ArcGraft — GRID-HANDOFF-GRAFT-001 Rev A

ArcGraft Composition Matrix

How the Grid builds, combines, and owns AI competence. Each department model is a home base plus QLoRA adapters, served through ArcRouter, traceable through ArcLedger. 5 phases from a zero-cost first adapter to a Noema MoE. Doctrine: ArcTide, the Reversible Mind.

5
Phases
25
Techniques
15
Packages amended
14
Decisions
7
ArcTide invariants
8
Frontier bets
Phase 0 — Foundation (2–4 weeks, zero cost)
TaskScopeStatusGate
P0-01
Home base bake-off
Finish the Noema bake-off with GRAFT criteria: commercial license clear for derivative training; size family sharing one tokenizer; strong tool calling at 4-bit; healthy adapter/merge ecosystem; fits Rig 3 with KV cache room. Ratify D-GR-01.
BlockedESCALATE: D-GR-01
P0-02
Capture verification
Confirm ArcRouter port 4000 capture is intact and DATACLASS M0 labels exist for the corpus slice.
NextDATACLASS M0
P0-03
llama-server multi-LoRA on Rig 3
Stand up llama-server with multi-LoRA as a new ArcRouter destination. Per D-GR-06 (proposed: llama-server now, vLLM at next hardware tier).
NextUnblocked
P0-04
Department model sort worksheet
List every model each department uses today; classify as adapter candidate / sense / tool / frontier escalation.
NextUnblocked
P0-05
First QLoRA adapter
Train first QLoRA adapter (r=16) on one task class. 2–6 hours on Rig 3 RTX 3070s.
FutureP0-01 + P0-02
P0-06
Capacity benchmark
Measure tokens/sec, concurrency, memory on Rig 3 and a GTX 1660 for the home base at 4-bit. Replaces estimates with real numbers.
FutureP0-03
P0-07
ArcHub lineage schema for adapters
Extend lineage record: base hash, data ref, DATACLASS, recipe, eval, owner, license. Write first records.
FutureP0-01
P0-08
Structured decoding
Enable structured/constrained decoding for every local route that feeds a Surface object (R-23). Nearly free — fixes most format failures.
FutureP0-03
P0-09
QA-006 evaluation — exit gate
Run QA-006 on adapter route vs current route. Adapter must match or beat current local route on its task class at equal or lower cost. Lineage and ledger receipts must exist.
FutureP0-05
Phase 1 — First Attachments (1–2 months)
TaskScopeStatusGate
P1-01
Department adapter v1
First full department on home base + adapters. Proposed: Marketing (highest volume, clearest accept/reject history).
FutureP0 exit + D-GR-02
P1-02
Skill adapters
3–5 skill adapters mapped to that department's Curate tags; hot-swapped per request.
FutureP1-01
P1-03
Client brand-voice adapters
Brand-voice adapters for 2–3 clients. Ownership: client owns adapter files and lineage; Swift retains base, cores, pipeline, and cross-client learnings. Contract terms per A-11.
FutureP0 exit + D-GR-03 + legal
P1-04
ArcRouter adapter-aware routing
Route tuple expands: (base, adapter stack with strengths, steers, server, tier). Curate tags resolve to adapter stacks. Adapter IDs written to ArcLedger metadata.
FutureP0 exit
P1-09
ArcTrace training events
ArcTrace emits: tenant, DATACLASS, task class, department, route, input context ref, output, human edits (diff), final accepted version, outcome, reason. This data is the moat (FB-01).
FutureD-GR-13 (ESCALATE)
P1-10
Proof point report
Cost per task and quality vs old multi-model setup for the first department. Investor-grade evidence.
FutureP1-01
P1-11
Technique radar
Monthly intake of new methods (file 08 §8.4): Wire feed watching arXiv cs.CL/cs.LG, lab blogs, HF trending. Agent scores on Value/Cost/Fit/Phase. Winners get time-boxed experiments.
NextUnblocked
P1-12
ArcTide Experiment E-1 (round trip)
Write client style rules as graph nodes, train adapter, probe candidate rules back, compare with source. First test of the reversible-mind hypothesis.
FutureP1-03
Phases 2–4 summary
PhaseGoalKey new capabilityExit gate
P2
Merging and Judgment (2–4 mo)
