Pith. sign in

Paper Citation Record · LEDGER

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone

As of 14 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2502.00217.

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

pith.paper-citation-record.v1
2502.00217 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T19:55:16.923519Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

29 of 29 outbound references displayed

  • verified exact0
  • verified fuzzy15
  • unresolved14
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8e0b8900-7fa1-4245-b316-e4ebb2f84e9f · outbound

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

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Just pick a sign: Optimizing deep multitask models with gradient sign dropout

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.277223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.803979Z digest=sha256:11837dfd880f90415a962a78188f531b80c3d0612f5c294b61d9e78a4c13ecbe

Observation aa1b066a-010a-4027-90b1-2e894a11b176 · outbound

This paper cites The cityscapes dataset for semantic urban scene understanding.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone The cityscapes dataset for semantic urban scene understanding

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.808923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.808923Z digest=sha256:6eb1b66b48f24812a3c729f49b6c593bbfe99b5d500d332494252d9064709f24

Observation 4ca1b901-070d-4f1c-9fb0-e340c78397db · outbound

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

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Multiple-gradient descent algorithm (mgda) for multiobjective optimization

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.257871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.813365Z digest=sha256:1853f28f2fd9d8162dfa1d5194429bea61ac274babbab08e8063f0afe6cb9965

Observation d5708693-411c-468b-9259-c7ba5db4bc02 · outbound

This paper cites Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.817738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.817738Z digest=sha256:57163da018e0cc55fe05db725936b4aa0cc4df127d515d3921c95b6feaf49985

Observation b90c6786-79de-4e48-849a-7a618c375faf · outbound

This paper cites Mask r-cnn.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Mask r-cnn

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.822134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.822134Z digest=sha256:83a7738620029479a990b42f5cefe13fedb27aec4f07c57ae12ecd38ee390071

Observation 1505de63-0160-4cd0-a5cd-556af4cabe48 · outbound

This paper cites an unresolved cited work.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:55:17.231960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.826472Z digest=sha256:23f6514ad2d47bba4b8c4b82ece1827e6886d743bf2bbd0f7cb5c6d88d5bbe62

Observation 8c2c076f-e279-4b9e-82bb-806563a4433c · outbound

This paper cites Multi-task learning using uncertainty to weigh losses for scene geometry and semantics.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Multi-task learning using uncertainty to weigh losses for scene geometry and semantics

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.830862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.830862Z digest=sha256:4a0ce9105cdc9fc007e7cbf5b3fa6a1e5f4bb5bfa61a463f40b101d2a79c543f

Observation e9792c14-6ec6-41da-b084-e878caf1aaeb · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Adam: A Method for Stochastic Optimization

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.835027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.835027Z digest=sha256:5e5eff858511f10fd13eee3a490009c83fadf05474fab93a1dc67733b18bcfad

Observation 47f94d36-0331-4981-92f6-2dcb37f410a9 · outbound

This paper cites Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.839556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.839556Z digest=sha256:b199215422c9433e8919240faafadb0c36560144c444402e85bbef8700740078

Observation 6c3ad359-f39b-4ff8-add5-7e184a58554d · outbound

This paper cites Mtmamba: Enhancing multi-task dense scene understanding by mamba-based decoders.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Mtmamba: Enhancing multi-task dense scene understanding by mamba-based decoders

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.212282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.844038Z digest=sha256:a9c182dd6f3be01f65bb161356440a1a8bc716b38afb4b0390cfe4bed1bff076

Observation ef1f616c-d3b6-4c67-8c30-ab2b5da828f1 · outbound

This paper cites Conflict-averse gradient descent for multi-task learning.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Conflict-averse gradient descent for multi-task learning

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.200355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.848224Z digest=sha256:c99f809b8d89a8b90586b49ac85ab18486b230c60be688729581523a5a3c3c50

Observation 26e2906a-3a78-4b7d-8375-fd2b60d3ec8d · outbound

This paper cites Famo: Fast adaptive multitask optimization.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Famo: Fast adaptive multitask optimization

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.189283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.852368Z digest=sha256:223a5cc4e85b2a7b8356561e2d69d4f7c3d6a178d5605389c97f5f9ea8f55f15

Observation 72484afc-7ef1-4069-9261-cec4ebe5b2bc · outbound

This paper cites Towards impartial multi-task learning.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Towards impartial multi-task learning

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.176281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.856745Z digest=sha256:ebc1ebf68549c2604c6f236590afc5802bc98a372888d384fd27a97d5ab24acb

Observation e79d41f0-9054-456a-8a66-18bfbc4eb3e5 · outbound

This paper cites an unresolved cited work.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Unresolved cited work

Reference 14

Resolution
unresolved
raw_fallback, observed 2026-08-09T19:55:17.163332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.860780Z digest=sha256:978862914c0026232a3081c03706f20662ce19b17576c53facea49adef4b9583

Observation 9dd34d52-2bc1-4eb0-95db-4746f7ffd1b5 · outbound

This paper cites Deep learning face attributes in the wild.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Deep learning face attributes in the wild

