Paper Citation Record · LEDGER

Characterizing Linear Alignment Across Language Models

As of 8 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2603.18908.

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

pith.paper-citation-record.v1
2603.18908 v4

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T22:20:23.676745Z

measured 27 of 27 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T19:59:45.160080Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T19:59:45.317164Z

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 95a0a283-8970-463a-a036-3aa3001dabfc · outbound

This paper cites Stealing Part of a Production Language Model.

Characterizing Linear Alignment Across Language Models Stealing Part of a Production Language Model

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d03f1e-d83a-4d1b-a285-aad2b93a2b60 · outbound

This paper cites The Platonic Representation Hypothesis.

Characterizing Linear Alignment Across Language Models The Platonic Representation Hypothesis

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8144ce5-5ca0-4800-8681-0df9611f033c · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3fa27b0-1d04-474c-83e2-807814780d75 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f725a7-2d6b-4eae-8545-1a5511c51c34 · outbound

This paper cites score": <1-10>,.

Characterizing Linear Alignment Across Language Models score": <1-10>,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b3dd573-40da-4eb8-87fe-2c833a87df39 · outbound

This paper cites In fact, a dog’s sense of smell is up to 1,000 to 10,000 more sensitive than a human’s.

Characterizing Linear Alignment Across Language Models In fact, a dog’s sense of smell is up to 1,000 to 10,000 more sensitive than a human’s

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b144c1f8-8065-417c-849b-3e4612a8236f · outbound

This paper cites To build the bridge we need construction equipment, including drills and jackhammers.

Characterizing Linear Alignment Across Language Models To build the bridge we need construction equipment, including drills and jackhammers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f775d29-2be1-4e50-b298-07607bafde2b · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5616bd02-5404-41ce-b195-28b8fa78510f · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7c9aac2-0e7e-4221-9f5a-09694f263f09 · outbound

This paper cites LM-head-ready.

Characterizing Linear Alignment Across Language Models LM-head-ready

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c1ebc2-fe7e-4f35-9159-cc32449d7f54 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3048cc36-01ff-4835-a643-27b8f13d2a3e · outbound

This paper cites This can be imple- mented as homomorphic linear aggregation over samples: Enc(Z ⊤ A ZB) = N ∑ k=1 ZA[k, :]⊤ ·Enc(Z B[k, :]).

Characterizing Linear Alignment Across Language Models This can be imple- mented as homomorphic linear aggregation over samples: Enc(Z ⊤ A ZB) = N ∑ k=1 ZA[k, :]⊤ ·Enc(Z B[k, :])

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712e912b-9a14-4a28-893f-0e30e927227b · outbound

This paper cites 32 Deployment of W∗.Unlike traditional outsourced training schemes, PARTYB retains the learned map (W∗, b∗) and uses it locally during inference.

Characterizing Linear Alignment Across Language Models 32 Deployment of W∗.Unlike traditional outsourced training schemes, PARTYB retains the learned map (W∗, b∗) and uses it locally during inference

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78170a41-77dc-46fa-a72e-7f5733df7979 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f27af6f-5be1-4aba-b9ee-f5a7d88cdefc · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 831ccbad-4dfa-4692-8221-602575b53fdb · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcca4d71-a12d-4c98-8ab0-e9b46870cf54 · outbound

This paper cites Argmax-only outputs.To reduce leakage about (V, c) through black-box queries, the protocol may return only a predicted class label via encrypted argmax rather than full logits.

Characterizing Linear Alignment Across Language Models Argmax-only outputs.To reduce leakage about (V, c) through black-box queries, the protocol may return only a predicted class label via encrypted argmax rather than full logits

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a38e26c-57ce-4fe5-9028-0cf5f38cfa47 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b9c7d1-7468-4bab-a850-b2e401206e82 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a3a1ff-f9f6-48ed-95e3-2259ae5261fb · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2af04060-9515-4044-a7a4-e3f03a8855f7 · outbound

This paper cites Output:Predictionyrevealed to PARTYB.

Characterizing Linear Alignment Across Language Models Output:Predictionyrevealed to PARTYB

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d007c5d-c1e4-4921-966e-37da11d7a866 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d3879be-8a0b-4d56-bd3b-6a28901ce4f8 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 582b7e57-9d3c-4500-92ac-b3901de9bf60 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf572771-b4cf-43d1-b8ab-4dbe8e3111f6 · outbound

This paper cites an unresolved cited work.

Characterizing Linear Alignment Across Language Models Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71ba532b-de9d-434e-9bf0-768d2a0a41c1 · outbound

This paper cites 35 I Extended Related Works In this section we include additional research related to security and machine learning.

Characterizing Linear Alignment Across Language Models 35 I Extended Related Works In this section we include additional research related to security and machine learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6dfd675c-24a0-409f-bc3c-cc13009b2d4b · inbound

How Far Do Simple Transformations Translate Across Text Embedding Models? cites this paper.

How Far Do Simple Transformations Translate Across Text Embedding Models? Characterizing Linear Alignment Across Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T19:59:45.323491Z

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.