Paper Citation Record · LEDGER

The Unreasonable Ineffectiveness of the Deeper Layers

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 39 inbound Pith citation observations for arXiv:2403.17887.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2403.17887 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 39 of 39 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T14:29:13.847195Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

5
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 15924654-a6e9-4bb0-a154-96407715c746 · inbound

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design cites this paper.

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design The Unreasonable Ineffectiveness of the Deeper Layers

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-23T06:57:40.285477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8278ec27-444a-4a53-b670-5bf17e096aa5 · inbound

Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs cites this paper.

Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs The Unreasonable Ineffectiveness of the Deeper Layers

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T14:29:13.847195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0879de0-20b5-4512-9560-2606bf0d14a3 · inbound

DarwinLM: Evolutionary Structured Pruning of Large Language Models cites this paper.

DarwinLM: Evolutionary Structured Pruning of Large Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T11:39:09.477311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2a0077f-9906-4d40-a7c2-332cf89e403b · inbound

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters cites this paper.

SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters The Unreasonable Ineffectiveness of the Deeper Layers

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T13:44:00.495709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aed77fdf-3f4e-48ae-b846-e454c23d7916 · inbound

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections cites this paper.

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections The Unreasonable Ineffectiveness of the Deeper Layers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T22:34:08.022953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d7c48b-a93a-4468-b8f5-be1252e80b84 · inbound

Void in Language Models cites this paper.

Void in Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:00.813610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65109521-ad22-4ee9-9643-971dc58d939b · inbound

Leveraging Stochastic Depth Training for Adaptive Inference cites this paper.

Leveraging Stochastic Depth Training for Adaptive Inference The Unreasonable Ineffectiveness of the Deeper Layers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:48:02.216637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4e4d684-fa8f-416f-b29c-851b1e4d532f · inbound

SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling cites this paper.

SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling The Unreasonable Ineffectiveness of the Deeper Layers

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:51:51.491364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2b52689-eac5-4880-893e-9e4446e96386 · inbound

GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching cites this paper.

GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching The Unreasonable Ineffectiveness of the Deeper Layers

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T22:53:11.013316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b716bc9a-db6d-4c36-bcd7-c917ef91e4cc · inbound

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling cites this paper.

GPAS: Accelerating Convergence of LLM Pretraining via Gradient-Preserving Activation Scaling The Unreasonable Ineffectiveness of the Deeper Layers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T22:21:09.909236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0a084e5-e6ef-4663-85d2-3565f95c0be8 · inbound

Towards Distributed Neural Architectures cites this paper.

Towards Distributed Neural Architectures The Unreasonable Ineffectiveness of the Deeper Layers

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T22:14:19.114883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39e6cb2-95ed-417a-99fd-7ee09908d0f3 · inbound

A Survey on Latent Reasoning cites this paper.

A Survey on Latent Reasoning The Unreasonable Ineffectiveness of the Deeper Layers

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:14:25.884327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4779f547-3305-4fa8-922a-a5d87963794a · inbound

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning cites this paper.

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning The Unreasonable Ineffectiveness of the Deeper Layers

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:39:00.502583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcab9834-a370-4cff-9f4f-0d1f01636d0d · inbound

Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers cites this paper.

Short-LVLM: Compressing and Accelerating Large Vision-Language Models by Pruning Redundant Layers The Unreasonable Ineffectiveness of the Deeper Layers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T10:55:18.132568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 428b471c-e54d-40c7-bb57-69bac7a49e01 · inbound

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models cites this paper.

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T05:11:11.524583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df68b59e-b75e-416b-9d0d-c110f7247e5c · inbound

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models cites this paper.

On the Limits of Layer Pruning for Generative Reasoning in Large Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:40:46.167908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e0df9383-f5c5-4323-bde1-0dd286d3095f · inbound

Inverse Depth Scaling From Most Layers Being Similar cites this paper.

Inverse Depth Scaling From Most Layers Being Similar The Unreasonable Ineffectiveness of the Deeper Layers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T04:07:45.518722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff7b1b89-f86b-40df-af12-51f254be6010 · inbound

Attention Residuals cites this paper.

Attention Residuals The Unreasonable Ineffectiveness of the Deeper Layers

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:39:04.388399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 05093803-5c9d-4837-b839-8b3b9182506b · inbound

When Does Sparsity Mitigate the Curse of Depth in LLMs cites this paper.

