{"as_of":"2026-08-15T11:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5f735f30709138dbeb138f311dded3c40afdac9190bdfcd353ca8389589f1542","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:40:36.088082Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.20986/citation-record","integrity":"/paper/2506.20986/integrity","json":"/paper/2506.20986/citation-record.json","paper":"/paper/2506.20986"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T22:40:32.974233Z","title":"Gpt-4 technical report.arXiv preprint arXiv:2303.08774,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:32.974233Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:535906198f6c30fd789d5080635f693393e4fb0bc8d6ec51f6b99c2ab7b33e4d","observation_id":"4870926f-347a-4fc6-befd-dba695c4c11f","resolution":{"observed_at":"2026-08-06T22:40:32.974233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.07639","last_updated":"2016-08-27T00:34:00Z","snapshot_observed_at":"2026-08-14T21:42:35.603296Z","submitted_at":"2016-08-27T00:34:00Z","title":"Learning to generalize to new compositions in image understanding","version":1},"cited_work":{"arxiv_id":"1608.07639","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.07639","snapshot_observed_at":"2026-08-06T22:40:36.185437Z","title":"Learning to generalize to new compositions in image understanding","venue":"cs.CV","work_id":"9ddc278c-db42-44c9-ad12-e67cfcca3385","year":2016},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.079614Z"},"links":{"cited_paper":"/paper/1608.07639","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:57dedd40bd7007213655d66b8909bca0d8cca44849359b523e8cf0ab7076ab8e","observation_id":"9884a507-ffe6-4bd5-96ed-1a36dbf6ef64","resolution":{"observed_at":"2026-08-06T22:40:36.189187Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.434742Z","title":"A causal view of compositional zero-shot recognition.Ad- vances in Neural Information Processing Systems, 33:1462– 1473, 2020","venue":null,"work_id":"2cbf99d0-ef16-44c8-8f97-badc3c70ffdc","year":2020},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.184350Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:9f4d4c85a3cd32c57d8c59770c1a9cd75b43718a2c2ffbee3fa811ba75987e08","observation_id":"8b860204-8371-4a54-b866-61a4168991ca","resolution":{"observed_at":"2026-08-06T22:40:36.438024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.425044Z","title":"Prompting language-informed distribution for compositional zero-shot learning","venue":null,"work_id":"3c721075-e23a-4dac-9aa3-594279340dc0","year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.320287Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:f2b75539eb412730a5ee8d1c2c2fd755364ac16ea4a5cf2164e4703b6e03292d","observation_id":"b9f5878e-890f-4096-bc4c-51a1af79b847","resolution":{"observed_at":"2026-08-06T22:40:36.428944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:33.474344Z","title":"Lan- guage models are few-shot learners.Advances in neural in- formation processing systems, 33:1877–1901, 2020","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.474344Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:6a65e08638eec7085be97d940613c0e31d163640dfd070823991d71744942cb4","observation_id":"e1900641-6d2b-4d26-a1ce-5491d0a0bb0c","resolution":{"observed_at":"2026-08-06T22:40:33.474344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.411864Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":"0494dd5e-6961-4501-80f8-9ad6f6fae64f","year":2019},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.637053Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:9d167abdb2108d6e86d39678e1ec4fda5f000c0dc13ed327c0d693bb4f6f718f","observation_id":"4dc9efd5-bc4a-4485-a83d-f01be081a3d3","resolution":{"observed_at":"2026-08-06T22:40:36.415030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.402956Z","title":"Unified language model pre-training for natural language un- derstanding and generation.Advances in neural information processing systems, 32, 2019","venue":null,"work_id":"a48cfa0e-7aa6-4b96-971c-2b5de354fe88","year":2019},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.750243Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:ed7320c627af2531eb7e013056a2e3cfc886bb3c3c47e050f7ea9e1801b69910","observation_id":"5e83e49d-2acf-4e55-90b3-0e3ac0942e52","resolution":{"observed_at":"2026-08-06T22:40:36.406431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T22:40:33.860998Z","title":"Edward Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.860998Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:67076eedd2d75e388687c65f8497a0a4fccdca441fc4fbb36d0db796509ffbc7","observation_id":"1c8721d3-933c-4aa7-afab-bf6207d53817","resolution":{"observed_at":"2026-08-06T22:40:33.860998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.393687Z","title":"Troika: