Pith. sign in

Paper Citation Record · LEDGER

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic

As of 10 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2606.20734.

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

pith.paper-citation-record.v1
2606.20734 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-26T21:20:32.375373Z

measured 22 of 22 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 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

22 of 22 outbound references displayed

  • verified exact4
  • verified fuzzy0
  • unresolved18
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 78aa255a-30ef-4d72-8ba2-31673c59afce · outbound

This paper cites Learning transferable visual models from natural language supervision,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Learning transferable visual models from natural language supervision,

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:e31e3b8a88db7da66baf767d52e788aa658d8d61047ae95b0bedc935f61f8b05

Observation 27286957-ed1c-483a-8b86-4e939d5db06d · outbound

This paper cites Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:0a87a8117deae31b95155bbc397101a278f1390287d45d2f9a211453393a32ad

Observation f68aece3-0f76-413f-92db-bffdbf0026af · outbound

This paper cites Merging models with fisher-weighted averaging,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Merging models with fisher-weighted averaging,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:8e2fe3c983bda9be7e2544fb131f91c24877d64cee35a10e201878439297a969

Observation 7f46ec57-a4ac-4c7a-b7df-347ef1ebde6a · outbound

This paper cites Editing models with task arithmetic,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Editing models with task arithmetic,

Reference 4

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:d578b4be1ad981e5b08192e08e737be7cc12f05a695272508d15e12702301602

Observation f5e08a33-2ee4-4eb6-acdb-a0cf9c3485b2 · outbound

This paper cites Task arithmetic in the tangent space: Improved editing of pre-trained models,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Task arithmetic in the tangent space: Improved editing of pre-trained models,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:bdd93d58a72c70b115672e2176384a006df08986d4ef4d18d54722fdd6dda224

Observation 1d250a4a-7119-47cf-b778-effd0903c4dd · outbound

This paper cites Ties- merging: Resolving interference when merging models,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Ties- merging: Resolving interference when merging models,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:30b98056b7593e68a01874632b42b97aef96a1db958eeae91b908385a6671f78

Observation eed6a755-e2cd-4af8-bfd9-22011669c78a · outbound

This paper cites Localizing Task Information for Improved Model Merging and Compression.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Localizing Task Information for Improved Model Merging and Compression

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-07-04T00:19:13.235198Z

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.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:9bfc300675d5b6f2d5d96a8d9f191dbc95a3efec950f6585cafb68261477ba0e

Observation 5f2c6289-c158-44ec-bf32-8f729212d8f6 · outbound

This paper cites Task singular vectors: Reducing task interference in model merging,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Task singular vectors: Reducing task interference in model merging,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:47346764a3309ab9a9837044d91faa17146730ecad38f722a519303cfe81d7d7

Observation 90263dec-ad67-445e-b75e-b03aa17ebea6 · outbound

This paper cites A Short Note on the Kinetics-700 Human Action Dataset.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic A Short Note on the Kinetics-700 Human Action Dataset

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-07-04T00:19:13.238225Z

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.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:ca64d3f384846104b249f0693bd7356991319686e66292b5aee63ebb927f14c0

Observation de28af37-8b73-4d5c-b2b0-f0c8afe11a2c · outbound

This paper cites UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-07-04T00:19:13.241022Z

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.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:5ace4aa960e2569218c5b8b27761099b6a42f80b74b77199c0c15788c7001d36

Observation cc2c131e-45ae-4447-beb7-b4666375a464 · outbound

This paper cites Hmdb: A large video database for human motion recognition,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Hmdb: A large video database for human motion recognition,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:39f482225e547e48bc4bd7281614aba55d2a817447e12d6ccd46bee4e10fa6eb

Observation d32d594f-aec4-4d76-9551-9765217d5199 · outbound

This paper cites Not only look, but also listen: Learning multimodal violence detection under weak supervision,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Not only look, but also listen: Learning multimodal violence detection under weak supervision,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:aca9a1ccec864b6856d41cdfa06a5c4db6d63fd5803a3f153ff8d2f1547ec0a4

