Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library

• URL: http://arxiv.org/abs/2608.11767v1
• Date: Wed, 12 Aug 2026 08:10:01 GMT
• Title: Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library
• Abstract summary: When a language model answers an interventional question, the computation it must perform depends on the type of evidence the query requires.<n>We report a decoupling in how a transformer organizes causal knowledge: slot-by-type structure induced by type-level supervision organizes routing, yet remains decoupled from answer readout.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When a language model answers an interventional question, the computation it must perform depends on the type of evidence the query requires. We report a decoupling in how a transformer organizes causal knowledge: slot-by-type structure induced by type-level supervision organizes routing, yet remains functionally decoupled from answer readout. We establish this with a typed mechanism library -- discrete mechanism slots partitioned by evidence type, auditable at the state level -- on a causal-world benchmark with exact interventional ground truth, under a frozen protocol, at two scales (22.6M and 125M). Four preregistered findings. (i) Origin. Slot-by-type organization is induced by type-level supervision: absent in architecturally identical unsupervised controls, not buyable by content-free gating labels, and statistically attributable to the supervision signal, replicating at 125M under a powered preregistered protocol (all nine cells passed). (ii) Boundary. The induced structure is a typed routing index with a sharp routing/readout boundary: slot codes scaffold routing but do not drive answer readout ($|Δ\hat{y}| \le 3.4\times10^{-6}$, zero collateral, three seeds, stable across a 5.6x scale window) -- we therefore make no behavioral-editability claim. (iii) Cost. The structure is free: LM quality matches a parameter-matched monolith within 0.0082 nats. (iv) Trust. The library state is exactly local under edit and bit-exactly revertible -- 250 single-edit and 1,000 stacked reverts per seed, zero failures. We further find that the unsupervised null itself moves with scale, so comparisons reusing a null calibrated at one scale may be confounded at another. Every claim is tied to a preregistered, machine-checkable criterion archived before the data it governs; the full audit trail, including one criterion we failed and how the frozen protocol handled it, is released as an appendix.

