Paper Citation Record · LEDGER

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 15 inbound Pith citation observations for arXiv:2312.13558.

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

pith.paper-citation-record.v1
2312.13558 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T11:28:42.485667Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T10:09:43.986675Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 1a557266-7cd3-4818-929d-f9a28db54faa · inbound

Holmes: A Benchmark to Assess the Linguistic Competence of Language Models cites this paper.

Holmes: A Benchmark to Assess the Linguistic Competence of Language Models The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-24T02:08:45.125550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation af495976-c665-41ef-8997-8bd30f57575f · inbound

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives cites this paper.

Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T11:28:42.485667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e2db77c-59c2-454c-88a2-a9bbadb71cc0 · inbound

DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer cites this paper.

DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:27:21.948988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef59a31-7451-4859-a02a-71bf4f207e68 · inbound

ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations cites this paper.

ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:20:43.477837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 586d5a36-5a80-422b-b19e-72f3bccac425 · inbound

Accelerating Attention with Basis Decomposition cites this paper.

Accelerating Attention with Basis Decomposition The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T12:54:34.403786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 160edf2d-14ab-4677-931e-5f21e2af6606 · inbound

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction cites this paper.

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:55:26.261039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 21d97fdc-4926-4c70-909e-58e785e1a56a · inbound

Aletheia: Gradient-Guided Layer Selection for Efficient LoRA Fine-Tuning Across Architectures cites this paper.

Aletheia: Gradient-Guided Layer Selection for Efficient LoRA Fine-Tuning Across Architectures The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T18:38:07.540451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cd6a969c-9cea-467c-874a-85fd88589ab9 · inbound

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing cites this paper.

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:06:03.399282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 102e7ebf-6925-4613-bdb5-6a5c28879496 · inbound

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders cites this paper.

Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-10T02:53:29.665167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1d62e62e-e111-48e5-b522-7b82ad18b756 · inbound

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations cites this paper.

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:51:08.275346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 106981ff-1622-45a7-85b3-5da685e54421 · inbound

Importance-Guided Basis Selection for Low-Rank Decomposition of Large Language Models cites this paper.

Importance-Guided Basis Selection for Low-Rank Decomposition of Large Language Models The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:56:06.753942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a04bfebd-990e-4608-ba9a-0035de6f642b · inbound

Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space cites this paper.

Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T20:39:00.205138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 12e66391-dca5-4672-901e-7fc20250cc06 · inbound

Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining cites this paper.

Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:49:49.889232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a0902e3e-4c6c-404d-833d-27e15b5c0dfb · inbound

Tapered Language Models cites this paper.

Tapered Language Models The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:09:43.988645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation abfa1dc4-98ec-4c41-a36e-5dbf0a6d17c5 · inbound

SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text cites this paper.

SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Reference 166

Resolution: unresolved; no resolver link, observed 2026-08-02T13:37:02.180545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.