Paper Citation Record · LEDGER

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning

As of 20 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2506.20986.

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

pith.paper-citation-record.v1
2506.20986 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:40:36.088082Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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

42 of 42 outbound references displayed

verified exact2
verified fuzzy21
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4870926f-347a-4fc6-befd-dba695c4c11f · outbound

This paper cites GPT-4 Technical Report.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:32.974233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9884a507-ffe6-4bd5-96ed-1a36dbf6ef64 · outbound

This paper cites Learning to generalize to new compositions in image understanding.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Learning to generalize to new compositions in image understanding

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:40:36.189187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8b860204-8371-4a54-b866-61a4168991ca · outbound

This paper cites A causal view of compositional zero-shot recognition.Ad- vances in Neural Information Processing Systems, 33:1462– 1473, 2020.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning A causal view of compositional zero-shot recognition.Ad- vances in Neural Information Processing Systems, 33:1462– 1473, 2020

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.438024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b9f5878e-890f-4096-bc4c-51a1af79b847 · outbound

This paper cites Prompting language-informed distribution for compositional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Prompting language-informed distribution for compositional zero-shot learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.428944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e1900641-6d2b-4d26-a1ce-5491d0a0bb0c · outbound

This paper cites Lan- guage models are few-shot learners.Advances in neural in- formation processing systems, 33:1877–1901, 2020.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Lan- guage models are few-shot learners.Advances in neural in- formation processing systems, 33:1877–1901, 2020

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:33.474344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc9efd5-bc4a-4485-a83d-f01be081a3d3 · outbound

This paper cites Bert: Pre-training of deep bidirectional trans- formers for language understanding.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Bert: Pre-training of deep bidirectional trans- formers for language understanding

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.415030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5e83e49d-2acf-4e55-90b3-0e3ac0942e52 · outbound

This paper cites Unified language model pre-training for natural language un- derstanding and generation.Advances in neural information processing systems, 32, 2019.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Unified language model pre-training for natural language un- derstanding and generation.Advances in neural information processing systems, 32, 2019

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.406431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1c8721d3-933c-4aa7-afab-bf6207d53817 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning LoRA: Low-Rank Adaptation of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:33.860998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd98c7f0-646d-4c37-9ae8-aab8fd2f0b64 · outbound

This paper cites Troika: Multi-path cross-modal trac- tion for compositional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Troika: Multi-path cross-modal trac- tion for compositional zero-shot learning

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.396946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0d98c6a9-f7de-4313-8c8a-3ff932263fab · outbound

This paper cites Dis- covering states and transformations in image collections.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Dis- covering states and transformations in image collections

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.388101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ab79cff6-854f-4192-b951-9837d5a6c20e · outbound

This paper cites Jacobs, Michael I.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Jacobs, Michael I

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.379377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4ae038a5-bba0-4025-86fb-f39c8eaf252b · outbound

This paper cites Mixtral of Experts.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Mixtral of Experts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:34.367325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a78707bf-7515-435a-b72f-0662e446038e · outbound

This paper cites Retrieval-augmented primitive representations for composi- tional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Retrieval-augmented primitive representations for composi- tional zero-shot learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.370023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9dbaccf0-fe7a-4065-89e7-71dbd7ffc079 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Adam: A Method for Stochastic Optimization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:34.645710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f26416d-86da-4445-8f32-8499702f218e · outbound

This paper cites PhD thesis, Massachusetts Institute of Technology,.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning PhD thesis, Massachusetts Institute of Technology,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.360728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 42d85b48-964a-4320-bfcc-39dec079c686 · outbound

This paper cites Building machines that learn and think like people.Behavioral and brain sciences, 40:e253,.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Building machines that learn and think like people.Behavioral and brain sciences, 40:e253,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:34.912477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c47da2-9210-4847-b7c9-7ca079241a75 · outbound

This paper cites Align before fuse: Vision and language representation learn- ing with momentum distillation.Advances in neural infor- mation processing systems, 34:9694–9705, 2021.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Align before fuse: Vision and language representation learn- ing with momentum distillation.Advances in neural infor- mation processing systems, 34:9694–9705, 2021

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:35.033088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dba3f290-5f3c-4aeb-9349-2e6a0534dd58 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:35.166543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e048b271-7fa9-40ab-8d7a-3506e55b96d5 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:35.274667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b20e4111-8dad-4b05-a9ec-f470bf03aa07 · outbound

