pod
Other formats agents might prefer:
markdownjsonllms.txt

Agent? You probably want markdown or json, or Pod over MCP.

Reported issues for Jacobian

Pod holds 24 of 208 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to Jacobian.

Most discussed

[Evaluation]: Jacobian is available but unused across a four-case conjecture canary

Area

Agent evaluation, MCP tool discovery, recently solved conjecture reliability.

Reproduction

A frozen four-case canary was run with gpt-5.6-terra at low reasoning under three conditions:

  1. no Jacobian;
  2. ordinary Jacobian availability;
  3. the same Jacobian surface plus a frozen 99-word selective operation-grounding card.

Prompts, sandbox, unified-exec mode, timeouts, and model configuration were otherwise held fixed.

Jacobian treatment fixture:

  • revision: `fb33f6f471ab804418

Read the thread · 2026-08-08 · closed · 37 comments

[Design]: Evaluate native resource-link handoffs for durable capability results

Decision

Should capability.invoke return native MCP resource links for durable result and episode artifacts, alongside its compact text projection, after a model-in-the-loop evaluation shows that supported hosts reliably follow those links with resources/read?

Context

Jacobian already has the important architectural pieces:

  • immutable artifacts are readable through the artifact://sha256/{digest} resource template;
  • capability.invoke keeps the canonical CapabilityResult in

Read the thread · 2026-07-29 · closed · 8 comments

[Feature]: Make capability contracts easier for agents to discover and compose

Priority

P2 (medium)

Area

mcp, kernel

Problem

Agents can call capability.describe and capability.invoke, but successful mathematical composition still depends on understanding exact scope, evidence type, artifact flow, and failure recovery from compact tool descriptions. The initial paired transcripts show that opaque artifact outputs and weak provenance cues can cause an agent to reconstruct or relabel an object instead of using the exact returned artifact.

Adding more cap

Read the thread · 2026-07-25 · closed · 7 comments

[Security][Reproducibility]: Adversarially validate per-checker identity, dependency closure, and non-interference

Priority

P1 checker-identity and operability bug: every bundled Python checker currently inherits one coarse package-wide implementation digest, and that digest also includes the entire jacobian product package because the checker worker lives inside it. Unrelated source changes can invalidate all checker authorizations, while some actual runtime dependencies are not represented by the digest at all.

Area

Checker authorization, implementation identity, worker runtime, packaging, provi

Read the thread · 2026-08-11 · closed · 5 comments

[Experiment][MCP]: Evaluate schema-bearing direct operation tools against the fixed two-tool contract

Summary

Jacobian currently represents hundreds of mathematical operations as data behind one MCP meta-tool:

{
  "name": "math.run",
  "arguments": {
    "capability_id": "matrix.rank.compute",
    "payload": {}
  }
}

The selected operation’s actual input/output schemas, effects, execution behavior, and value type are not the schema of the tool the model calls. They were returned earlier by math.find as data. This erases the strongest native affordance MCP provides: every tool

Read the thread · 2026-08-11 · closed · 5 comments

[Superseded]: Improve concrete examples/contracts; do not add prepared-call tokens or dynamic selected tools

Disposition

Closed as not planned. The original ergonomics diagnosis remains useful, but the proposed schema-bound execution mechanisms would introduce another stateful handoff protocol.

The issue identified a real problem: after math.find, an agent must place a capability-specific nested request into generic math.run arguments, and weak models can choose the wrong wrapper level.

The proposed alternatives—per-session dynamically materialized tools, prepared invocation tokens bound to c

Read the thread · 2026-08-10 · closed · 5 comments

[Architecture] Preserve declared producer-consumer composition

Problem

A producer can return a canonical value that a declared consumer then rejects, reparses into a parallel representation, or loses at a serialized boundary.

Desired outcome

When a producer or its declared consumer changes, test native and serialized composition with the same canonical value. Include a meaningful empty, zero, singleton, or other degenerate carrier when that value is part of the contract.

Non-goals

Do not infer every possible composition pair from annotations o

Read the thread · 2026-08-24 · closed · 4 comments

markov_chain math module exports missing mixing_time symbol

Symptom

Loading markov-chain operations fails at import time because jacobian.math.markov_chain exports mixing_time but the implementation module defines only ergodic_properties and stationary_distribution.

