{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SYYHQQDXFOBSZHEBPDRTIGVVI3","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":"f40f724b8575e3803e8297b043269036ad155440563919749b3b568b4c337504","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T19:49:52Z","title_canon_sha256":"1aee61d908d2aa4aa28e9c56f67930157c6d240c206f90b6b0ebbdf95720d975"},"schema_version":"1.0","source":{"id":"2111.01236","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.01236","created_at":"2026-07-05T03:34:08Z"},{"alias_kind":"arxiv_version","alias_value":"2111.01236v2","created_at":"2026-07-05T03:34:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01236","created_at":"2026-07-05T03:34:08Z"},{"alias_kind":"pith_short_12","alias_value":"SYYHQQDXFOBS","created_at":"2026-07-05T03:34:08Z"},{"alias_kind":"pith_short_16","alias_value":"SYYHQQDXFOBSZHEB","created_at":"2026-07-05T03:34:08Z"},{"alias_kind":"pith_short_8","alias_value":"SYYHQQDX","created_at":"2026-07-05T03:34:08Z"}],"graph_snapshots":[{"event_id":"sha256:010d8945d087aed807c99469063559ed0cfabc297abe98c54ea5b0e4d87c5e8f","target":"graph","created_at":"2026-07-05T03:34:08Z","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/2111.01236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViTs) have emerged with superior performance on computer vision tasks compared to convolutional neural network (CNN)-based models. However, ViTs are mainly designed for image classification that generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs. Therefore, we propose HRViT, which enhances ViTs to learn semantically-rich and spatially-precise multi-scale representations by integrating high-resolution multi-branch architectures with ViTs. We balance the model performance and efficiency ","authors_text":"David Z. Pan, Dilin Wang, Hyoukjun Kwon, Jiaqi Gu, Liangzhen Lai, Meng Li, Vikas Chandra, Wei Ye, Yu-hsin Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T19:49:52Z","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01236","kind":"arxiv","version":2},"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:a6c22aa573248b3d01895796a685d8539243a07a539981ce8e0c6c176625b637","target":"record","created_at":"2026-07-05T03:34:08Z","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":"f40f724b8575e3803e8297b043269036ad155440563919749b3b568b4c337504","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T19:49:52Z","title_canon_sha256":"1aee61d908d2aa4aa28e9c56f67930157c6d240c206f90b6b0ebbdf95720d975"},"schema_version":"1.0","source":{"id":"2111.01236","kind":"arxiv","version":2}},"canonical_sha256":"96307840772b832c9c8178e3341ab546f47774d5c5beefee6367d9683b4f2482","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96307840772b832c9c8178e3341ab546f47774d5c5beefee6367d9683b4f2482","first_computed_at":"2026-07-05T03:34:08.398361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:08.398361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+aniwz7PKizlR0tXb+3HB+whkVPPJH5PJMvYT9n+SUWTWNu3WBr4T/yMLwqCyivc3H+Y5YU43Yy641J9l3sAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:08.398891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.01236","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6c22aa573248b3d01895796a685d8539243a07a539981ce8e0c6c176625b637","sha256:010d8945d087aed807c99469063559ed0cfabc297abe98c54ea5b0e4d87c5e8f"],"state_sha256":"be6cecb0c02fd19e3f7de8eb9091ec5356d5de5f5932d18aa6d141ec5e6ead9f"}