `seed/CoulombResearchKernel.md` §9.
|
||||
`seed/CoulombResearchKernel.md` §9 suggests, as a candidate model rather
|
||||
than a settled architecture, keeping the research graph, discussions,
|
||||
datasets, models, mutable workspaces, and most AI inference off-chain, with
|
||||
identity attestations, content commitments, resource transfers, scarce
|
||||
rights, and selected governance events as optionally on-chain. The stated
|
||||
principle — prioritize decentralization where it increases resilience,
|
||||
portability, independent verification, or freedom to fork, and treat
|
||||
blockchain as unnecessary for ordinary research data — is consistent with
|
||||
the institutional-minimality argument in §3.2: nothing in M0 or M1 required
|
||||
any on-chain component, because Git already provides the resilience,
|
||||
portability, and independent-verification properties needed for one paper
|
||||
and one registry (`seed/CoulombResearchMilestonePlan.md` M5 makes this
|
||||
point specifically about the registry). This paper does not argue that
|
||||
on-chain components will never be justified — only that none has been
|
||||
justified yet, and that the suggested off-chain/on-chain split remains an
|
||||
untested design sketch rather than an implemented boundary.
|
||||
|
||||
## 10. Research signals and relevance
|
||||
|
||||
`[MISSING]` — presentation of `seed/ResearchSignals.md` and
|
||||
`seed/ResearchCharts.md`, to the extent they inform this paper's claims.
|
||||
`seed/ResearchSignals.md` and `seed/ResearchCharts.md` propose keeping
|
||||
attention, influence, epistemic support, utility/reuse, criticism, and
|
||||
generativity as distinct signal families, explicitly rejecting a single
|
||||
canonical "impact score" (`seed/ResearchSignals.md` §5) because it
|
||||
collapses unlike dimensions, invites gaming, and becomes a Goodhart target.
|
||||
`CR-000-C008` states this paper's endorsement of that design principle: no
|
||||
single research signal or composite score should be treated as a stand-in
|
||||
for epistemic support specifically, because support is a claim about what
|
||||
survives evidence and criticism, while attention, reuse, and the rest
|
||||
measure something else entirely (`seed/ResearchSignals.md` §1's
|
||||
"foundational separation"). This section is a presentation of that design
|
||||
principle, not a report of any signal actually being computed: CR-000 has
|
||||
no attention, influence, reuse, or generativity data, because it has not
|
||||
yet circulated beyond this repository (`publication.yaml`
|
||||
`visibility: collaborators`). The one signal family this paper can speak to
|
||||
concretely is criticism (§11), and even there, the criticism is
|
||||
self-authored rather than independently observed, which `[CONJECTURE]`
|
||||
weakens rather than satisfies the anti-self-interaction principle in
|
||||
`seed/ResearchSignals.md` §8.
|
||||
|
||||
## 11. Failure modes
|
||||
|
||||
`[MISSING]` — this section requires actual criticism (`criticism.md`)
|
||||
before it can be written honestly; a self-authored failure-modes section
|
||||
without external criticism would understate risk.
|
||||
This section is written from `CR-000-X001` and `CR-000-X002` in
|
||||
`criticism.md`, added specifically so this section would have real
|
||||
criticism to draw on rather than being self-authored without a named,
|
||||
addressable critique behind it (the M0 skeleton deferred this section for
|
||||
exactly that reason).