Multi-path cross-modal trac- tion for compositional zero-shot learning","venue":null,"work_id":"ee5bff9f-2a44-4c72-9a70-3ab7776db654","year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:33.962705Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:124a5abb97f6cfc6f4c568a1dfd111d4fca33b0beec581bc86ccb067602d1a12","observation_id":"fd98c7f0-646d-4c37-9ae8-aab8fd2f0b64","resolution":{"observed_at":"2026-08-06T22:40:36.396946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.384599Z","title":"Dis- covering states and transformations in image collections","venue":null,"work_id":"8d250849-4ce7-4ffe-8d2b-ee64c8f7a29a","year":2015},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.131627Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:1f4526c00e40caa69834aab1121d02480e21d184b28cae196987021b4df42ca5","observation_id":"0d98c6a9-f7de-4313-8c8a-3ff932263fab","resolution":{"observed_at":"2026-08-06T22:40:36.388101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.376408Z","title":"Jacobs, Michael I","venue":null,"work_id":"eb50ade9-3342-43db-912f-8ad1070d25eb","year":1991},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.256410Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:bbba822dc950bbd17d136028433889513ada52270c4b7a2d78c2441241ca9588","observation_id":"ab79cff6-854f-4192-b951-9837d5a6c20e","resolution":{"observed_at":"2026-08-06T22:40:36.379377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04088","last_updated":"2024-01-08T18:47:34Z","snapshot_observed_at":"2026-08-13T19:43:49.936776Z","submitted_at":"2024-01-08T18:47:34Z","title":"Mixtral of Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04088","snapshot_observed_at":"2026-08-06T22:40:34.367325Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.367325Z"},"links":{"cited_paper":"/paper/2401.04088","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:a8cf38043c0136c9a35a874554e0b74b9c44678c79f77732bc76e77475b32e3a","observation_id":"4ae038a5-bba0-4025-86fb-f39c8eaf252b","resolution":{"observed_at":"2026-08-06T22:40:34.367325Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.366614Z","title":"Retrieval-augmented primitive representations for composi- tional zero-shot learning","venue":null,"work_id":"38a91d02-7be4-4d3b-9b0d-624eb07c6dd9","year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.498916Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:12e2dc39f704b9df6d6a148a146020ec42a27707a0eb61bee177e75f6b10de71","observation_id":"a78707bf-7515-435a-b72f-0662e446038e","resolution":{"observed_at":"2026-08-06T22:40:36.370023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-06T22:40:34.645710Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.645710Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:cb821845a739d2fe6163ccf42f58f8d067b6aeb2c3dace1c4430a4e2240177ac","observation_id":"9dbaccf0-fe7a-4065-89e7-71dbd7ffc079","resolution":{"observed_at":"2026-08-06T22:40:34.645710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.357725Z","title":"PhD thesis, Massachusetts Institute of Technology,","venue":null,"work_id":"155534e4-d928-4477-80b1-34ab90a2e3dc","year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.760582Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:4522e90758b7d24c41ab6570bf7e2060d84559b0eff6b22c3afb841e6ee4d6a1","observation_id":"3f26416d-86da-4445-8f32-8499702f218e","resolution":{"observed_at":"2026-08-06T22:40:36.360728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:34.912477Z","title":"Building machines that learn and think like people.Behavioral and brain sciences, 40:e253,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:34.912477Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:06d63161766f1088f06fc60b309a6b46f4c55fb605746d9630108cb6e6130c95","observation_id":"42d85b48-964a-4320-bfcc-39dec079c686","resolution":{"observed_at":"2026-08-06T22:40:34.912477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:35.033088Z","title":"Align before fuse: Vision and language representation learn- ing with momentum distillation.Advances in neural infor- mation processing systems, 