{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VAALX4RGFJVMGXDE6PXNV2ZLWB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"823a3fef8133e70a5c3d74ef62d8200bf921c9a611de6296c9dc1a3f0c523e98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T09:34:44Z","title_canon_sha256":"dca1784bc332e9f377b4eacd190551c7b21bf6739b21e1099bace595b989ded5"},"schema_version":"1.0","source":{"id":"2205.14949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14949","created_at":"2026-07-05T04:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14949v1","created_at":"2026-07-05T04:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14949","created_at":"2026-07-05T04:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"VAALX4RGFJVM","created_at":"2026-07-05T04:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"VAALX4RGFJVMGXDE","created_at":"2026-07-05T04:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"VAALX4RG","created_at":"2026-07-05T04:27:22Z"}],"graph_snapshots":[{"event_id":"sha256:c4cb297e662f0625bc3e044bcbe25c03cf7ff3dd480961a3bb36683b94c19cdf","target":"graph","created_at":"2026-07-05T04:27:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2205.14949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lingxi Xie, Qi Dai, Qi Tian, Qixiang Ye, Wei Huang, Xiaosong Zhang, Yunjie Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T09:34:44Z","title":"HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14949","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc8c6df5914a30789bf60c980f87a0ee6107a0232d0b50b4928219c17a249f44","target":"record","created_at":"2026-07-05T04:27:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"823a3fef8133e70a5c3d74ef62d8200bf921c9a611de6296c9dc1a3f0c523e98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T09:34:44Z","title_canon_sha256":"dca1784bc332e9f377b4eacd190551c7b21bf6739b21e1099bace595b989ded5"},"schema_version":"1.0","source":{"id":"2205.14949","kind":"arxiv","version":1}},"canonical_sha256":"a800bbf2262a6ac35c64f3eedaeb2bb0618b6e296a59c45518c4790d0091a497","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a800bbf2262a6ac35c64f3eedaeb2bb0618b6e296a59c45518c4790d0091a497","first_computed_at":"2026-07-05T04:27:22.768902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:22.768902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CpFEj1vpDABjd6jBaAR7R4AePHcMWq6OXELDZFvsGdSUiotXsX/FczHmP3hPVNCNmtZTLxWdFicWGKpJDN5DCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:22.769309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc8c6df5914a30789bf60c980f87a0ee6107a0232d0b50b4928219c17a249f44","sha256:c4cb297e662f0625bc3e044bcbe25c03cf7ff3dd480961a3bb36683b94c19cdf"],"state_sha256":"ab06e1b8fffc070b3a2f309dae5e6abda0ee38ce9d6c63170b538ad53b951336"}