|
||||
|
||||
**Document-centrism reasserting itself (`CR-000-X001`).** `CR-000-C002` and
|
||||
`CR-000-C003` argue that papers need not remain the canonical
|
||||
representation of knowledge and that a graph of propositions, evidence,
|
||||
actions, and provenance can outperform document-centric publication. The
|
||||
M0/M1 implementation does not demonstrate this: `claims.md`, `evidence.md`,
|
||||
and `criticism.md` are flat Markdown files. Cross-references between them
|
||||
(e.g. "`CR-000-E003` bears on `CR-000-C002`") are strings a reader or
|
||||
script must locate by grep, not edges in a queryable graph with any
|
||||
traversal, consistency-checking, or query capability beyond what
|
||||
`scripts/validate_research_registry.py` happens to check today (link
|
||||
resolution and registry/publication-metadata agreement — nothing about
|
||||
proposition/evidence/criticism relation integrity). This is precisely the
|
||||
pattern §2.1 describes in the field generally: an infrastructure that
|
||||
argues against document-centrism while quietly rebuilding it. `claims.md`
|
||||
now marks `CR-000-C002` and `CR-000-C003` `contested` on this basis. This
|
||||
is not evidence that the underlying idea is wrong — a real graph
|
||||
representation has simply not been attempted yet — but it is evidence that
|
||||
stating the idea is much cheaper than building it, and that the gap between
|
||||
the two should not be allowed to go unmarked, which is the specific failure
|
||||
this section exists to guard against.
|
||||
|
||||
**Self-criticism is not a substitute for independent criticism
|
||||
(`CR-000-X002`).** `CR-000-C004` claims criticism can operate continuously
|
||||
rather than as a discrete peer-review gate. The only criticism CR-000 has
|
||||
received so far is self-authored, produced by the same
|
||||
human/agent pairing that wrote the claims being criticized, during the same
|
||||
workplan. This is compatible with continuous, low-friction criticism in
|
||||
principle, but it is a weak instance of it in practice: self-criticism is
|
||||
structurally biased toward finding criticisms the author is comfortable
|
||||
publishing, and `seed/ResearchSignals.md` §8 explicitly names
|
||||
self-interaction as something signal systems should discount. Until CR-000
|
||||
receives criticism from an actor other than the one that wrote the claim
|
||||
under criticism, `CR-000-C004` should be read as motivating this paper's
|
||||
process, not as validated by it.
|
||||
|
||||
**A general risk this section itself cannot fully escape.** Writing one's
|
||||
own failure-modes section, informed only by one's own self-criticism, risks
|
||||
producing a section that is thorough-looking but self-limiting — it can
|
||||
only surface the failure modes the author was willing and able to see.
|
||||
This paragraph is that risk stated explicitly rather than hidden by the
|
||||
section's own existence.
|
||||
|
||||
## 12. Initial experiments
|
||||
|
||||
`[MISSING]` — candidate experiment: RP-000 itself, i.e. whether this
|
||||
facility can register, criticize, and revise this very paper (M2). No
|
||||
experiment has been run yet; this section will report on M2 once conducted.
|
||||
The candidate experiment identified in the M0 skeleton was RP-000/CR-000
|
||||
itself: whether this facility can register, criticize, and revise this very
|
||||
paper. This workplan (`CR-WP-0003`) is a partial run of that experiment —
|
||||
it took CR-000 from an empty skeleton through one self-criticism cycle
|
||||
(§11) to a v0.1 manuscript with `claims.md` states updated in response. It
|
||||
is partial because the criticism involved was self-authored (§11,
|
||||
`CR-000-X002`); a fuller run of the experiment requires at least one
|
||||
criticism from an actor other than the paper's own author-agent pair, which
|
||||
is explicitly out of scope for this workplan and is carried forward as
|
||||
residual work (`SCOPE.md`, `docs/ResearchArtifactConvention.md` — see the
|
||||
handoff note at the end of this workplan). No claim of success or failure
|
||||
for the underlying architecture is made from this one partial cycle; a
|
||||
single self-reviewed paper is far too small a sample.
|
||||
|
||||
## 13. Open research questions
|
||||
|
||||
See `research/programs/RP-000-researching-research/questions.md` for the
|
||||
current, maintained list. This section will summarize a subset once the
|
||||
program has run long enough to prioritize among them.
|
||||
`research/programs/RP-000-researching-research/questions.md` is the
|
||||
maintained list; this section summarizes its current state rather than
|
||||
duplicating it.
|
||||
|
||||
- **Q1 (kernel sufficiency)** — the paper's own research question (this
|
||||
document, in full) — remains open. This v0.1 manuscript is a more
|
||||
complete statement of the position than the M0 skeleton, but it is not
|
||||
evidence for the position; see §11 for why the implementation so far cuts
|
||||
against, rather than for, two of the paper's own claims.