Observation 1f0deda6-b6c1-4da5-83d2-35a762b56dde · outbound

This paper cites Language models are super mario: Absorbing abilities from homologous models as a free lunch,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Language models are super mario: Absorbing abilities from homologous models as a free lunch,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:b3ac53806c15647e8f4b6e196dc24be859f6e61b0d9589cc0232e6b9de04ddfd

Observation 607cdf57-fd1b-4895-b101-83e71c3bccbe · outbound

This paper cites U-net transplant: the role of pre-training for model merging in 3d medical segmentation,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic U-net transplant: the role of pre-training for model merging in 3d medical segmentation,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:24a8471a3c52ad7694d8ac07273ab63978928caa3d1b04ea5db7e6a3536299ca

Observation 9156f010-6bf3-4a10-ad43-a15e4cfb66cb · outbound

This paper cites No task left behind: Isotropic model merging with common and task-specific subspaces,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic No task left behind: Isotropic model merging with common and task-specific subspaces,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:28b1272e36ef621a01eaf1503a6ae3066eefa5099e25215eb2c69e286fd70fc8

Observation 7a4d1b8e-27b6-4c11-998d-92c61f5c755f · outbound

This paper cites Open-vclip: Transforming clip to an open-vocabulary video model via interpolated weight optimization,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Open-vclip: Transforming clip to an open-vocabulary video model via interpolated weight optimization,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:d027f9c47b010f1bacd1f566144d3569c15cfdd851df3c9254646d29eb5f7a5a

Observation e6944d06-20c9-4866-8fcd-77b599c20894 · outbound

This paper cites Mastering task arithmetic:τjp as a key indicator for weight disentanglement,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Mastering task arithmetic:τjp as a key indicator for weight disentanglement,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:e98020141c9ff249addd6ea0b8135d9efb177ea4cf70624e3dd215e8709bd805

Observation d459ab8f-5221-4167-b03e-462185d22380 · outbound

This paper cites Dataless weight disentanglement in task arith- metic via kronecker-factored approximate curvature,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Dataless weight disentanglement in task arith- metic via kronecker-factored approximate curvature,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:ac15fbf164bc23266aba6d4f12b5102df95f0be1a790bcb6246dcff53e5effee

Observation ab7c4b06-6e2f-43ee-9ea1-b0178c92f70e · outbound

This paper cites A second-order perspective on model compositionality and incremental learning,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic A second-order perspective on model compositionality and incremental learning,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:4e6e1ca5fa6189451cfa8f0feb8a697175e4c56405b124b1b8c011664fe0ee85

Observation 08f1e612-9dbd-4894-868f-fea81a4efb7f · outbound

This paper cites Distilling linearized behavior into non-linear fine-tuning for effective task arith- metic,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Distilling linearized behavior into non-linear fine-tuning for effective task arith- metic,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:5d6acc48483a3951303c68b957d52ecc8b97dfee7d5a470aec6dffa49aa2f0ae

Observation 1743bd2c-f531-416c-b125-7e0588961daa · outbound

This paper cites The Kinetics Human Action Video Dataset.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic The Kinetics Human Action Video Dataset

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-07-04T00:19:13.237038Z

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.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:cb1f32d35f89fa54b064043bffd422949ddd1126d68370d5d246252e1123d6bd

Observation 66146a70-7c22-4eaf-854f-dc09fd545539 · outbound

This paper cites Decoupled weight decay regularization,.

Robust Zero-Shot Generalization for Open-Vocabulary Action Recognition via Task Arithmetic Decoupled weight decay regularization,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-06-26T21:20:32.375373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-26T21:20:32.375373Z digest=sha256:0559575ef823f267bb993268599c00f3c5eb706503d7ad94f732487e851aab6d

Pith citing papers

No inbound Pith citation observations are available.