{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UJYOVXV4GSGYARGVD3SZLZGYHC","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":"8daf9a0f6ce0cdb102a86701daa424e3cca6ca5b5fd84b7519a273525e12c48b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-04T04:56:57Z","title_canon_sha256":"6f5059b9edeff93da19bce1929bc8aef28d743ef52ab833a49f3a83f341e88f7"},"schema_version":"1.0","source":{"id":"2201.00978","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00978","created_at":"2026-07-05T03:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00978v1","created_at":"2026-07-05T03:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00978","created_at":"2026-07-05T03:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"UJYOVXV4GSGY","created_at":"2026-07-05T03:45:14Z"},{"alias_kind":"pith_short_16","alias_value":"UJYOVXV4GSGYARGV","created_at":"2026-07-05T03:45:14Z"},{"alias_kind":"pith_short_8","alias_value":"UJYOVXV4","created_at":"2026-07-05T03:45:14Z"}],"graph_snapshots":[{"event_id":"sha256:13a57f85e215521b82ff22a550e937edffa1b7d98c114f4f23fe43c3ad1d0431","target":"graph","created_at":"2026-07-05T03:45:14Z","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/2201.00978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer networks have achieved great progress for computer vision tasks. Transformer-in-Transformer (TNT) architecture utilizes inner transformer and outer transformer to extract both local and global representations. In this work, we present new TNT baselines by introducing two advanced designs: 1) pyramid architecture, and 2) convolutional stem. The new \"PyramidTNT\" significantly improves the original TNT by establishing hierarchical representations. PyramidTNT achieves better performances than the previous state-of-the-art vision transformers such as Swin Transformer. We hope this new b","authors_text":"Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-04T04:56:57Z","title":"PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00978","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:ecbb5838e7859229bc2d7444d8ee09573e1039955a6893a9bbeeea3ec5d2fe49","target":"record","created_at":"2026-07-05T03:45:14Z","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":"8daf9a0f6ce0cdb102a86701daa424e3cca6ca5b5fd84b7519a273525e12c48b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-04T04:56:57Z","title_canon_sha256":"6f5059b9edeff93da19bce1929bc8aef28d743ef52ab833a49f3a83f341e88f7"},"schema_version":"1.0","source":{"id":"2201.00978","kind":"arxiv","version":1}},"canonical_sha256":"a270eadebc348d8044d51ee595e4d838838eaad0cb0b15c25320785486ca846f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a270eadebc348d8044d51ee595e4d838838eaad0cb0b15c25320785486ca846f","first_computed_at":"2026-07-05T03:45:14.885927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:14.885927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3sEWiboQ5dG0nfgXka2a+bkdF9Gk1eHObEdtW/KP5MA9y0RRaTOl9WB0AEyv+dWgSAb9zt3JId2hghFo0XQTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:14.886385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.00978","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecbb5838e7859229bc2d7444d8ee09573e1039955a6893a9bbeeea3ec5d2fe49","sha256:13a57f85e215521b82ff22a550e937edffa1b7d98c114f4f23fe43c3ad1d0431"],"state_sha256":"abc5775d064b83fa72f76f277a4d4a85ecdf9f9b87a401492fc69d36d6728ee2"}