This paper cites Siamese contrastive embedding network for composi- tional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Siamese contrastive embedding network for composi- tional zero-shot learning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.333613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9579271e-44eb-449b-a199-725045e9ea1c · outbound

This paper cites Context-based and diversity-driven specificity in compositional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Context-based and diversity-driven specificity in compositional zero-shot learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.324105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c5e67da7-e508-4d16-ad8e-39cbdeb19884 · outbound

This paper cites Symme- try and group in attribute-object compositions.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Symme- try and group in attribute-object compositions

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.315732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d10329e7-3403-4ad7-b1be-ea0ae1ea1f91 · outbound

This paper cites DeepSeek-V3 Technical Report.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning DeepSeek-V3 Technical Report

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:35.827916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b02baa4e-8b1d-4f88-9ab1-a8dfe01d1a37 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36, 2024.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Visual instruction tuning.Advances in neural information processing systems, 36, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:35.941958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1fa687-12c8-48e1-a409-7188b6d9de1c · outbound

This paper cites De- composed soft prompt guided fusion enhancing for compo- sitional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning De- composed soft prompt guided fusion enhancing for compo- sitional zero-shot learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.302302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7b35e50c-c8cd-4384-8e12-85171d83eb2e · outbound

This paper cites Open world compositional zero- shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Open world compositional zero- shot learning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.292057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0b3131de-ab92-4786-bc6f-428ed5e09e73 · outbound

This paper cites Learning graph embeddings for open world compositional zero-shot learning.IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2022.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Learning graph embeddings for open world compositional zero-shot learning.IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2022

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.283105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9fc482b5-ff7f-4440-a276-9dc6076b37aa · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Efficient Estimation of Word Representations in Vector Space

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.001028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1226475-b02a-4596-b21e-6fc2d408e2a8 · outbound

This paper cites From red wine to red tomato: Composition with context.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning From red wine to red tomato: Composition with context

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.273855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 44889fac-4502-485f-a8da-313b7a475f78 · outbound

This paper cites Learning graph embeddings for compositional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Learning graph embeddings for compositional zero-shot learning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.263559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 947647a3-57a3-4ec0-b018-79a9605f9400 · outbound

This paper cites Learning to Compose Soft Prompts for Compositional Zero-Shot Learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:40:36.140003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 53d9c44c-2de7-4057-8fae-7a161f08657c · outbound

This paper cites Pytorch: An im- perative style, high-performance deep learning library.Ad- vances in neural information processing systems, 32, 2019.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Pytorch: An im- perative style, high-performance deep learning library.Ad- vances in neural information processing systems, 32, 2019

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.026052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0b87b86-5610-43e1-bad6-cf9f82ef7dc1 · outbound

This paper cites Task-driven modular networks for zero-shot compositional learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Task-driven modular networks for zero-shot compositional learning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.249816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 33d484f9-c554-4843-a7e1-4416f2a14da5 · outbound

This paper cites Language models are unsu- pervised multitask learners.OpenAI blog, 1(8):9, 2019.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Language models are unsu- pervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.037594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31c2a6aa-13da-4cfa-860e-b01e0bd5d581 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Learn- ing transferable visual models from natural language super- vision

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.235554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation daf8b0b1-454b-4bbf-83c5-784500096024 · outbound

This paper cites Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.050194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80218ce5-6f21-47a9-8e9b-7163bdf29c94 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.057364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d0305a-b5f6-4138-949b-2531e03c5938 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.064203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb21e691-673f-41c2-9161-6eee88302e83 · outbound

This paper cites Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.070333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10772740-abe7-48df-b908-6f9380801ab5 · outbound

This paper cites Gipcol: Graph-injected soft prompting for compositional zero-shot learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Gipcol: Graph-injected soft prompting for compositional zero-shot learning

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.221231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e361c574-bdc8-4ed8-a73e-baa62c19bc3f · outbound

This paper cites Fine-grained visual compar- isons with local learning.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Fine-grained visual compar- isons with local learning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T22:40:36.211763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 774ffad0-617e-4bcc-ae82-6dba06c5c980 · outbound

This paper cites Learning to prompt for vision-language models.In- ternational Journal of Computer Vision, 130(9):2337–2348,.

EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning Learning to prompt for vision-language models.In- ternational Journal of Computer Vision, 130(9):2337–2348,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T22:40:36.088082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.