|
||||
- **Q2 (representation usefulness)** — still blocked on M2
|
||||
(claim/evidence/criticism linkage exercise), which this workplan
|
||||
deliberately did not fold into its own scope (see the workplan's
|
||||
Non-Goals). §11's `CR-000-X001` is, if anything, a preliminary negative
|
||||
signal on Q2's premise: the representation as built has not yet shown
|
||||
itself more useful than prose, only differently organized prose with ID
|
||||
labels.
|
||||
- **Q3 (institutional minimality in practice)** — §3.2 and §9 report one
|
||||
small data point each (no database or registry service was needed for
|
||||
M0/M1; no on-chain component was needed either), consistent with the
|
||||
kernel test predicting these functions were not load-bearing yet at this
|
||||
scale. Whether that holds as the facility grows past one paper is
|
||||
untested.
|
||||
|
||||
## 14. Conclusion
|
||||
|
||||
`[MISSING]` — cannot be honestly written before the preceding sections
|
||||
exist.
|
||||
CR-000's v0.1 draft states a real position — that a small kernel of actors,
|
||||
propositions, evidence, actions, and resources, with conventional
|
||||
institutions treated as an interoperability boundary rather than an
|
||||
internal requirement, can support real research coordination — and
|
||||
subjects that position to the facility's own tools rather than presenting
|
||||
it as already validated. The most useful result of writing this v0.1 is not
|
||||
any of its numbered claims but the self-criticism in §11: the paper that
|
||||
argues papers should not remain canonical is itself, right now, a paper.
|
||||
Closing that specific gap — building or at least prototyping something that
|
||||
is actually graph-queryable rather than ID-labeled prose, and getting
|
||||
criticism from an actor other than this paper's own author-agent pair — is
|
||||
the concrete, falsifiable next step this paper leaves for the program that
|
||||
follows it, rather than a general call for "future work."
|
||||
|
|
|
|||
|
|
@ -20,3 +20,26 @@ rather than edited in place in their source files.
|
|||
- **Context:** Implements `workplans/CR-WP-0002-research-facility-skeleton.md`
|
||||
task T02. This is a draft skeleton, not a coherent v0.1 manuscript (M1 is
|
||||
a separate, later milestone).
|
||||
|
||||
## 2026-09-29 — v0.1 manuscript
|
||||
|
||||
- **Actor:** agent:claude-sonnet-5 (with human:bernd.worsch)
|
||||
- **Change:** Replaced all `[MISSING]` sections of `manuscript.md` with real
|
||||
content (§§2.1, 3.1, 3.2, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, Abstract).
|
||||
Added three new claims (`CR-000-C006`, `CR-000-C007`, `CR-000-C008`) to
|
||||
`claims.md`. Added two self-criticism entries (`CR-000-X001`,
|
||||
`CR-000-X002`) to `criticism.md`, and updated `CR-000-C002` and
|
||||
`CR-000-C003` to `contested` in `claims.md` on the basis of `CR-000-X001`
|
||||
(the implementation is flat Markdown, not a queryable graph, in tension
|
||||
with those claims). `evidence.md` remains empty — no evidence has been
|
||||
produced yet; see `manuscript.md` §12.
|
||||
- **Context:** Implements `workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md`
|
||||
tasks T01–T03. `publication.yaml` `version` updated to `"0.1"` (already
|
||||
`"0.1"`; confirmed accurate against this content, not incremented from a
|
||||
higher M0 placeholder). This is a coherent v0.1 internal-circulation
|
||||
manuscript per the M1 exit criterion
|
||||
(`seed/CoulombResearchMilestonePlan.md`), self-criticized but not yet
|
||||
independently criticized (`CR-000-X002`). Independent criticism and a
|
||||
prototype graph representation (`CR-000-X001`) are carried forward as
|
||||
residual work rather than folded into this workplan; see
|
||||
`workplans/CR-WP-0003-paper-zero-v0-1-manuscript.md` for the handoff.
