Paper Citation Record · LEDGER

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

As of 10 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 4 inbound Pith citation observations for arXiv:2501.15556.

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

pith.paper-citation-record.v1
2501.15556 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:26:11.903685Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T19:55:52.417363Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T16:49:58.057648Z

Reference resolution

43 of 43 outbound references displayed

verified exact1
verified fuzzy24
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 486df368-2ddc-4efd-b476-b47eb9c754d6 · outbound

This paper cites Qwen Technical Report.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Qwen Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.698242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed707237-6e6e-4032-aa6f-b8bbeb133d5e · outbound

This paper cites An introduction to the geometry of stochastic flows.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning An introduction to the geometry of stochastic flows

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.562997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bac9eeaa-23ad-400b-8e3a-0ceee9d7fe4f · outbound

This paper cites Gradient-based Bi-level Optimization for Deep Learning: A Survey.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Gradient-based Bi-level Optimization for Deep Learning: A Survey

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.709561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e37390be-1692-455f-a7a1-4498c8a91261 · outbound

This paper cites Gradnorm: Gra- dient normalization for adaptive loss balancing in deep multitask networks.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Gradnorm: Gra- dient normalization for adaptive loss balancing in deep multitask networks

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.549055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1f5a1101-34a6-47db-9988-354b8f9a166f · outbound

This paper cites Just pick a sign: Optimizing deep multitask models with gradient sign dropout.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Just pick a sign: Optimizing deep multitask models with gradient sign dropout

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.534135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8871ea8-a030-4d93-88da-02395cec63b7 · outbound

This paper cites Order matters in the presence of dataset imbalance for multilingual learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Order matters in the presence of dataset imbalance for multilingual learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.517418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 01c9ed4c-88f4-436b-96a8-94b21489a582 · outbound

This paper cites The loss landscape of overparameterized neural networks.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning The loss landscape of overparameterized neural networks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.737232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ac65e2-4ee5-413e-ad42-cf9e2df54ea5 · outbound

This paper cites How to compute hessian- vector products? In The Third Blogpost Track at ICLR 2024, 2024.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning How to compute hessian- vector products? In The Third Blogpost Track at ICLR 2024, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.502088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2f1acc6f-42ca-4529-a8ff-9f9f040fe8da · outbound

This paper cites Laplace redux-effortless bayesian deep learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Laplace redux-effortless bayesian deep learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.488155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b08a1e5-cce4-4471-8b65-ad8fb264fd30 · outbound

This paper cites Multiple-gradient descent algorithm (mgda) for multiobjective opti- mization.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Multiple-gradient descent algorithm (mgda) for multiobjective opti- mization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.473162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e1ef8831-db92-44bb-ae43-f5b850649534 · outbound

This paper cites Implicit biases in multitask and continual learningfrom a backward error analysis perspective.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Implicit biases in multitask and continual learningfrom a backward error analysis perspective

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.458983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b3c73123-282e-4abd-9c0e-ba93ae54329c · outbound

This paper cites Bilevel programming for hyperparameter optimization and meta-learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Bilevel programming for hyperparameter optimization and meta-learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.760151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e752474-8956-4b25-ab11-cce8fdcc7bde · outbound

This paper cites Gradual domain adaptation: Theory and algorithms, 2023.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Gradual domain adaptation: Theory and algorithms, 2023

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.435452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 23df4a3b-b424-4c68-b3ef-3cb0dc59ddbf · outbound

This paper cites RotoGrad: Gradient Homogenization in Multitask Learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning RotoGrad: Gradient Homogenization in Multitask Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.769109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1af2ce6-ae7c-47ec-973c-862e3f724028 · outbound

This paper cites How does adaptive optimization impact local neural network geometry? Advances in Neural Information Processing Systems, 36, 2024.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning How does adaptive optimization impact local neural network geometry? Advances in Neural Information Processing Systems, 36, 2024

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.420858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6f19d429-6a4c-4978-8f6b-3ef1df4153fb · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Adam: A Method for Stochastic Optimization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.778674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a9e500-c4dc-4d8f-859e-93b7a4df8bf2 · outbound

This paper cites Understanding black-box predictions via influence functions.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Understanding black-box predictions via influence functions

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.783112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daafc727-b59c-4625-ae4b-20c35e363224 · outbound

This paper cites Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.393077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 65624969-7e5a-4f44-acb0-189db6b01805 · outbound

This paper cites Understanding Self-Training for Gradual Domain Adaptation.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Understanding Self-Training for Gradual Domain Adaptation

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-10T14:26:12.011585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 324df71c-ff94-45cc-b056-0832ea3a4256 · outbound

This paper cites Smooth manifolds.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Smooth manifolds

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.796835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45bd61c8-5f83-41ae-8939-13f71a54a450 · outbound