Specialist fine-tunes per sub-skill; TIES/DARE merge into department cores; evolutionary merge search; DPO on ArcTrace approve/reject pairs; Noema Check v1; learned routing in shadow mode; all departments migrated.
Merged cores + DPO judgmentMerged cores beat adapters on QA-006; DPO measurably reduces revisions
P3
Absorption (4–8 mo)
Governed teacher roster with license clearance; FuseChat-style cross-family pipeline; vision projector for Design/Dev; RL with verifiable rewards; home-base upgrade drill (portability proof).
Cross-family fusion + visionFused model beats unfused home base; base-swap rehearsed end to end
P4
Consolidation (8+ mo)
Branch-Train-MiX: departments as experts in one Noema MoE; Noema Pocket (1–4B distill for Rigs 1+2 and edge); ArcSwarm packaging; ArcTide Experiments E-3 and E-4.
Noema MoE + PocketMoE vs routed cores decision; Pocket shipped
Technique Radar — R-01 to R-25
IDTechniqueValueCostWhenNotes
R-01Quantization (GGUF, AWQ, GPTQ; 4-8 bit)51NowPhase 0. GTX 1660: ≤4B comfortable, 7-9B tight. RTX 3070: ≤9B comfortable, 14B borderline.
R-02Multi-LoRA serving52NowPhase 0. llama-server on Rig 3. 500 adapters stored, served copies scale with traffic.
R-03QLoRA training52NowPhase 0-1. Rig 3 for ≤9B (2-6h). GTX 1660 marginal for 7-9B with Unsloth.
R-04Speculative decoding42NowPhase 1. Same-family small draft. Pocket serves double duty.
R-05Prompt/prefix caching41NowPhase 1. System prompt and brand context. Cheap latency and cost reduction.
R-06Steering vectors31NowPhase 1. Tone/trait dials in Surface. Coarse but near-zero cost.
R-07Embedding and reranker fine-tuning52NowPhase 1. Tiny models, train in minutes on any GPU. Measure with QA-004.
R-08Merging (TIES, DARE, SLERP, soups)41NowPhase 2. CPU merge on ArcHelm. 32 GB RAM handles models up to ~7B. mergekit initially.
R-09DPO / preference tuning53NowPhase 2. Small models on current rigs. ArcTrace accept/reject pairs are the data source.
R-10Learned routing (RouteLLM-style)42NowPhase 2. Shadow mode behind ArcRouter Selector per DR-3. Reduces frontier escalations.
R-11Evolutionary merge search43NowPhase 2. Overnight on ArcHelm + Rigs. QA-006 as fitness function.
R-12Test-time compute + verifier42NowPhase 2. Noema Check as verifier in the loop.
R-13Synthetic data pipelines43NowPhase 2. Augment sparse task classes.
R-14RL with verifiable rewards54Next tierPhase 3. Tests-pass for Dev; schema/process checks for Ops. Needs ArcProof.
R-15Knowledge fusion (FuseLLM/FuseChat)54Next tierPhase 3. Cross-family absorption. Requires teacher roster with license clearance (D-GR-10).
R-16Vision projector43Next tierPhase 3. Noema sees screenshots, mockups, PDFs, brand boards. Design + Dev departments.
R-17Prune + distill (Minitron-style)44Next tierPhase 4. Noema Pocket 1–4B from department cores. Rigs 1+2 and edge use.
R-18Branch-Train-MiX / upcycling45Next tierPhase 4. Departments as MoE experts. Requires next hardware tier.
R-19Sparse autoencoders (SAE) / interpretability54NowArcTide research lane from Phase 1. Strongest on small models. Supports tide-out (surfacing).
R-20Machine unlearning44LaterResearch lane. TIDE-I5 retraction. Immature; use steering/SAE suppression first.
R-21Continual learning (avoiding forgetting)43NowPhase 2 onward. Retrain cadence, replay sets, rollback rules. Adapters make this cheaper.
R-22Long-context / KV-cache compression32NowPhase 1. KV cache grows with context and concurrent users. Important at scale.
R-23Structured / constrained decoding51NowPhase 0. Nearly free. Fixes most Surface object format failures immediately.
R-24Federated fine-tuning34LaterResearch lane. Relevant for ArcNode on-prem client deployments.
R-25Watermarking / fingerprinting33NowPhase 3. Client and Swift adapter provenance. AuthenLoRA / dual-watermark approach.
ArcTide Doctrine — GRID-DOCTRINE-TIDE-001