Related papers

• FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs [13.55424508650495]
  FaultLens is a method for learning compact behavioral test suites while preserving an auditable connection to executed evidence.<n>It executes a rich probe domain once, stores the fault-probe kill relation as a sparse outcome cache, and learns probe orderings only from earlier program generations.<n>We evaluate twenty generated operational policies across four environments, ten execution seeds, 1,200 measured run summaries, 2,160 controlled program transformations, and 4,120,200 executed program-probe pairs.
  arXiv  Detail & Related papers  (2026-08-27T07:37:28Z)
• Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol [3.202978695204522]
  Language-model agents can improve after failure or carry text across episodes without revising what counts as success.<n>We evaluate CMB-0.1 on twelve cross-domain cases and four arms.<n>No model trial satisfies all five conditions, but this zero does not establish general capability absence.
  arXiv  Detail & Related papers  (2026-08-21T04:21:28Z)
• Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release [0.0]
  We submit the complete pipeline -- detect, localize, and release -- to a fully preregistered stress test on a 25.7M transformer.<n> Interventions at observation-evidence channels of mid layers restore target behavior on otherwise-suppressed worlds.<n>Gating fails out of distribution: a detector calibrated to trigger on zero out-of-distribution calibration worlds triggers on 6.9-7.3% of held-out in-distribution generations and on zero of the 2,400 held-out generations that actually need it.
  arXiv  Detail & Related papers  (2026-08-12T09:04:54Z)
• Runtime Observability for Heterogeneous Attention Memory [20.158719055939383]
  We give a runtime observability contract that covers all four memory classes with three operators.<n>We compose the per-stage stack into an executable request-level risk ledger.
  arXiv  Detail & Related papers  (2026-08-06T10:41:50Z)
• The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents [0.0]
  We present an agent instrument built so that verification is structural rather than post-hoc.<n>Every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached.<n>We report a clean, single-variable result on a failure every long-horizon agent suffers.
  arXiv  Detail & Related papers  (2026-08-04T15:10:37Z)
• Semantic Drift in Bug Resolution: How Behavioral Signals Propagate from Reports to Tests and Patches [18.727291516223115]
  Desc2Fix is a framework for measuring semantic alignment between bug reports, triggering tests, and developer-written fixes.<n>We analyze 2,857 report-test-patch triplets from Defects4J and SWT-Bench using GPT-4o and DeepSeek-Chat.
  arXiv  Detail & Related papers  (2026-07-20T22:32:23Z)
• Closed-Loop Control with Rule-Aligned Small Language Models and Multi-Agent Self-Correction [17.527470001317685]
  This work investigates whether a compact Small Language Model (SLM) can be retrained for control reasoning and embedded in a validator-guided correction loop.<n>In randomized thermal-control simulations (30 experiments with 500 steps each), the framework achieves 91.5% average action-alignment accuracy.<n>Under symbolic re-mapping, it maintains a 95% in-range rate, indicating robust physical regulation despite reduced token-level agreement.
  arXiv  Detail & Related papers  (2026-06-24T13:49:01Z)
• Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization [25.540859911959885]
  Autoformalization (AF) asks a model to translate informal mathematical or logical reasoning into a formally checkable object.<n>We introduce a reference-free proxy-judge framework for AF that replaces gold-standard matching with a vector of per-axis property checks.<n>Across seven formalization backbones on miniF2F, ProofNet, e-SNLI, and ProntoQA, refinement consistently lifts Pass Rate over the single-shot ICL baseline.
  arXiv  Detail & Related papers  (2026-06-08T12:57:09Z)
• TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent Memory [22.85129722207174]
  We show that contradiction resolution is write-time control and make the missing contract explicit.<n> TOKI types the fourjudicats as one family of bitemporal operators over a dual-row schema.<n>A verdict matrix over eight systems localizes the gap: every baseline that keeps a language-model judge on the write path admits at least one of three write-time anomalies.
  arXiv  Detail & Related papers  (2026-06-04T14:46:52Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• From Admission to Invariants: Measuring Deviation in Delegated Agent Systems [0.4929694290403903]
  We show that enforcement-based governance is unable to determine whether an agent behavior remains within the admissible behavior space A0 established at admission time.<n>We prove an information-theoretic impossibility for enforcement-based monitoring and show IML detects admission-time drift with provably finite detection delay.
  arXiv  Detail & Related papers  (2026-04-19T16:19:57Z)
• Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge [0.0]
  We call this CAR: retrieving the currently active authority for a semantic anchor q, that is, front(cl(A_k(q))).<n>We evaluate three real-world datasets: security advisories, SCOTUS overruling pairs, and FDA drug records.<n>A GPT-4omini experiment shows RAG produces explicit "not patched" claims for 39% of queries where a patch exists.
  arXiv  Detail & Related papers  (2026-04-15T23:56:35Z)
• Breaking the Illusion of Identity in LLM Tooling [0.0]
  No existing mitigation provides a systematic deployable constraint set output register.<n>This paper proposes seven outputside rules, each targeting a documented linguistic mechanism.
  arXiv  Detail & Related papers  (2026-04-08T09:15:14Z)
• Reliable Control-Point Selection for Steering Reasoning in Large Language Models [28.288321095634128]
  Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models.<n>However, constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states.<n>We show that current methods detect these behaviors through keyword matching in chain-of-thought traces, implicitly assuming that every detected boundary encodes a genuine behavioral signal.<n>We develop a probabilistic model that formalizes intrinsic reasoning behaviors as events with context-dependent trigger probabilities, and show that unstable boundaries dilute the steering signal.
  arXiv  Detail & Related papers  (2026-04-02T14:48:56Z)
• Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning [18.75349680577575]
  SSLogic is a framework for continuous family evolution with controllable difficulty.<n>Training on SSLogic-evolved data yields consistent gains over the seed baseline at matched steps.
  arXiv  Detail & Related papers  (2026-01-23T13:26:01Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.