{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VAALX4RGFJVMGXDE6PXNV2ZLWB","short_pith_number":"pith:VAALX4RG","schema_version":"1.0","canonical_sha256":"a800bbf2262a6ac35c64f3eedaeb2bb0618b6e296a59c45518c4790d0091a497","source":{"kind":"arxiv","id":"2205.14949","version":1},"attestation_state":"computed","paper":{"title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingxi Xie, Qi Dai, Qi Tian, Qixiang Ye, Wei Huang, Xiaosong Zhang, Yunjie Tian","submitted_at":"2022-05-30T09:34:44Z","abstract_excerpt":"Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e.g., ViT), albeit hierarchical vision transformers (e.g., Swin Transformer) have potentially better properties in formulating vision inputs. In this paper, we offer a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) that enjoys both high effici"},"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":"2205.14949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T09:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"dca1784bc332e9f377b4eacd190551c7b21bf6739b21e1099bace595b989ded5","abstract_canon_sha256":"823a3fef8133e70a5c3d74ef62d8200bf921c9a611de6296c9dc1a3f0c523e98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:22.769309Z","signature_b64":"CpFEj1vpDABjd6jBaAR7R4AePHcMWq6OXELDZFvsGdSUiotXsX/FczHmP3hPVNCNmtZTLxWdFicWGKpJDN5DCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a800bbf2262a6ac35c64f3eedaeb2bb0618b6e296a59c45518c4790d0091a497","last_reissued_at":"2026-07-05T04:27:22.768902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:22.768902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingxi Xie, Qi Dai, Qi Tian, Qixiang Ye, Wei Huang, Xiaosong Zhang, Yunjie Tian","submitted_at":"2022-05-30T09:34:44Z","abstract_excerpt":"Recently, masked image modeling (MIM) has offered a new methodology of self-supervised pre-training of vision transformers. A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e.g., ViT), albeit hierarchical vision transformers (e.g., Swin Transformer) have potentially better properties in formulating vision inputs. In this paper, we offer a new design of hierarchical vision transformers named HiViT (short for Hierarchical ViT) that enjoys both high effici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14949","kind":"arxiv","version":1},"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/2205.14949/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":"2205.14949","created_at":"2026-07-05T04:27:22.768960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14949v1","created_at":"2026-07-05T04:27:22.768960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14949","created_at":"2026-07-05T04:27:22.768960+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAALX4RGFJVM","created_at":"2026-07-05T04:27:22.768960+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAALX4RGFJVMGXDE","created_at":"2026-07-05T04:27:22.768960+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAALX4RG","created_at":"2026-07-05T04:27:22.768960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03716","citing_title":"Unified Multimodal Visual Tracking with Dual Mixture-of-Experts","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB","json":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB.json","graph_json":"https://pith.science/api/pith-number/VAALX4RGFJVMGXDE6PXNV2ZLWB/graph.json","events_json":"https://pith.science/api/pith-number/VAALX4RGFJVMGXDE6PXNV2ZLWB/events.json","paper":"https://pith.science/paper/VAALX4RG"},"agent_actions":{"view_html":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB","download_json":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB.json","view_paper":"https://pith.science/paper/VAALX4RG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14949&json=true","fetch_graph":"https://pith.science/api/pith-number/VAALX4RGFJVMGXDE6PXNV2ZLWB/graph.json","fetch_events":"https://pith.science/api/pith-number/VAALX4RGFJVMGXDE6PXNV2ZLWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB/action/storage_attestation","attest_author":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB/action/author_attestation","sign_citation":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB/action/citation_signature","submit_replication":"https://pith.science/pith/VAALX4RGFJVMGXDE6PXNV2ZLWB/action/replication_record"}},"created_at":"2026-07-05T04:27:22.768960+00:00","updated_at":"2026-07-05T04:27:22.768960+00:00"}