Paper Citation Record · LEDGER

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 24 inbound Pith citation observations for arXiv:2203.05482.

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

pith.paper-citation-record.v1
2203.05482 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:24:30.373901Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T15:37:20.456341Z

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 c1ab5fe7-1a51-47e5-867c-1d8df37510fb · inbound

Flamingo: a Visual Language Model for Few-Shot Learning cites this paper.

Flamingo: a Visual Language Model for Few-Shot Learning Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 128

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T04:22:30.361878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aff079c3-78f4-40fa-ba7d-ce901866992b · inbound

CoCa: Contrastive Captioners are Image-Text Foundation Models cites this paper.

CoCa: Contrastive Captioners are Image-Text Foundation Models Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T10:53:08.469412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7275cc95-6bd5-4e0c-99b9-d984564b938a · inbound

Editing Models with Task Arithmetic cites this paper.

Editing Models with Task Arithmetic Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 106

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T08:09:13.238439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 10fbb273-5df5-4443-8a26-25068dfa7cb6 · inbound

A Roadmap to Pluralistic Alignment cites this paper.

A Roadmap to Pluralistic Alignment Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 295

Resolution: verified exact; arxiv_id, observed 2026-05-16T14:37:53.522897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b54aedf5-e7ea-4316-8240-bb36358a5c6f · inbound

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques cites this paper.

Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 164

Resolution: unresolved; no resolver link, observed 2026-08-06T16:24:30.373901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21270a1-15ce-42d1-a7d7-63d044765785 · inbound

Clinical Semantic Intelligence (CSI): Emulating the Cognitive Framework of the Expert Clinician for Comprehensive Oral Disease Diagnosis cites this paper.

Clinical Semantic Intelligence (CSI): Emulating the Cognitive Framework of the Expert Clinician for Comprehensive Oral Disease Diagnosis Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T15:42:59.121277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0734622-a6e7-4d73-9526-3974273a12ca · inbound

DivMerge: A divergence-based model merging method for multi-tasking cites this paper.

DivMerge: A divergence-based model merging method for multi-tasking Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-05T11:59:12.481134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba12cc5c-971f-4e97-826e-7e6d1e0a4465 · inbound

EmbeddingGemma: Powerful and Lightweight Text Representations cites this paper.

EmbeddingGemma: Powerful and Lightweight Text Representations Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-15T12:07:21.039250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fc28890-c1c8-498b-9bac-03023aa2e168 · inbound

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts cites this paper.

Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:56:11.358483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5ede85db-3bcc-4e35-b00f-a921b196280e · inbound

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies cites this paper.

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-12T09:21:26.123916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 531a884d-f3f7-4f74-86ac-d81d393a44c2 · inbound

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies cites this paper.

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:06:23.820477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 684d6332-214a-4d01-af2a-91185d85dc5e · inbound

BoostLoRA: Growing Effective Rank by Boosting Adapters cites this paper.

BoostLoRA: Growing Effective Rank by Boosting Adapters Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:06:27.691011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e97c16e2-f50f-4174-9595-c257b4fb0a60 · inbound

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning cites this paper.

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:47:58.481093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 89894934-1197-4aa9-9405-8de1a73baf6f · inbound

TaDA: Calibrated Probe Gating for Task-Domain LoRA Merging cites this paper.

TaDA: Calibrated Probe Gating for Task-Domain LoRA Merging Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T08:36:48.660733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bd86e585-fe01-4a9e-9c15-eebaabec7771 · inbound

Recoverable but Not Stationary:Local Linear Structures in Weights and Activations cites this paper.

Recoverable but Not Stationary:Local Linear Structures in Weights and Activations Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T04:27:37.358053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 75c94ad7-f8fb-4c72-932e-a3b685627ad8 · inbound

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs cites this paper.

Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T19:41:48.225019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ee8b44-5d6d-489b-8557-c56ab1b289dd · inbound

Persona Cartography: Charting Language Model Personality Traits in Weight Space cites this paper.

Persona Cartography: Charting Language Model Personality Traits in Weight Space Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 73

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:37:20.457650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f815908f-4f04-4d3e-ab0d-1a2d17958f11 · inbound

AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning cites this paper.

AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T00:14:56.914549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ab159e-1da9-40c1-bcf6-46bc1e95350d · inbound

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers cites this paper.

First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T19:55:53.887920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f50fbd0e-7592-4ca3-aabc-cc99e6d75619 · inbound

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification cites this paper.

Unlearning as Distribution Restoration: A Controlled Counterfactual Study, a Validated Selective Screen, and the Limits of Oracle-Free Certification Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T14:11:43.526214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad9b149-7465-4141-bb3f-3cd8cf177929 · inbound

Making Open-Source Text LLM Watermarks Durable Against Merging cites this paper.

Making Open-Source Text LLM Watermarks Durable Against Merging Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T14:26:15.102901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b915df-8103-4827-adaa-b912a66c2bc5 · inbound

TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging cites this paper.

TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T09:12:24.803667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c752d6-8a86-4e08-8f51-08fabdd1b411 · inbound

FORGE-plus: Force-Budgeted Recovery for Contact-Rich Assembly with a Frozen LLM Supervisor cites this paper.

FORGE-plus: Force-Budgeted Recovery for Contact-Rich Assembly with a Frozen LLM Supervisor Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T08:12:03.889873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1495071b-1964-4f29-b086-b939dc748415 · inbound

Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition cites this paper.

Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T23:38:26.034943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.