{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UMHKMXSXIC2G7NK7Y5RZ2MQYAN","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":"f77e9d35f4dc01375e73c08ebaeaceb6a569edb96419da618d9425e2cf24ab75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T00:30:26Z","title_canon_sha256":"55239549117a66dec03dbc093e1b90ba611530e8bf19e8a875c9d45f58cd1a94"},"schema_version":"1.0","source":{"id":"2210.05844","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05844","created_at":"2026-07-05T05:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05844v2","created_at":"2026-07-05T05:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05844","created_at":"2026-07-05T05:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"UMHKMXSXIC2G","created_at":"2026-07-05T05:24:14Z"},{"alias_kind":"pith_short_16","alias_value":"UMHKMXSXIC2G7NK7","created_at":"2026-07-05T05:24:14Z"},{"alias_kind":"pith_short_8","alias_value":"UMHKMXSX","created_at":"2026-07-05T05:24:14Z"}],"graph_snapshots":[{"event_id":"sha256:3855f3ef95363b82a4a1586db36b5170d05b528e28fad04ed1dee9ac041e19ff","target":"graph","created_at":"2026-07-05T05:24:14Z","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/2210.05844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the","authors_text":"Bowen Zhang, Chunhua Shen, Quan Tang, Xiangxiang Chu, Xiaolin Wei, Yifan Liu, Zhi Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T00:30:26Z","title":"SegViT: Semantic Segmentation with Plain Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05844","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:b1cac016d4ae9ad978f37ce48006e0864384c99ee9f1256ed8c69bfdffb94e9d","target":"record","created_at":"2026-07-05T05:24:14Z","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":"f77e9d35f4dc01375e73c08ebaeaceb6a569edb96419da618d9425e2cf24ab75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T00:30:26Z","title_canon_sha256":"55239549117a66dec03dbc093e1b90ba611530e8bf19e8a875c9d45f58cd1a94"},"schema_version":"1.0","source":{"id":"2210.05844","kind":"arxiv","version":2}},"canonical_sha256":"a30ea65e5740b46fb55fc7639d3218035516e2fec9ca5873110bb29ff9f6b36f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a30ea65e5740b46fb55fc7639d3218035516e2fec9ca5873110bb29ff9f6b36f","first_computed_at":"2026-07-05T05:24:14.457819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:14.457819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/6YissAO4f+M3FkxfkbWMrUiTRYkQRh7y0wHuoCMDX6jppmrajvH0WTE8mjThoe2Zhf4OyKOUMwNo/DrPfpfDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:14.458238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05844","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1cac016d4ae9ad978f37ce48006e0864384c99ee9f1256ed8c69bfdffb94e9d","sha256:3855f3ef95363b82a4a1586db36b5170d05b528e28fad04ed1dee9ac041e19ff"],"state_sha256":"9638f5bd6f19ef09fa44281ef9546fe847c14a6abeae5551721b984b8998ca92"}