Metraipolis › archive › dc_1973e08ac300
Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It — arXiv:2609.16183
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16183
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:23:23.043Z
- SHA-256 of the archived text
29567736f3e07df7bf9d9c6c29ea2ba7bd871d2e8d3e2c1e6828d92220cf9ac0- Stable URL of this page
https://metraipolis.com/documento/dc_1973e08ac300
How to cite
Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It — arXiv:2609.16183 — arXiv (en), https://arxiv.org/abs/2609.16183 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1973e08ac300 (Metraipolis archive dc_1973e08ac300, sha256 29567736f3e07df7bf9d9c6c29ea2ba7bd871d2e8d3e2c1e6828d92220cf9ac0)
BibTeX
@misc{dc1973e08ac300,
title = {Anatomy of Associative Recall in Fixed-State Recurrences: A Matched-State Decomposition, an Interference Wall, and a Curriculum That Breaks It — arXiv:2609.16183},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16183},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1973e08ac300; sha256 29567736f3e07df7bf9d9c6c29ea2ba7bd871d2e8d3e2c1e6828d92220cf9ac0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16183. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fixed-state recurrences--linear attention and state-space models--are reported to lag behind attention on associative recall, but whole-architecture comparisons cannot say which ingredient is responsible. We decompose masked multi-query recall at a fixed state budget along three single-knob axes: a short causal convolution, the transition structure (rank-1 delta rule vs. diagonal), and decay. The convolution dominates (~+0.5 recall in both families under matched training): comparisons that pit convolution-free cells against a convolution-equipped Mamba measure the missing convolution, not the recurrence. The rank-1 transition beats its diagonal ablation by +0.19/+0.32 at 16/32 pairs, but the margin shrinks to +0.03 once both cells carry the convolution, and a state-matched Mamba-2 ties the unarmed rank-1 cell: no class claim survives. Cells that solve 32-pair recall degrade gracefully with load yet fall to chance retrieving 4 pairs from a distractor haystack--flat across lengths and transitions. Interference under sparse supervision, not capacity: a distance curriculum takes the unchanged architecture from 0.021 to 1.000. Training is a lock-in lottery--a seed either locks in or does not--and the curriculum is the lever. Lock-in rises from 1/10 to 7/10 (p=0.02); dense supervision adds nothing; at L=256 a shaped ramp reopens a boundary the uniform curriculum cannot (4/5 vs. 0/9); and at L=512, where the ramp collapses (0/6), gating it on measured accuracy locks in 6/6 (p=0.001). Bidirectional denoiser cells, reading the query before the haystack, show no measurable advantage over causal training (ten seeds), and collision-key retrieval needs two layers. Arming for recall is free on an S_5 state-tracking guardrail--the armed cell is significantly better at every depth (p<=0.0044). These replace "recurrent models are bad at recall" with a measured decomposition and two cheap interventions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.16183 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T18:32:32.885Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).