{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UGRR2E4FFZAX4WD4M5LRE6JRBH","short_pith_number":"pith:UGRR2E4F","canonical_record":{"source":{"id":"2105.12723","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T17:56:48Z","cross_cats_sorted":[],"title_canon_sha256":"697a28945859e66a5c67031323c6e72fc198830676bd33098cca3ff8072228a1","abstract_canon_sha256":"7133dbd0c283cfc5adf6af0e60bc7c6e3370810c2373468d1e888f75cf81d7e3"},"schema_version":"1.0"},"canonical_sha256":"a1a31d13852e417e587c675712793109c1e4ed31707c55accc01571379b8119e","source":{"kind":"arxiv","id":"2105.12723","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.12723","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2105.12723v4","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12723","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"UGRR2E4FFZAX","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"UGRR2E4FFZAX4WD4","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"UGRR2E4F","created_at":"2026-07-05T03:44:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UGRR2E4FFZAX4WD4M5LRE6JRBH","target":"record","payload":{"canonical_record":{"source":{"id":"2105.12723","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T17:56:48Z","cross_cats_sorted":[],"title_canon_sha256":"697a28945859e66a5c67031323c6e72fc198830676bd33098cca3ff8072228a1","abstract_canon_sha256":"7133dbd0c283cfc5adf6af0e60bc7c6e3370810c2373468d1e888f75cf81d7e3"},"schema_version":"1.0"},"canonical_sha256":"a1a31d13852e417e587c675712793109c1e4ed31707c55accc01571379b8119e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:29.508220Z","signature_b64":"XRB4oIV4RmluPXt/ZHQJs7ky6hM8FgTGEX6pyfL/gOw1YouI/2WM7aGqkMAPPNjPbaopRu8OtRJibnIlNJdbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1a31d13852e417e587c675712793109c1e4ed31707c55accc01571379b8119e","last_reissued_at":"2026-07-05T03:44:29.507837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:29.507837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.12723","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGXlNls7pVujU86YXhsmDfJkqnlTFKwEYT5lCML/IWSEPjDdipFTh31i8nvGK25LSgvscuQmfDa54ku9IOurAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T07:58:43.968024Z"},"content_sha256":"e8487266e6b48691479c29da1ab4054e2eef16da781143cb281b47b6b9f1e73f","schema_version":"1.0","event_id":"sha256:e8487266e6b48691479c29da1ab4054e2eef16da781143cb281b47b6b9f1e73f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UGRR2E4FFZAX4WD4M5LRE6JRBH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhang, Long Zhao, Sercan O. Arik, Ting Chen, Tomas Pfister, Zizhao Zhang","submitted_at":"2021-05-26T17:56:48Z","abstract_excerpt":"Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-select"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12723","kind":"arxiv","version":4},"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/2105.12723/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uTIlRKa3YGGFClucrrt5wPLxameuAtdVYy3qOKarFTrKte/kchf6ov49E/esH2ypKpr+jgH05gfHDna2egWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T07:58:43.968391Z"},"content_sha256":"1796a6bcbe76e855173af73e73e7b801c602c3ea08f37cd0df1c6e70c890af25","schema_version":"1.0","event_id":"sha256:1796a6bcbe76e855173af73e73e7b801c602c3ea08f37cd0df1c6e70c890af25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH/bundle.json","state_url":"https://pith.science/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-18T07:58:43Z","links":{"resolver":"https://pith.science/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH","bundle":"https://pith.science/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH/bundle.json","state":"https://pith.science/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGRR2E4FFZAX4WD4M5LRE6JRBH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UGRR2E4FFZAX4WD4M5LRE6JRBH","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":"7133dbd0c283cfc5adf6af0e60bc7c6e3370810c2373468d1e888f75cf81d7e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T17:56:48Z","title_canon_sha256":"697a28945859e66a5c67031323c6e72fc198830676bd33098cca3ff8072228a1"},"schema_version":"1.0","source":{"id":"2105.12723","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.12723","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2105.12723v4","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12723","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"UGRR2E4FFZAX","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"UGRR2E4FFZAX4WD4","created_at":"2026-07-05T03:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"UGRR2E4F","created_at":"2026-07-05T03:44:29Z"}],"graph_snapshots":[{"event_id":"sha256:1796a6bcbe76e855173af73e73e7b801c602c3ea08f37cd0df1c6e70c890af25","target":"graph","created_at":"2026-07-05T03:44:29Z","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/2105.12723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-select","authors_text":"Han Zhang, Long Zhao, Sercan O. Arik, Ting Chen, Tomas Pfister, Zizhao Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T17:56:48Z","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12723","kind":"arxiv","version":4},"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:e8487266e6b48691479c29da1ab4054e2eef16da781143cb281b47b6b9f1e73f","target":"record","created_at":"2026-07-05T03:44:29Z","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":"7133dbd0c283cfc5adf6af0e60bc7c6e3370810c2373468d1e888f75cf81d7e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-26T17:56:48Z","title_canon_sha256":"697a28945859e66a5c67031323c6e72fc198830676bd33098cca3ff8072228a1"},"schema_version":"1.0","source":{"id":"2105.12723","kind":"arxiv","version":4}},"canonical_sha256":"a1a31d13852e417e587c675712793109c1e4ed31707c55accc01571379b8119e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1a31d13852e417e587c675712793109c1e4ed31707c55accc01571379b8119e","first_computed_at":"2026-07-05T03:44:29.507837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:44:29.507837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XRB4oIV4RmluPXt/ZHQJs7ky6hM8FgTGEX6pyfL/gOw1YouI/2WM7aGqkMAPPNjPbaopRu8OtRJibnIlNJdbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:44:29.508220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.12723","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8487266e6b48691479c29da1ab4054e2eef16da781143cb281b47b6b9f1e73f","sha256:1796a6bcbe76e855173af73e73e7b801c602c3ea08f37cd0df1c6e70c890af25"],"state_sha256":"7c91623f59536a116b68b4834be339f5eece7be6016d68c0d81e58c935de4176"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2z0LMNYXiMlXkaICKT49Rlvt7UxuwMdHWxORCMWmcej1cgpOW3yCgLEMndmX+tHwFUm850CoDRaqfNs5dXMdAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T07:58:43.970407Z","bundle_sha256":"8d547b24d8f9aa4186387ff3f5965ef5b509a5c449a0e0baa2f368fa7c3b15a2"}}