|
||||
|
|
|
|||
|
|
@ -31,8 +31,12 @@ claims linked to real evidence and criticism (M2), so it is currently
|
|||
unresolved by construction — M0 only establishes the empty structure this
|
||||
question will be tested against.
|
||||
|
||||
Status: open — blocked on M1 (coherent manuscript) and M2 (claim/evidence
|
||||
linkage) being carried out, not just scaffolded.
|
||||
Status: open — M1 (`CR-WP-0003`) produced a coherent v0.1 manuscript and, in
|
||||
doing so, surfaced a preliminary negative signal: the paper's own
|
||||
implementation is flat Markdown, in tension with `CR-000-C002`/
|
||||
`CR-000-C003` (see `criticism.md` `CR-000-X001`). M2
|
||||
(`CR-WP-0004`) is the workplan that will actually test this question
|
||||
against linked evidence rather than self-criticism alone.
|
||||
|
||||
## Q3 — Institutional minimality in practice
|
||||
|
||||
|
|
|
|||
|
|
@ -4,11 +4,15 @@ type: workplan
|
|||
title: "M1: CR-000 Paper Zero v0.1 manuscript"
|
||||
domain: communication
|
||||
repo: coulomb-research
|
||||
status: proposed
|
||||
status: finished
|
||||
owner: codex
|
||||
topic_slug: coulomb-social
|
||||
created: "2026-09-28"
|
||||
updated: "2026-09-28"
|
||||
updated: "2026-09-29"
|
||||
quality_dod: DoD-Ok
|
||||
quality_dod_at: "2026-09-29"
|
||||
quality_dod_by: codex
|
||||
quality_dod_note: "v0.1 manuscript coherent, all [MISSING] sections replaced, self-criticism recorded and claims updated accordingly; independent criticism and graph prototype handed off to CR-WP-0004 (M2) as residuals rather than claimed here."
|
||||
origin: residual
|
||||
origin_ref: CR-WP-0002
|
||||
state_hub_workstream_id: "2e0fa669-8410-5a4f-a422-fb6b8797768a"
|
||||
|
|
@ -37,7 +41,7 @@ Inputs: `research/programs/RP-000-researching-research/papers/paper-000/`
|
|||
|
||||
```task
|
||||
id: CR-WP-0003-T01
|
||||
status: todo
|
||||
status: done
|
||||
priority: high
|
||||
state_hub_task_id: "2b872628-b731-5b71-a687-8afd5ae4fbfc"
|
||||
```
|
||||
|
|
@ -61,7 +65,7 @@ placeholder) and any conjectural claim not yet backed by evidence is marked
|
|||
|
||||
```task
|
||||
id: CR-WP-0003-T02
|
||||
status: todo
|
||||
status: done
|
||||
priority: medium
|
||||
state_hub_task_id: "164e498f-8276-5f59-afad-954368c19189"
|
||||
```
|
||||
|
|
@ -84,7 +88,7 @@ silently dropped).
|
|||
|
||||
```task
|
||||
id: CR-WP-0003-T03
|
||||
status: todo
|
||||
status: done
|
||||
priority: high
|
||||
state_hub_task_id: "f1ffc924-5b95-5f2d-a6c3-2f065dfcfee1"
|
||||
```
|
||||
|
|
@ -110,6 +114,14 @@ exit criterion) with `publication.yaml` `version: "0.1"` confirmed accurate,
|
|||
no `[MISSING]` markers remaining except where explicitly deferred with
|
||||
stated rationale, and the registry validator passes.
|
||||
|
||||
Closed: added `CR-000-X001` and `CR-000-X002` to `criticism.md`
|
||||
(self-criticism), updated `CR-000-C002`/`CR-000-C003` to `contested` in
|
||||
`claims.md`, added `CR-000-C006`–`CR-000-C008`, wrote the Abstract and §11
|
||||
(Failure modes) last. Registry validator passes. M2 (independent criticism,
|
||||
evidence linkage, and a response to the document-centrism criticism) handed
|
||||
off as `workplans/CR-WP-0004-claim-evidence-discipline.md` rather than
|
||||
folded into this workplan.