This paper cites Sequential reptile: Inter-task gradient alignment for multilingual learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Sequential reptile: Inter-task gradient alignment for multilingual learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.364697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eadc5bfc-d4e0-4a1e-80d2-ade2bf1353fd · outbound

This paper cites Pareto multi-task learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Pareto multi-task learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.349971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 876267d2-d9b9-4dd2-867f-8d2b5e7f7cef · outbound

This paper cites On the limited memory bfgs method for large scale optimization.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning On the limited memory bfgs method for large scale optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.809976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6144cb-c559-43ab-9d3b-70f0b33fd8ed · outbound

This paper cites Towards impartial multi-task learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Towards impartial multi-task learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.326801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 974885eb-75c3-45fb-97d6-d4613332fa3c · outbound

This paper cites Decoupled Weight Decay Regularization.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Decoupled Weight Decay Regularization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.819289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18526ae6-2418-40dd-8a06-7ac765ce7b29 · outbound

This paper cites Abide by the law and follow the flow: Conservation laws for gradient flows.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Abide by the law and follow the flow: Conservation laws for gradient flows

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.312456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9a539a25-55ae-40a1-a2c4-bd78b3d1735b · outbound

This paper cites The benefit of multitask representation learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning The benefit of multitask representation learning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.298587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c77dd37-8202-4087-9460-b43c84af7637 · outbound

This paper cites Multi-task learning as a bargaining game.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Multi-task learning as a bargaining game

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.283668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0aaf6509-978b-49cc-8bd8-7d7d7f4e71b8 · outbound

This paper cites Numerical optimization.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Numerical optimization

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.840452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c1ee67-aa4b-409d-ba47-df899be961f5 · outbound

This paper cites Fast exact multiplication by the hessian.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Fast exact multiplication by the hessian

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.259569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ab81ee9-19e2-40d3-b02f-e37f9ab10729 · outbound

This paper cites Estimating training data influence by tracing gradient descent.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Estimating training data influence by tracing gradient descent

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.849578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a89ea3d2-aed5-45e1-8de5-cdde2a5f1474 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.854466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07405d1c-48f6-47c9-a460-65f46f11835d · outbound

This paper cites Scalarization for multi-task and multi-domain learning at scale.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Scalarization for multi-task and multi-domain learning at scale

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.224655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b1d10c1-4199-4550-8364-4e7bc9377438 · outbound

This paper cites Scaling up influence functions.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Scaling up influence functions

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.209513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 133cc434-fc3b-4a83-952b-3bfec5a37bbe · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.868025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aa28f08-fc33-451f-8fb1-05e6c8a83787 · outbound

This paper cites Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.192435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 75c91cea-3438-4f2d-822e-be51d2d5c310 · outbound

This paper cites On the Power-Law Hessian Spectrums in Deep Learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning On the Power-Law Hessian Spectrums in Deep Learning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.877550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b94bc8-dde0-43fd-b8fc-76d482a9eb51 · outbound

This paper cites mT5: A massively multilingual pre-trained text-to-text transformer.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning mT5: A massively multilingual pre-trained text-to-text transformer

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T14:26:11.882025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5f937f5-4782-4b03-81f5-3590b0083346 · outbound

This paper cites Adatask: A task-aware adaptive learning rate approach to multi-task learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Adatask: A task-aware adaptive learning rate approach to multi-task learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.174319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 43bd8547-1d03-4069-8a85-cb8d5053e21d · outbound

This paper cites Gradient surgery for multi-task learning.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Gradient surgery for multi-task learning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.160100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b0ae2db7-337f-4773-b95a-9063ee078f7d · outbound

This paper cites Gradual domain adaptation via gradient flow.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Gradual domain adaptation via gradient flow

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:26:12.145462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fbbad324-0496-4302-b887-68fac5fa22b8 · outbound

This paper cites an unresolved cited work.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:26:12.129720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a0bc995a-daaf-496d-a18e-c857bbc54144 · outbound

This paper cites an unresolved cited work.

Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-10T14:26:12.112756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 66f08c25-4762-406d-b8a7-017d9b59a568 · inbound

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training cites this paper.

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-19T03:37:00.912798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 983c94c1-7b98-4d07-81c1-06320fa77607 · inbound

The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order cites this paper.

The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T16:49:58.059064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a4998d28-efb1-4b11-94a5-234f171e7fad · inbound

Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise cites this paper.

Optimizer Memory Makes Shuffle Order a First-Order Source of Fine-Tuning Noise Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-06-30T07:24:21.838843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 99e2bb68-a0c6-40a0-9d36-3d9d047fab04 · 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 Commute Your Domains: Trajectory Optimality Criterion for Multi-Domain Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T19:55:52.417363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.