34:9694–9705, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.033088Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:19b0db08f84f725ff728da6da579a0fa9e1a58bbfca5d84b276b11680bcc7a7b","observation_id":"70c47da2-9210-4847-b7c9-7ca079241a75","resolution":{"observed_at":"2026-08-06T22:40:35.033088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:35.166543Z","title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.166543Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:9b173e70ec8280cb564adcacce6bb2ccaf1182a63526e884d820de9f5e77ed22","observation_id":"dba3f290-5f3c-4aeb-9349-2e6a0534dd58","resolution":{"observed_at":"2026-08-06T22:40:35.166543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:35.274667Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.274667Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:266cd29291bf1abb2e122148d248a35b2122e4319ffaa038735df35266ec11e7","observation_id":"e048b271-7fa9-40ab-8d7a-3506e55b96d5","resolution":{"observed_at":"2026-08-06T22:40:35.274667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.329955Z","title":"Siamese contrastive embedding network for composi- tional zero-shot learning","venue":null,"work_id":"c74f6b8e-5c33-474d-baa6-d9c7679383f0","year":2022},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.416201Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:6aac3f12100ae83891acdbe64d3ea7cbaa482e0abf27886a8f4c26676fccaa8b","observation_id":"b20e4111-8dad-4b05-a9ec-f470bf03aa07","resolution":{"observed_at":"2026-08-06T22:40:36.333613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.320929Z","title":"Context-based and diversity-driven specificity in compositional zero-shot learning","venue":null,"work_id":"dcc9bc9e-c393-4ecf-8fe0-68c88c208f03","year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.569761Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:2a022aa20e0a10c5010413f29ace1b8d22a732efebba65849a18de1ba595dee5","observation_id":"9579271e-44eb-449b-a199-725045e9ea1c","resolution":{"observed_at":"2026-08-06T22:40:36.324105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.312852Z","title":"Symme- try and group in attribute-object compositions","venue":null,"work_id":"89ae0022-3ef7-48eb-9019-448d01a6fd5c","year":2020},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.697330Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:fef3b7a5a233cd9869a1595a9cb5f70e57673f3652e6c78419cd9b5f6134f0f4","observation_id":"c5e67da7-e508-4d16-ad8e-39cbdeb19884","resolution":{"observed_at":"2026-08-06T22:40:36.315732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-11T01:48:59.557045Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-06T22:40:35.827916Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.827916Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:b1ee697f0d5f52a06557f6ca744f402531824afd11af02346175d9732b80fdd7","observation_id":"d10329e7-3403-4ad7-b1be-ea0ae1ea1f91","resolution":{"observed_at":"2026-08-06T22:40:35.827916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:35.941958Z","title":"Visual instruction tuning.Advances in neural information processing systems, 36, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.941958Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:6a51801756a20666d5598b82c9720cbeec051b3f96a3fb1ffc25f54915cf1583","observation_id":"b02baa4e-8b1d-4f88-9ab1-a8dfe01d1a37","resolution":{"observed_at":"2026-08-06T22:40:35.941958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.298271Z","title":"De- composed soft prompt guided fusion enhancing for compo- sitional zero-shot learning","venue":null,"work_id":"583db3b2-f10c-4581-98aa-f88e9163149b","year":2023},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.980128Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:f2e06d1d8971be50d019bd25ac4690a4cfd44e1b3382cb78b66d4609e9819274","observation_id":"fd1fa687-12c8-48e1-a409-7188b6d9de1c","resolution":{"observed_at":"2026-08-06T22:40:36.302302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.288523Z","title":"Open world compositional zero- shot learning","venue":null,"work_id":"09a2f0f5-93ff-49ff-9d06-61f05b5d4dbe","year":2021},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.988196Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:4059791b98fbf35abbcd7d91ffb214dfa0109b12bd69e449c7a8611944d3312d","observation_id":"7b35e50c-c8cd-4384-8e12-85171d83eb2e","resolution":{"observed_at":"2026-08-06T22:40:36.292057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.279411Z","title":"Learning graph embeddings for open world compositional zero-shot