|
||||
|
||||
## Non-Goals
|
||||
|
||||
No P2/P3 publication advancement, no M2 claim/evidence/criticism linkage
|
||||
|
|
|
|||
142
workplans/CR-WP-0004-claim-evidence-discipline.md
Normal file
142
workplans/CR-WP-0004-claim-evidence-discipline.md
Normal file
|
|
@ -0,0 +1,142 @@
|
|||
---
|
||||
id: CR-WP-0004
|
||||
type: workplan
|
||||
title: "M2: introduce minimal claim/evidence discipline for CR-000"
|
||||
domain: communication
|
||||
repo: coulomb-research
|
||||
status: proposed
|
||||
owner: codex
|
||||
topic_slug: coulomb-social
|
||||
created: "2026-09-29"
|
||||
updated: "2026-09-29"
|
||||
origin: residual
|
||||
origin_ref: CR-WP-0003
|
||||
---
|
||||
|
||||
# M2: introduce minimal claim/evidence discipline for CR-000
|
||||
|
||||
Implement M2 of `seed/CoulombResearchMilestonePlan.md`: test whether the
|
||||
Coulomb-native claim/evidence/criticism representation is actually useful
|
||||
for conducting research (Q2 in
|
||||
`research/programs/RP-000-researching-research/questions.md`), by linking
|
||||
CR-000's existing claims to real evidence and criticism rather than leaving
|
||||
`evidence.md` empty.
|
||||
|
||||
This workplan carries forward two residuals named explicitly in
|
||||
`CR-WP-0003`'s self-criticism (`CR-000-X001`, `CR-000-X002` in
|
||||
`criticism.md`):
|
||||
|
||||
1. **Independent criticism.** All criticism CR-000 has received so far
|
||||
(`CR-000-X001`, `CR-000-X002`) is self-authored by the same human/agent
|
||||
pair that wrote the claims under criticism. `CR-000-C004` (criticism can
|
||||
operate continuously) is not meaningfully tested until CR-000 receives
|
||||
criticism from a different actor.
|
||||
2. **Document-centrism.** `CR-000-C002`/`CR-000-C003` (currently `contested`
|
||||
in `claims.md`) argue papers should not remain the canonical
|
||||
representation and that a graph representation can outperform
|
||||
document-centric publication, but CR-000's own artifacts are flat
|
||||
Markdown with no queryable graph behind the ID cross-references.
|
||||
|
||||
Inputs: `research/programs/RP-000-researching-research/papers/paper-000/`
|
||||
(all files, especially `claims.md` and `criticism.md`),
|
||||
`seed/CoulombResearchMilestonePlan.md` (M2 section), and
|
||||
`docs/ResearchArtifactConvention.md`.
|
||||
|
||||
## Solicit and Record Independent Criticism
|
||||
|
||||
```task
|
||||
id: CR-WP-0004-T01
|
||||
status: todo
|
||||
priority: high
|
||||
```
|
||||
|
||||
Obtain at least one criticism entry in `criticism.md` from an actor other
|
||||
than the human/agent pair that authored `CR-WP-0002`/`CR-WP-0003` (e.g. a
|
||||
human collaborator's review, or a differently-configured agent/model asked
|
||||
to critique CR-000 independently, with its provenance recorded honestly per
|
||||
`docs/ResearchArtifactConvention.md` §4). Do not simulate or fabricate an
|
||||
"independent" critic using the same authoring context — that would not
|
||||
resolve `CR-000-X002`, only relabel it. Update the resolution state of
|
||||
`CR-000-X002` in `criticism.md` once independent criticism exists.
|
||||
|
||||
Done when at least one criticism entry's critic is verifiably distinct from
|
||||
CR-000's own authors, and `claims.md`/`criticism.md` reflect its impact on
|
||||
any claim it bears on.