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.864848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.864848Z digest=sha256:dc6a56507a71be64d4792d2714ee3ea4abe3027c5a01153865cb91a01e78d163

Observation 667faedd-712a-4be5-8017-ac133c33bb0d · outbound

This paper cites Fully convolutional networks for semantic segmentation.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Fully convolutional networks for semantic segmentation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.868664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.868664Z digest=sha256:603947901d43cf8a7798049a806b550b194606454026404d2dc660907afca0e1

Observation b7ab6734-944b-49c7-b94a-00b79bdac299 · outbound

This paper cites Multi-Task Learning as a Bargaining Game.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Multi-Task Learning as a Bargaining Game

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.872799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.872799Z digest=sha256:7ecfc82b96d167cc812dde07a14b77b17297633eee147ef5065a896ad4d24f78

Observation ba82d28e-938b-4c85-9415-75eba713f1c8 · outbound

This paper cites and Koltun, V.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone and Koltun, V

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.136615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.877294Z digest=sha256:e5bd642dff76ae68e32031e644c7a22328f01b2c57b4ba7f5ebd824d3b3ff543

Observation b9f4d012-1fcf-49b8-8203-5bfe2013b990 · outbound

This paper cites Indoor segmentation and support inference from rgbd images.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Indoor segmentation and support inference from rgbd images

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.123472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.881298Z digest=sha256:86f07b24b87292c696e7dc718dc0062133167d391210a48a92f11b68f5dcf4d4

Observation 3ce16ca8-26ab-4f2d-8d31-974b5d0fc98d · outbound

This paper cites and Zhang, A.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone and Zhang, A

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.110574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.885396Z digest=sha256:952f7e9eeb1f67c225253add47daee645056cb393dacfe8de7ea3da86a697716

Observation d005711a-f927-400e-9af3-391b54f137b1 · outbound

This paper cites ptflops: a flops counting tool for neural networks in pytorch framework, 2018-2024.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone ptflops: a flops counting tool for neural networks in pytorch framework, 2018-2024

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.098343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.889718Z digest=sha256:02ed9d6c0514903f9353f7068c6efeb54fcb0ac108f573e7227f082cdcc410d9

Observation 2bb83cff-fc82-4450-825b-8d9a0c3dbca2 · outbound

This paper cites an unresolved cited work.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.893918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.893918Z digest=sha256:fb846dc4bb0d31a9014c8bc93689d88054173b4c2d593860dbef9d6339cf4a8e

Observation f678d07e-588b-4400-85bd-6a5cc821dec3 · outbound

This paper cites Multi-task learning for dense prediction tasks: A survey.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Multi-task learning for dense prediction tasks: A survey

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.078029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.898048Z digest=sha256:6cdd79ad9b72aba4d56dca30e6f53a5258a6d25349009c894a9fe9b90840b7de

Observation f1584432-83ff-456d-b7bd-201882151b3c · outbound

This paper cites Direction-oriented multi-objective learning: Simple and provable stochastic algorithms.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Direction-oriented multi-objective learning: Simple and provable stochastic algorithms

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.063997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.902728Z digest=sha256:07f5b9f3064fff09acda97dc0d8a6f91a9002513c5cdb05b20f26c27df1b39d3

Observation 7d3317a5-a1e0-4691-8dd2-e609ee0d7b6e · outbound

This paper cites Multi-task reinforcement learning with soft modularization.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Multi-task reinforcement learning with soft modularization

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.907016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.907016Z digest=sha256:50cbdf70cd6479f90af8e1506a9f3a4118c21765c15f5710160cd13091632eaf

Observation 18544085-0580-446f-90ed-db3fd4097c65 · outbound

This paper cites Gradient surgery for multi-task learning.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Gradient surgery for multi-task learning

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.039601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.911053Z digest=sha256:f1ea6e0350c6dc20a9bf10ff13a33ce4470dec4bca023c93cf1eebc279722000

Observation bb91fc5b-fc1c-4c1c-b429-1c02da8054ab · outbound

This paper cites Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.025168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.915114Z digest=sha256:2d7fb4cca6e8a85a102c43637f2cca937178c6c98cf1c3395ce2db959bec29cc

Observation 6596d8de-40bd-4a02-a0d6-3e5d52c45e7a · outbound

This paper cites Sgw-based multi-task learning in vision tasks.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone Sgw-based multi-task learning in vision tasks

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T19:55:17.011422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-09T19:55:16.919227Z digest=sha256:86d8422b1a7a73c5e1ef6e43f7dd4a08c327a57743ef0bb9a8e7942fb019611e

Observation ce8b91ec-be6b-42f6-b3bc-57591737b531 · outbound

This paper cites write newline.

Fantastic Multi-Task Gradient Updates and How to Find Them In a Cone write newline

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-09T19:55:16.923519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T19:55:16.923519Z digest=sha256:9cee7d4d9b816675a5d2cc15b20240682e1beb4c68deaf269512c768a396b672

Pith citing papers

No inbound Pith citation observations are available.