learning.IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2022","venue":null,"work_id":"ee47e7e4-3b09-43ee-921a-3939617fdf36","year":2022},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:35.995235Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:3251dd4d55be9e56c039284af60005ece98fbb11905c7bc870dc4ba7ee5061be","observation_id":"0b3131de-ab92-4786-bc6f-428ed5e09e73","resolution":{"observed_at":"2026-08-06T22:40:36.283105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1301.3781","last_updated":"2013-09-07T00:30:40Z","snapshot_observed_at":"2026-07-06T03:04:11.148340Z","submitted_at":"2013-01-16T18:24:43Z","title":"Efficient Estimation of Word Representations in Vector Space","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1301.3781","snapshot_observed_at":"2026-08-06T22:40:36.001028Z","title":"Efficient estimation of word representa- tions in vector space.arXiv preprint arXiv:1301.3781, 3781,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.001028Z"},"links":{"cited_paper":"/paper/1301.3781","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:1513db673bd7fcf9191a3fe689e505b4483e83c16f337e5cb11a6ad44c231b85","observation_id":"9fc482b5-ff7f-4440-a276-9dc6076b37aa","resolution":{"observed_at":"2026-08-06T22:40:36.001028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.270007Z","title":"From red wine to red tomato: Composition with context","venue":null,"work_id":"d6cc9432-db1d-44cf-8baa-a133952d248c","year":2017},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.007338Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:5246425c6e5b52f4a6d4064a524e2dc8f4fcb82d97d6d61eedbdba47fdfac5ca","observation_id":"c1226475-b02a-4596-b21e-6fc2d408e2a8","resolution":{"observed_at":"2026-08-06T22:40:36.273855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.259857Z","title":"Learning graph embeddings for compositional zero-shot learning","venue":null,"work_id":"ddaf27ab-a774-42e2-ae24-88abc4162e3c","year":2021},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.013239Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:0d7314af9e682b3f9979e2738ed137a8a705254912864f5196dfbef27141fd7b","observation_id":"44889fac-4502-485f-a8da-313b7a475f78","resolution":{"observed_at":"2026-08-06T22:40:36.263559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.03574","last_updated":"2023-04-24T15:46:28Z","snapshot_observed_at":"2026-08-13T16:06:49.360304Z","submitted_at":"2022-04-07T16:51:12Z","title":"Learning to Compose Soft Prompts for Compositional Zero-Shot Learning","version":3},"cited_work":{"arxiv_id":"2204.03574","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.03574","snapshot_observed_at":"2026-08-06T22:40:36.133810Z","title":"Learning to Compose Soft Prompts for Compositional Zero-Shot Learning","venue":"cs.LG","work_id":"146a5df3-2a46-4076-91cb-8a30532b0144","year":2022},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.019138Z"},"links":{"cited_paper":"/paper/2204.03574","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:0191a84df747c5f9e087175f91f7c0d9166ee62de6dec10369fab84dfdb4999e","observation_id":"947647a3-57a3-4ec0-b018-79a9605f9400","resolution":{"observed_at":"2026-08-06T22:40:36.140003Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.026052Z","title":"Pytorch: An im- perative style, high-performance deep learning library.Ad- vances in neural information processing systems, 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.026052Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:f8f2e090cef6317d4e3bdc3950d396a52d23d3405c554c4ad4e26c25a0b2bd96","observation_id":"53d9c44c-2de7-4057-8fae-7a161f08657c","resolution":{"observed_at":"2026-08-06T22:40:36.026052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.245326Z","title":"Task-driven modular networks for zero-shot compositional learning","venue":null,"work_id":"ade00adf-38d7-48e7-b532-a06f78544c0a","year":2019},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.031647Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:03a9247200ccd8d7777b4ab409e8f966ff7a91ae67399daa1ec35ffd29e43633","observation_id":"e0b87b86-5610-43e1-bad6-cf9f82ef7dc1","resolution":{"observed_at":"2026-08-06T22:40:36.249816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.037594Z","title":"Language models are unsu- pervised multitask learners.OpenAI blog, 