|
||||
|
||||
## Collect and Link Real Evidence
|
||||
|
||||
```task
|
||||
id: CR-WP-0004-T02
|
||||
status: todo
|
||||
priority: high
|
||||
```
|
||||
|
||||
Populate `evidence.md` with real evidence entries (`CR-000-E001`, ...) that
|
||||
bear on specific claims in `claims.md` — not placeholder or anticipated
|
||||
evidence. Candidate evidence sources include: this program's own revision
|
||||
history and workplan record as evidence about `CR-000-C001`/`CR-000-C005`
|
||||
(human-AI participation, recursive self-improvement), and the outcome of
|
||||
T01 as evidence about `CR-000-C004` (continuous criticism). Update each
|
||||
linked claim's state (conjectural/supported/contested/etc.) in `claims.md`
|
||||
to reflect what the evidence actually shows, including leaving a claim
|
||||
`conjectural` if the evidence is inconclusive — do not inflate a claim's
|
||||
state to `supported` on weak or single-instance evidence.
|
||||
|
||||
Done when at least the claims discussed in T01's outcome and in this task's
|
||||
description have at least one linked evidence entry each, with claim states
|
||||
updated accordingly.
|
||||
|
||||
## Prototype a Queryable Representation (or Explicitly Decline To)
|
||||
|
||||
```task
|
||||
id: CR-WP-0004-T03
|
||||
status: todo
|
||||
priority: medium
|
||||
```
|
||||
|
||||
Directly address `CR-000-X001`: either (a) build the smallest possible
|
||||
prototype that makes claim/evidence/criticism relations actually
|
||||
queryable (e.g. a script that loads all `CR-000-*` IDs and their stated
|
||||
relations from the paper's Markdown files and answers a query like "what
|
||||
challenges CR-000-C002" or "what evidence bears on CR-000-C003" without
|
||||
manual grepping), consistent with the institutional-minimality principle
|
||||
of building only what a concrete artifact demonstrates a need for; or (b)
|
||||
if the facility's scale (one paper) does not yet justify even a minimal
|
||||
prototype, record that reasoning explicitly as a revision-log entry and
|
||||
leave `CR-000-X001` open with that rationale, rather than silently letting
|
||||
it drop. Do not build a database or service — that remains out of scope
|
||||
per the M0/M2 non-goals.
|
||||
|
||||
Done when `CR-000-X001` has either a working minimal prototype referenced
|
||||
from `manuscript.md` §11, or an explicit, reasoned decision recorded in
|
||||
`revision-log.md` for why not yet, with `criticism.md`'s resolution state
|
||||
updated either way.
|
||||
|
||||
## Assess Representation Usefulness and Close Out M2
|
||||
|
||||
```task
|
||||
id: CR-WP-0004-T04
|
||||
status: todo
|
||||
priority: high
|
||||
```
|
||||
|
||||
Using the outcomes of T01–T03, answer Q2
|
||||
(`research/programs/RP-000-researching-research/questions.md`): was the
|
||||
Coulomb-native claim/evidence/criticism representation useful for
|
||||
conducting this research, or did it mainly add bookkeeping overhead? Record
|
||||
the answer as a new section or revision to `manuscript.md`, update Q2's
|
||||
status in `questions.md`, and update `claims.md` states for any claim T01–
|
||||
T03 newly bear on. Run `python3 scripts/validate_research_registry.py` and
|
||||
the canonical Repo Manager sync. Before closure, evaluate whether M3 (CR-001
|
||||
registration) or a different next step is the appropriate live follow-up,
|
||||
and hand it off per the residual convention.
|
||||
|
||||
Done when the M2 exit criterion (major manuscript claims are explicitly
|
||||
addressable and linked to supporting or challenging evidence) is met for at
|
||||
least the claims this workplan touched, and the registry validator passes.
|
||||
|
||||
## Non-Goals
|
||||
|
||||
No CR-001 work (that is M3), no P2/P3 publication advancement, no general
|
||||
graph database or service (only a minimal prototype or an explicit decision
|
||||
not to build one, per T03), no facility software beyond what T03 justifies.
|
||||
Loading…
Add table
Add a link
Reference in a new issue