{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MR5VZR5RFUPAZTYYDMKJXNSKDA","short_pith_number":"pith:MR5VZR5R","schema_version":"1.0","canonical_sha256":"647b5cc7b12d1e0ccf181b149bb64a18280c9ca4b1f0805eda4d45aa243db8d2","source":{"kind":"arxiv","id":"2303.11331","version":2},"attestation_state":"computed","paper":{"title":"EVA-02: A Visual Representation for Neon Genesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Quan Sun, Tiejun Huang, Xinggang Wang, Xinlong Wang, Yue Cao, Yuxin Fang","submitted_at":"2023-03-20T17:59:59Z","abstract_excerpt":"We launch EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling. With an updated plain Transformer architecture as well as extensive pre-training from an open & accessible giant CLIP vision encoder, EVA-02 demonstrates superior performance compared to prior state-of-the-art approaches across various representative vision tasks, while utilizing significantly fewer parameters and compute budgets. Notably, using exclusively publicly accessible training data, EVA-02 with only 304M pa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.11331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T17:59:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"eabed4e8a77cbb370f66cd3d3fe3ba078af4b6eecb750fa02a5302ec4c27e318","abstract_canon_sha256":"df36b0087b72d9474dfbe653f242bd4b576c800c0487f71c799c9a83a8baa628"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:50.941997Z","signature_b64":"pKMNSnndL7KS/+tewtoRniHGD85Zi9LIin43nNOTlbdWJ7n09crBWv0GP2d4u0rBqBrGAQf9GdwWX9RjnywECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"647b5cc7b12d1e0ccf181b149bb64a18280c9ca4b1f0805eda4d45aa243db8d2","last_reissued_at":"2026-07-05T08:50:50.941561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:50.941561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVA-02: A Visual Representation for Neon Genesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Quan Sun, Tiejun Huang, Xinggang Wang, Xinlong Wang, Yue Cao, Yuxin Fang","submitted_at":"2023-03-20T17:59:59Z","abstract_excerpt":"We launch EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling. With an updated plain Transformer architecture as well as extensive pre-training from an open & accessible giant CLIP vision encoder, EVA-02 demonstrates superior performance compared to prior state-of-the-art approaches across various representative vision tasks, while utilizing significantly fewer parameters and compute budgets. Notably, using exclusively publicly accessible training data, EVA-02 with only 304M pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11331","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.11331/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.11331","created_at":"2026-07-05T08:50:50.941613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11331v2","created_at":"2026-07-05T08:50:50.941613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11331","created_at":"2026-07-05T08:50:50.941613+00:00"},{"alias_kind":"pith_short_12","alias_value":"MR5VZR5RFUPA","created_at":"2026-07-05T08:50:50.941613+00:00"},{"alias_kind":"pith_short_16","alias_value":"MR5VZR5RFUPAZTYY","created_at":"2026-07-05T08:50:50.941613+00:00"},{"alias_kind":"pith_short_8","alias_value":"MR5VZR5R","created_at":"2026-07-05T08:50:50.941613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18543","citing_title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03879","citing_title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16401","citing_title":"CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16401","citing_title":"CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11710","citing_title":"Unlocking Compositional Generalization in Continual Few-Shot Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20085","citing_title":"Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06978","citing_title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11710","citing_title":"Unlocking Compositional Generalization in Continual Few-Shot Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2303.15389","citing_title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06525","citing_title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13305","citing_title":"Bias at the End of the Score","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10218","citing_title":"SMFormer: Empowering Self-supervised Stereo Matching via Foundation Models and Data Augmentation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07194","citing_title":"Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15451","citing_title":"Weak-to-Strong Knowledge Distillation Accelerates Visual Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18549","citing_title":"Advancing Vision Transformer with Enhanced Spatial Priors","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA","json":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA.json","graph_json":"https://pith.science/api/pith-number/MR5VZR5RFUPAZTYYDMKJXNSKDA/graph.json","events_json":"https://pith.science/api/pith-number/MR5VZR5RFUPAZTYYDMKJXNSKDA/events.json","paper":"https://pith.science/paper/MR5VZR5R"},"agent_actions":{"view_html":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA","download_json":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA.json","view_paper":"https://pith.science/paper/MR5VZR5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11331&json=true","fetch_graph":"https://pith.science/api/pith-number/MR5VZR5RFUPAZTYYDMKJXNSKDA/graph.json","fetch_events":"https://pith.science/api/pith-number/MR5VZR5RFUPAZTYYDMKJXNSKDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA/action/storage_attestation","attest_author":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA/action/author_attestation","sign_citation":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA/action/citation_signature","submit_replication":"https://pith.science/pith/MR5VZR5RFUPAZTYYDMKJXNSKDA/action/replication_record"}},"created_at":"2026-07-05T08:50:50.941613+00:00","updated_at":"2026-07-05T08:50:50.941613+00:00"}