{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XEUGIQTVRADBLDRDUNVDBHH67W","short_pith_number":"pith:XEUGIQTV","schema_version":"1.0","canonical_sha256":"b9286442758806158e23a36a309cfefd9eea3161b148ccbd6de3842ab9bffa67","source":{"kind":"arxiv","id":"2211.07636","version":2},"attestation_state":"computed","paper":{"title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Ledell Wu, Quan Sun, Tiejun Huang, Wen Wang, Xinggang Wang, Xinlong Wang, Yue Cao, Yuxin Fang","submitted_at":"2022-11-14T18:59:52Z","abstract_excerpt":"We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks, such as image recognition, video action recognition, object detection, instance segmentation and semantic segmentation without heavy supervised training. Moreo"},"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":"2211.07636","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T18:59:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d4f8edbf7916cec27b9d7be75c95e3e0657bb10f65e0fb81c58b589220537718","abstract_canon_sha256":"cb0402c4c4c4f391167651798e3f2ded7ba6210dd952587adbd857a6f7d79144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:12.493500Z","signature_b64":"UE+XBPOynPI88nFhrWxfrI7CGEFEeFUiFMC8sy33/RkG+4O9lmD/eAJLyfWtfc/qhQMNDGg4CFgXHcUN19qXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9286442758806158e23a36a309cfefd9eea3161b148ccbd6de3842ab9bffa67","last_reissued_at":"2026-07-05T05:22:12.493003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:12.493003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Ledell Wu, Quan Sun, Tiejun Huang, Wen Wang, Xinggang Wang, Xinlong Wang, Yue Cao, Yuxin Fang","submitted_at":"2022-11-14T18:59:52Z","abstract_excerpt":"We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks, such as image recognition, video action recognition, object detection, instance segmentation and semantic segmentation without heavy supervised training. Moreo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07636","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/2211.07636/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":"2211.07636","created_at":"2026-07-05T05:22:12.493059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07636v2","created_at":"2026-07-05T05:22:12.493059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07636","created_at":"2026-07-05T05:22:12.493059+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEUGIQTVRADB","created_at":"2026-07-05T05:22:12.493059+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEUGIQTVRADBLDRD","created_at":"2026-07-05T05:22:12.493059+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEUGIQTV","created_at":"2026-07-05T05:22:12.493059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.17323","citing_title":"XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11011","citing_title":"Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2310.09478","citing_title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","ref_index":12,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06500","citing_title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2303.15389","citing_title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2301.12597","citing_title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2304.10592","citing_title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W","json":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W.json","graph_json":"https://pith.science/api/pith-number/XEUGIQTVRADBLDRDUNVDBHH67W/graph.json","events_json":"https://pith.science/api/pith-number/XEUGIQTVRADBLDRDUNVDBHH67W/events.json","paper":"https://pith.science/paper/XEUGIQTV"},"agent_actions":{"view_html":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W","download_json":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W.json","view_paper":"https://pith.science/paper/XEUGIQTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07636&json=true","fetch_graph":"https://pith.science/api/pith-number/XEUGIQTVRADBLDRDUNVDBHH67W/graph.json","fetch_events":"https://pith.science/api/pith-number/XEUGIQTVRADBLDRDUNVDBHH67W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W/action/storage_attestation","attest_author":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W/action/author_attestation","sign_citation":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W/action/citation_signature","submit_replication":"https://pith.science/pith/XEUGIQTVRADBLDRDUNVDBHH67W/action/replication_record"}},"created_at":"2026-07-05T05:22:12.493059+00:00","updated_at":"2026-07-05T05:22:12.493059+00:00"}