<?xml version="1.0" encoding="UTF-8"?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-11-20T19:45:35Z</responseDate>
  <request verb="GetRecord" identifier="oai:lifeofresearch.com:229" metadataPrefix="oai_dc">https://lifeofresearch.com/oai2</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:lifeofresearch.com:229</identifier>
        <datestamp>2026-11-15T11:05:38Z</datestamp>
        <setSpec>type:preprint</setSpec>
        <setSpec>openaire</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
        <dc:title>A Relocated Dependency Is Not a Vanished One: What the Neural-Cellular-Automaton Result on Integer Multiplication Shows About Long-Range Dependency, Why the Neural GPU Line Already Bounds It, and the Controls That Would Separate Locality, Supervision and Carry Coverage</dc:title>
        <dc:creator>Pranay Mahendrakar</dc:creator>
        <dc:subject>integer multiplication</dc:subject>
        <dc:subject>length generalization</dc:subject>
        <dc:subject>long-range dependency</dc:subject>
        <dc:subject>neural cellular automata</dc:subject>
        <dc:subject>algorithm learning</dc:subject>
        <dc:subject>carry propagation</dc:subject>
        <dc:subject>transformers</dc:subject>
        <dc:subject>circuit complexity</dc:subject>
        <dc:description>(c) 2026 Pranay Mahendrakar. Licensed under CC BY 4.0.
Life of Research
Multi-digit multiplication is a standing failure case for neural sequence models, and a 2025 reverse-engineering study traced the failure of standard fine-tuning to long-range dependencies that the model never learns. A 2026 paper rejects that diagnosis: it lays two binary integers out as an outer-product grid, trains a 321-parameter neural cellular automaton on single update steps, and reports exact products up to 4,096 bits after training on 2 to 6 bits, which it reads as proof that the long-range dependency was a mirage of the chosen representation and architecture. In this analysis the author reviews and synthesises published results to show that the two papers are mostly not in conflict, because &quot;long-range dependency&quot; names three different things. The functional dependency of a high product bit on many input bits is a property of multiplication under any encoding; the reach of a single update step is a property of representation and architecture, and the grid removes it; the number of sequential steps is the price of that removal, and the automaton pays it, taking about n steps for n-bit operands. The paper then argues that the published record already bounds the mirage claim. Local, iterated networks learned binary multiplication from input-output pairs alone in 2015, including a one-dimensional variant that reached 2,000 bits from 20; the same line failed on long carry chains that uniformly random test inputs almost never contain; and on both sides of the dispute, most of the reliable successes supervise intermediate states. The paper consolidates the measured values in Table 1 and Figure 1, states an attribution procedure as Algorithm 1, and specifies six controls, including a carry-adversarial test set and an end-to-end-trained automaton, that would separate locality, supervision and carry coverage.</dc:description>
        <dc:publisher>Life of Research</dc:publisher>
        <dc:date>2026-11-15</dc:date>
        <dc:type>info:eu-repo/semantics/preprint</dc:type>
        <dc:identifier>https://lifeofresearch.com/preprints/229</dc:identifier>
        <dc:identifier>https://doi.org/10.5281/zenodo.24235210</dc:identifier>
        <dc:language>eng</dc:language>
        <dc:relation>https://lifeofresearch.com/preprints/229/files/250/a-relocated-dependency-is-not-a-vanished-one.pdf</dc:relation>
        <dc:format>application/pdf</dc:format>
        <dc:rights>https://creativecommons.org/licenses/by/4.0/</dc:rights>
        <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>