Reproducer

from jacobian.domains.markov_chain.math_tools import MARKOV_CHAIN_OPERATIONS

Observed traceback:

Traceback (most recent call last):
  File ".../jacobian/domains/markov_chain/operations.py", line 13, in <module>
    from jacobian.math.markov_c

[Read the thread](https://github.com/morluto/jacobian/issues/1754) · 2026-08-16 · closed · 4 comments

## Most recent

### Expose admitted operations directly for client-managed discovery and composition

## Decision

Should Jacobian replace its mandatory `math.find` -> `math.run` execution path with directly exposed typed MCP operations, allowing clients with deferred tool search and code mode to discover and compose those operations themselves?

This issue proposes that direct operation tools become the only execution surface. `math.find` may remain only if it provides measurable mathematical vocabulary discovery beyond client tool search. `math.run` would be removed rather than retained as a c

[Read the thread](https://github.com/morluto/jacobian/issues/2982) · 2026-08-28 · closed · 3 comments

### [Discovery] Separate math.find namespace filtering from descriptive tags

## Current limitation

`math.find` exposes an optional `domain` filter, but its implementation does not have one stable meaning. A value matches either the first segment of an operation ID or any descriptive tag:

```python
return (
    normalized_domain == normalize_domain(operation_domain(operation))
    or normalized_domain in normalized_tags
)

Consequently an agent can reasonably use domain="polynomial" expecting the polynomial.* operation family, while the result also contains grap

Read the thread · 2026-08-27 · closed · 0 comments

[Graphs] Construct bounded rooted-tree fine partitions

Parent gap / RFC

Erdős Problem 550 was resolved in Li, A Resolution of Erdős Problem 550 on Tree versus Complete Multipartite Ramsey Numbers (arXiv:2606.23659v2). Its off-Turán embedding argument repeatedly needs a finite rooted-tree decomposition before any regularity, Ramsey, or compactness reasoning: choose a small seed set and expose the bounded rooted components (shrubs) with their boundary/parity data.

Jacobian has graph and tree-decomposi

Read the thread · 2026-08-27 · closed · 0 comments

[Coding theory]: Construct the exact selected-distance graph of an explicit binary code

Parent gap / RFC

Follow-up to closed #1785. Its proposed code.binary.constant_weight.distance_graph.compute was an explicit acceptance criterion, but the landed code_nonlinear domain currently exposes only word distance, compact explicit/constant-weight profiles, and a support-set conversion.

Public mathematical postcondition

For a bounded explicit binary code and selected Hamming distance, return the complete indexed simple graph w

Read the thread · 2026-08-27 · closed · 0 comments

[Rigidity] Compute exact planar framework rigidity-matrix profiles

Current limitation

Jacobian can compute pairwise distances of a labelled rational planar configuration and the exact rank of a caller-authored rational matrix. It has no operation that binds a realised graph to its planar rigidity matrix: callers must independently align graph vertices with point labels, lay out the two coordinate columns per vertex, construct one row per edge, and interpret the rank.

That is a reusable finite geometry postcondition, not a unit-distance or rigidity-conjectu

Read the thread · 2026-08-27 · closed · 1 comment

[Matrix permanent] Bind admission to Ryser work and correct the public order limit

Confirmed contract failure

matrix.permanent.compute has the right stable mathematical postcondition, but its admitted envelope does not bound the work of its pinned backend.

SquareRationalMatrixRequest accepts every dense rational square matrix of order at most 32 with 256-digit scalar components. The permanent operation calls sympy.Matrix.per() directly. In the pinned SymPy 1.14.0, _per uses Ryser's formula by materializing every nonempty subset of the matrix columns and then for

Read the thread · 2026-08-27 · closed · 1 comment

[Differential geometry] Compute exact Laplace–Beltrami values on rational coordinate metrics

Parent gap / RFC

This is a focused follow-up to #2877, #2878, and #2885. Those issues establish the exact coordinate metric, rational partial derivatives, and covariant derivative, but none returns the scalar second-order operator determined by a supplied metric. Existing polynomial_field.scalar.laplacian.compute is the Euclidean, polyno

Read the thread · 2026-08-27 · open · 0 comments

[Bug]: Project unexpected operation failures through math.run

Priority P2

Area mcp

Component math.run transport projection and backend-owning math operations.

Observed behavior An audit reported that interval.expression.box_enclosure.compute raised ExceptionGroup: unhandled errors in a TaskGroup for a valid positive-domain logarithm. This exposes an SDK worker failure instead of a Jacobian result or typed error.

The exact positive-logarithm payload now succeeds on the current checkout through the MCP client at 1024-bit precision,

