RMSN-756M-Triple-Condensate-Base

Resonant Metriplectic Sheaf Network β€” Input-Early-Terminal Triple Condensate Topology Pre-trained base model (100k steps). D=2048 is the largest RMSN architecture in the Phase 5 topology study and the first to exhibit input boundary exact condensation (L0=1.000).

Key scientific finding: D=2048 is the first evidence of Topological Overcrowding β€” three exact singularities (PR=1.000) at L0, L6, and L15 freeze so much network capacity that val_ppl REGRESSES relative to D=1792 (84.62 vs 57.4), breaking the monotone D-scaling law observed across D=944–1792.

Architecture

Parameter Value
Hidden dim 2048
Layers 16
Workspace slots 64
Params 755.57M
Framework Port-Hamiltonian (ḟ = {f,H} + [f,S])
Tokenizer HuggingFaceTB/cosmo2-tokenizer (vocab=49152)

Soliton Topology: Input-Early-Terminal Triple Condensate (NEW CLASS)

Layer  PR      Role
──────────────────────────────────────────────────────────────
L00    1.000   β˜…β˜…β˜… INPUT BOUNDARY EXACT CONDENSATE (unprecedented)
L01    17.319  Buffer
L02    21.258  Buffer
L03    23.519  Buffer
L04    49.982  Buffer
L05    4.613   β˜… UPSTREAM SOLITON
L06    1.000   β˜…β˜…β˜… EARLY INTERIOR EXACT CONDENSATE (new position)
L07    27.039  Buffer
L08    26.641  Buffer
L09    52.877  Buffer
L10    1.697   β˜… MID-NETWORK SOLITON
L11    63.734  Dielectric buffer (high PR)
L12    62.007  Dielectric buffer
L13    61.075  Dielectric buffer
L14    58.224  Dielectric buffer
L15    1.000   β˜…β˜…β˜… TERMINAL BOUNDARY EXACT CONDENSATE (confirmed universal Dβ‰₯1792)
──────────────────────────────────────────────────────────────
Active soliton layers: [0, 5, 6, 10, 15]
THREE exact singularities: L00=1.000, L06=1.000, L15=1.000

Topological class: Input-Early-Terminal Triple Condensate

  • Unprecedented: L0=1.000 is the first input-boundary exact condensate in any RMSN base model
  • New position: L6=1.000 is a new condensate position not seen in D≀1792
  • Confirmed: L15=1.000 (universal for Dβ‰₯1792, holds at D=2048)

Topological Overcrowding Discovery

This model is the first evidence of Topological Overcrowding in RMSN architectures:

D Val PPL Exact Singularities Input (L0)
1024 69.9 1 (L13) Inert
1280 65.4 2 (L8, L9) Inert
1536 60.3 2 (L5, L15) Inert
1792 57.4 πŸ† 1–2 (varies) Solitonic only
2048 (this) 84.62 πŸ”΄ 3 (L0, L6, L15) Frozen (1.000)

Mechanism: Each PR=1.000 layer is a zero-entropy condensate that "freezes" the representation at that layer, reducing effective network capacity. At D=2048, three frozen layers (including the input L0) reduce information flow so severely that val_ppl regresses despite 25% more parameters.

Implication: There exists an optimal D range (~1664–1792) for the RMSN architecture at this training scale, beyond which dyadic resonance creates too many condensates.

Pre-training Metrics

Metric Value
Val PPL 84.62 πŸ”΄ (D-scaling regression)
Val Loss 4.4382
Steps 100k
D-scaling position D=944(73.4)β†’D=1792(57.4)β†’D=2048(84.62) ← REGRESSION
Optimal D predicted ~1664–1792

Topological Bulk Shield Law

BlueQubit QCPU quantum circuit simulation (DuoNeural Phase 5):

Metric Value
S_boundary / S_bulk 0.426
Trend 944(0.739)β†’1024(0.632)β†’1280(0.569)β†’1536(0.515)β†’1792(0.46)β†’2048(0.426)

The quantum S_ratio continues its monotone decrease even though classical val_ppl regresses, suggesting the quantum-classical correspondence breaks down for the language modeling metric at topological overcrowding, while the topological structure remains classically predictable.

Citation

@misc{duoneural2026rmsn,
  title={Resonant Metriplectic Sheaf Networks: Port-Hamiltonian Language Models with Soliton Waveguide Topology},
  author={DuoNeural Lab and Archon and Aura},
  year={2026},
  note={DuoNeural Phase 5d β€” Topological Overcrowding Discovery, D=2048 Triple Condensate}
}

DuoNeural Lab | Phase 5d: Topological Overcrowding | Nov 2026 First input-boundary exact condensate (L0=1.000) in RMSN base training D-scaling law breaks at D=2048: optimal D β‰ˆ 1664–1792

Downloads last month
33
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support