When Does Sparsity Mitigate the Curse of Depth in LLMs The Unreasonable Ineffectiveness of the Deeper Layers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T20:29:33.439034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33c3ed4-d16b-4b5c-9096-fdb75cea654a · inbound

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task cites this paper.

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task The Unreasonable Ineffectiveness of the Deeper Layers

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:16:07.468222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e8104843-579d-42a9-9d15-eb0b8db47ea3 · inbound

LASER: Low-Rank Activation SVD for Efficient Recursion cites this paper.

LASER: Low-Rank Activation SVD for Efficient Recursion The Unreasonable Ineffectiveness of the Deeper Layers

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T09:23:37.409033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 36982239-45d0-44d2-8e0a-541c046845e1 · inbound

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales cites this paper.

Variance Is Not Importance: Structural Analysis of Transformer Compressibility Across Model Scales The Unreasonable Ineffectiveness of the Deeper Layers

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:26:04.417968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation da4b0a3c-dd7c-472f-8b1e-611296fcf2c8 · inbound

Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking cites this paper.

Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking The Unreasonable Ineffectiveness of the Deeper Layers

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:41:06.430899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 968f2024-b415-4611-830c-e3e2d21054b6 · inbound

Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions cites this paper.

Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions The Unreasonable Ineffectiveness of the Deeper Layers

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-11T02:25:53.883150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9edb290a-8f87-4e97-beaf-00ab32135e20 · inbound

A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models cites this paper.

A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-29T23:04:01.068662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0f089641-195d-4c4e-863e-279db3fc46d7 · inbound

A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models cites this paper.

A Hamiltonian-Inspired Local-Operator Ansatz for Slimming Large Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T05:01:02.976226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b9f4ddb-81d9-427a-9268-c1049d67dde0 · inbound

Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling cites this paper.

Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling The Unreasonable Ineffectiveness of the Deeper Layers

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:55.034985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2c2190d2-c753-4317-80b6-fb56bc47b5c2 · inbound

Complementary Attention Head Pruning for Efficient Transformers cites this paper.

Complementary Attention Head Pruning for Efficient Transformers The Unreasonable Ineffectiveness of the Deeper Layers

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:49:18.756029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 906b38bd-28c8-4533-8690-63b81b2d6f74 · inbound

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think cites this paper.

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think The Unreasonable Ineffectiveness of the Deeper Layers

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-04T04:29:34.938693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 038e7b6e-7223-4dda-bee5-2689f8499486 · inbound

Tapered Language Models cites this paper.

Tapered Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:09:43.999154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bb2b8ee1-e747-4e0f-9231-b0b9414c71b2 · inbound

Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients cites this paper.

Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients The Unreasonable Ineffectiveness of the Deeper Layers

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-04T17:20:00.869307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 75daf596-2a9d-485b-bb1d-3b0c5e5ed129 · inbound

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry cites this paper.

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry The Unreasonable Ineffectiveness of the Deeper Layers

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-26T05:29:00.076990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 089336c5-735d-4e29-a588-97efa8dd67c0 · inbound

Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization cites this paper.

Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization The Unreasonable Ineffectiveness of the Deeper Layers

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T09:25:41.186898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation afafa4bd-10a8-460a-8c10-0b46a478daa9 · inbound

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield cites this paper.

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield The Unreasonable Ineffectiveness of the Deeper Layers

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-01T10:15:44.054375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b3ff6bd-0d27-4ead-bada-7607901cac3b · inbound

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield cites this paper.

CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield The Unreasonable Ineffectiveness of the Deeper Layers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T09:24:12.859247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 448ee395-7f79-4a6c-a86d-f39707d2bc37 · inbound

Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective cites this paper.

Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective The Unreasonable Ineffectiveness of the Deeper Layers

Reference 128

Resolution: unresolved; no resolver link, observed 2026-07-11T23:58:47.097757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db6df2d3-4bbb-45c9-9a50-b67f2d74f697 · inbound

Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models cites this paper.

Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T15:58:40.406682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a05f125-ea59-4a1e-9499-0f213ae44cec · inbound

Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text cites this paper.

Latent Communication Between Language Model Agents: Channels, Alignment, and the Limits of Text The Unreasonable Ineffectiveness of the Deeper Layers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T14:51:05.502290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2735368-4d99-448e-977c-6c8e1e2645b6 · inbound

Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders cites this paper.

Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders The Unreasonable Ineffectiveness of the Deeper Layers

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T03:15:58.833724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.