Read the thread · 2026-08-27 · closed · 2 comments

[Geometry] Compute exact intersections of bounded convex rational polygons

Parent gap / RFC

Exact rational geometry currently has:

  • geometry.segments.intersection.compute for two closed segments;
  • geometry.polygon.simple.decide and geometry.polygon.point.classify for one polygon;
  • geometry.points.compute.convex_hull for a canonical convex boundary; and
  • geometry.polygon.visibility_kernel.compute for the intersection of the interior half-planes derived from one simple CCW polygon.

None returns the exact closed intersection of two independently su

Read the thread · 2026-08-27 · open · 1 comment

[Hypergraphs] Compute bounded exact minimum vertex transversals

Parent gap / RFC

Erdős Problem #167 (Tuza's conjecture) compares the largest edge-disjoint triangle packing with the smallest triangle edge cover. Under the standard triangle-hypergraph reduction (V(H_G)=E(G)), (E(H_G)=\mathcal T(G)), a triangle edge cover is a vertex transversal of (H_G). The planned complete triangle family (#2809) makes that reduction available, but Jacobian has no operation that minimizes a vertex set meeting every edge of an arbitrary FiniteHypergraph.

This i

Read the thread · 2026-08-27 · closed · 1 comment

[Number theory] Compute exact least-prime-factor profiles on bounded intervals

Problem

Jacobian has scalar complete factorization and proposed interval profiles for (\omega(n)), squarefreeness, (\tau(n)), and the greatest prime factor (P^+(n)), but it has no source-complete table of the least prime factor (p(n)) across a finite integer interval. Repeated scalar factorization is not a substitute: it neither uses the natural segmented sieve nor establishes that every member of a declared interval was covered.

This is independent source demand, not an Erdős #

Read the thread · 2026-08-27 · closed · 1 comment

[Operation]: Decide bounded non-monochromatic vertex-colourability of a finite hypergraph

Parent gap / RFC

Erdős Problem #966 has a finite core: after forming a finite set A and its k-term arithmetic-progression hypergraph, decide whether every r-colouring of A makes some k-edge monochromatic, while a separate (k+1)-AP carrier checks the forbidden larger progression. The same exact relation consumes the word-cube combinatorial-line hypergraphs proposed in #2848 and ordinary interval AP hypergraphs in #2791. Current Jacobian exposes the carriers and generic logical kernels, but no

Read the thread · 2026-08-27 · closed · 2 comments

[Edge-coloured graphs] Construct monochromatic-clique candidate hypergraphs

Need

Resolved Erdős Problem #1015 packages a two-coloured complete graph into one finite candidate family before a caller chooses a packing: every monochromatic copy of K_t is a candidate block, and a vertex-disjoint selection leaves the desired remainder. Jacobian has an edge-colour-preserving one-embedding operation proposed in #2810 and a generalized exact-cover operation, but neither produces the complete, source-bound family of candidate vertex sets.

Repeated embedding calls canno

Read the thread · 2026-08-26 · closed · 1 comment

[Graphs] Construct bounded uniform-subset intersection graphs

Problem

Many finite extremal-set questions begin with the same carrier: vertices are all k-subsets of an n-element ground set, and adjacency records whether their intersection meets a caller-specified threshold. Erdős #83 is the n=4r, k=2r, t=2 conflict instance: an edge joins two subsets when their intersection has size < t, so a t-intersecting family is an independent set. The special cases include Kneser graphs (t=1) and Johnson-scheme threshold graphs.

Jacobian has generic

Read the thread · 2026-08-26 · closed · 1 comment

[Graphs] Construct bounded labelled hypercube graphs

Problem

The hypercube graph Q_n is a recurring finite carrier in extremal graph theory, coding theory, Boolean analysis, and discrete isoperimetry. Jacobian has generic graph invariants and transforms but no operation that constructs the exact labelled graph from its dimension. Agents therefore hand-author the 2^n bit-vector vertices and n 2^(n-1) Hamming-distance-one edges before they can compose ordinary graph operations.

A concrete source demand is the solved hypercube short-cycl

Read the thread · 2026-08-26 · closed · 1 comment

[Graph optimization] Compute a bounded graph’s exact minimum edge-path partition

Observed mathematical task(s)

Erdős problem #583 (Gallai's path decomposition conjecture) and current work on Eulerian, planar, bounded-treewidth, and dense graphs use the path number (p(G)): the minimum number of edge-disjoint simple paths whose union is (E(G)). For a supplied finite graph, obtaining the exact value and a realizing partition is a reusable optimisation step, independent of the conjecture’s universal bound.

Missing mathematical result

For one bounded labelled simple

Read the thread · 2026-08-26 · closed · 1 comment

The remaining reports are on the project's issue tracker.