1(8):9, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.037594Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:948b547d58f54af34ae3ef94921d919388791d2c0c1fdf23c3f2f3369eb249da","observation_id":"33d484f9-c554-4843-a7e1-4416f2a14da5","resolution":{"observed_at":"2026-08-06T22:40:36.037594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.232347Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":"b6de204d-21b6-4628-a765-6aaa3bf650d5","year":2021},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.044373Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:1f249716c54b9f9f168df294eec79fb260b6e90602beb5254d7d8f6f75216fa4","observation_id":"31c2a6aa-13da-4cfa-860e-b01e0bd5d581","resolution":{"observed_at":"2026-08-06T22:40:36.235554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-08-13T11:35:07.866136Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-06T22:40:36.050194Z","title":"Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.050194Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:38a6de6c2ea141f7932836a7b248571d3e2b208a83c7831c08103cd4607a57f8","observation_id":"daf8b0b1-454b-4bbf-83c5-784500096024","resolution":{"observed_at":"2026-08-06T22:40:36.050194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05530","last_updated":"2024-12-16T17:39:39Z","snapshot_observed_at":"2026-08-14T18:15:53.516440Z","submitted_at":"2024-03-08T18:54:20Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05530","snapshot_observed_at":"2026-08-06T22:40:36.057364Z","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of con- text.arXiv preprint arXiv:2403.05530, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.057364Z"},"links":{"cited_paper":"/paper/2403.05530","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:aaadd426807140433dba1d1923f5175ba4f4b398a331620fafa3fcc14ee36bb5","observation_id":"80218ce5-6f21-47a9-8e9b-7163bdf29c94","resolution":{"observed_at":"2026-08-06T22:40:36.057364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.064203Z","title":"Attention is all you need.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.064203Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:e91c03849fcbc8dfde5708af9653dcd28302273579111a9cc96f9658ecebb374","observation_id":"51d0305a-b5f6-4138-949b-2531e03c5938","resolution":{"observed_at":"2026-08-06T22:40:36.064203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.05077","last_updated":"2022-11-09T18:08:53Z","snapshot_observed_at":"2026-08-13T17:13:10.216217Z","submitted_at":"2022-11-09T18:08:53Z","title":"Prompting Large Pre-trained Vision-Language Models For Compositional Concept Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.05077","snapshot_observed_at":"2026-08-06T22:40:36.070333Z","title":"Prompting large pre-trained vision-language models for compositional concept learning.arXiv preprint arXiv:2211.05077, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.070333Z"},"links":{"cited_paper":"/paper/2211.05077","citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:5e0cbca4730b13fdfde6171777886ba5639174cf2ae942687298cd25869633e4","observation_id":"cb21e691-673f-41c2-9161-6eee88302e83","resolution":{"observed_at":"2026-08-06T22:40:36.070333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.217222Z","title":"Gipcol: Graph-injected soft prompting for compositional zero-shot learning","venue":null,"work_id":"efbabfec-65f6-4351-bcfa-55d59da9a654","year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.075818Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:03c9559788b006a66d5d8ef70f1b5d76a30d9a3eb892f25808c2885f621e42db","observation_id":"10772740-abe7-48df-b908-6f9380801ab5","resolution":{"observed_at":"2026-08-06T22:40:36.221231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.207803Z","title":"Fine-grained visual compar- isons with local learning","venue":null,"work_id":"07a6becb-a8bd-45db-a61d-2593e8795af4","year":2014},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.082123Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:67cd4dbf7b74985dbe179498d0cd4ce455d7fa913538c12d7df27ead62eabeec","observation_id":"e361c574-bdc8-4ed8-a73e-baa62c19bc3f","resolution":{"observed_at":"2026-08-06T22:40:36.211763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:40:36.088082Z","title":"Learning to prompt for vision-language models.In- ternational Journal of Computer Vision, 130(9):2337–2348,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:40:36.088082Z"},"links":{"citing_paper":"/paper/2506.20986"},"observation_digest":"sha256:f598b6a21809c9c8034490cced67cd293278f1d5214b2c98e54026232745f808","observation_id":"774ffad0-617e-4bcc-ae82-6dba06c5c980","resolution":{"observed_at":"2026-08-06T22:40:36.088082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.20986","last_updated":"2025-06-26T04:00:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T08:39:25.924074Z","submitted_at":"2025-06-26T04:00:55Z","title":"EVA: Mixture-of-Experts Semantic Variant Alignment for Compositional Zero-Shot Learning"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":2,"verified_fuzzy":21},"total_outbound_references":42},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2506.20986."}