Every piece of competence in the Grid exists in up to three states and can move between them under a ledger. Explicit (ArcGraph: rules, rubrics, exemplars, facts). Tacit (adapters and cores in ArcHub: fast, fluent, opaque). Title (ArcLedger receipt chain: provenance, contribution, ownership). Ratification pending D-GR-11.

TIDE-I1 — No orphan weights
Every tacit artifact links to its explicit sources and trace data. An adapter without lineage cannot be served.
TIDE-I2 — Graph is canonical for facts
Weights may hold skill; they are never the only holder of a fact. Facts used at answer time come from ArcGraph and records.
TIDE-I3 — Every crossing receipted
Consolidation, surfacing, retraction, transfer, and export each write ArcLedger receipts. No silent transitions.
TIDE-I4 — Surfaced knowledge is a candidate
Anything extracted from weights enters ArcGraph as a candidate and passes the Human Approval Gate before becoming canonical.
TIDE-I5 — Retraction propagates
Removing or correcting a graph node marks every dependent artifact stale. Interim: suppress at answer time. Final: retrain from corrected sources.
TIDE-I6 — Family neutrality
Every production skill must pass a portability test: recompiled from its explicit sources into a second model family, it reaches an agreed share of its original eval score.
TIDE-I7 — Title follows contribution
Receipts attribute contributions (client data, Swift process, teacher models, human reviewers) so ownership and licensing can be computed, not argued.
Rig capacity quick-reference
What fits where (4-bit quantization)
  • GTX 1660 (6 GB, Rigs 1+2, 24 cards): comfortable ≤4B; tight 7-9B (short context, single user, Unsloth); no 12B+. No bf16 (fp16 only, slower training). Embeddings, rerankers, evals, speculative drafts, Pocket inference.
  • RTX 3070 (8 GB, Rig 3, 5 cards): comfortable ≤9B; borderline 14B with Unsloth; no 30B+. QLoRA training (2-6h for 7B adapter). Multi-LoRA serving home base. Merge evaluation runs.
  • ArcHelm (CPU, 32 GB RAM, Rig 3 node): CPU merge jobs (any method ≤7B fits in RAM). Pipeline orchestration. Evolutionary search coordinator.
  • ArcNode (planned): 14B adapter training; local dev inference; leaf routing capture sink (D-AN-08 upgraded to required).
  • Cloud burst (D-GR-05): fusion training runs, full fine-tunes, MoE serving, large teachers. Per-run spend cap required.
  • D-GR-04 (ESCALATE): one 16-24 GB GPU unlocks 14B adapters comfortably, real concurrency, and vLLM. Timing aligned with ArcNode M0 pilot.
Frontier bets
IDBetFirst experimentKill criterion
FB-01
Process-trace training
Train on how agency work actually happens (drafts, edits, rejections, approvals) not just finished text. The moat is the data, which only Surface captures. Start immediately.
DPO adapter from ArcTrace accept/reject pairs on one task class (P2-04)No measurable reduction in revisions after two training cycles
FB-02
Self-compounding client adapters
Each client's adapter retrains automatically from their approved work with eval gates and one-click rollback.
Weekly automatic retrain for one client adapter in shadow modeQuality flat or declining over 6 cycles, or forgetting incidents
FB-03
Governed merge-on-demand
Compose a model per request from an adapter library with policy controls on which adapters may combine (tenant, DATACLASS, license).
Router-selected adapter blends for one department with a policy tableBlends never beat the best single stack
FB-04
Business-outcome evolution
Evolutionary merging scored on business results (approval rate, revisions avoided, client KPIs) instead of benchmarks.
One evolution run using QA-006 net value as fitnessFitness signal too noisy to rank candidates
FB-05
Verifiable lineage and title
Receipt chains for every dataset, teacher, merge and promotion; title computed from contribution. Patent search required before external claims.
Attribution report for one production adapter (ArcTide E-5)Attribution not reproducible across runs
FB-06
Cross-family Rosetta layer
One learned translator between model families' internal spaces so adapters transfer with little retraining.
Probe alignment of two small models on Swift tasks (relative-representation analysis)No usable alignment between small models of two families
FB-07
ArcTide — The Reversible Mind
Knowledge round-trips between graph and weights under a ledger. Graph as cross-family medium. Ledger as title. Partly written down in pieces; unified loop not found in literature. Patent search required.
ArcTide E-1 round trip (Phase 1)E-1 and E-2 both fail their pass signals twice
FB-08
Pocket as team member's double
Each engineer's ArcNode trains a personal adapter from their approved work, owned by them, usable across the Grid with receipts. Consent/contract terms required before production.
One volunteer's personal adapter on ArcNode with consent termsVolunteer finds it unhelpful or terms unworkable
Open decisions
For Charles — status as of 2026-10-18
  • D-GR-01 (BLOCKING Phase 0) — Foundation strategy. Recommendation: Option A (one home base, others as teachers). Option C allowed if bake-off shows a 10+ point QA-006 gap for Development.
  • D-GR-13 (BLOCKING Phase 1) — Where trace-derived training data lives. Resolve jointly with ArcHub D-AH-05 and ArcRouter port 4000 capture thread.
  • D-GR-06 (proposed) — llama-server now; vLLM at next hardware tier; Ollama stays for fixed pairings.
  • D-GR-08 (proposed) — Noema Check is never a component of the model it judges.
  • D-GR-09 (proposed) — Use mergekit now; replace with Grid-owned code in Phase 3.
  • D-GR-11 (proposed) — Ratify GRID-DOCTRINE-TIDE-001 (ArcTide) as a foundational doctrine.
  • D-GR-12 (proposed) — Package name ArcGraft; doctrine name ArcTide. Collision check pending before external use.
  • D-GR-02 (open) — First department for Phase 1. Proposed: Marketing; confirm with P0-04 worksheet data.
  • D-GR-03 (open) — Client adapter ownership terms. Requires legal review (contract clauses per A-11).
  • D-GR-04 (open) — First hardware upgrade: one 16-24 GB GPU, aligned with ArcNode M0 pilot.
  • D-GR-05 (open) — Burst cloud GPU policy for fusion and full fine-tunes. DATACLASS ceiling and per-run spend cap required.
  • D-GR-07 (open) — Long-run shape: single Noema MoE vs routed department cores. Decide on Phase 3-4 evidence.
  • D-GR-10 (open) — Teacher roster owner: one accountable reviewer for license clearance. Required before Phase 3.
  • D-GR-14 (open) — Finance as a sixth department. Carry from PKG-NOEMA-001; no change from this package.