{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NSWVHLDMX6NUMCJEXCQ4LO3OKB","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":"325e3c606d820d6e4f15b23184cde653f533f3ea11798672857addc79e60a94b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-09T22:29:56Z","title_canon_sha256":"5400cd9f3850315eb1fe1db7369cdfcf61a04edff13a55de00357b05ec559b3a"},"schema_version":"1.0","source":{"id":"2306.06289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06289","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06289v2","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06289","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"NSWVHLDMX6NU","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"NSWVHLDMX6NUMCJE","created_at":"2026-07-05T06:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"NSWVHLDM","created_at":"2026-07-05T06:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:bdd866b62983966804ea5b0f0a2fdb394dc26490bd8117c9280e5c3e53913790","target":"graph","created_at":"2026-07-05T06:46:05Z","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/2306.06289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework and introduces \\textbf{SegViTv2}. In this study, we introduce a novel Attention-to-Mask (\\atm) module to design a lightweight decoder effective for plain ViT. The proposed ATM converts the global attention map into semantic masks for high-quality segmentation results. Our decoder outperforms the popular decoder UPerNet using various ViT backbones while consuming only about $5\\%$ of the computational cost. For the encoder, we address the concern of the relativ","authors_text":"Bowen Zhang, Chunhua Shen, Liyang Liu, Minh Hieu Phan, Yifan Liu, Zhi Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-09T22:29:56Z","title":"SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06289","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:c27fd14c5dfaae586f535cd5b3b4d7949edc96dacf5ca88960a71d4fa26b4ce9","target":"record","created_at":"2026-07-05T06:46:05Z","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":"325e3c606d820d6e4f15b23184cde653f533f3ea11798672857addc79e60a94b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-09T22:29:56Z","title_canon_sha256":"5400cd9f3850315eb1fe1db7369cdfcf61a04edff13a55de00357b05ec559b3a"},"schema_version":"1.0","source":{"id":"2306.06289","kind":"arxiv","version":2}},"canonical_sha256":"6cad53ac6cbf9b460924b8a1c5bb6e506c3e7f74fdf86b3476ffc0abb6003f8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cad53ac6cbf9b460924b8a1c5bb6e506c3e7f74fdf86b3476ffc0abb6003f8a","first_computed_at":"2026-07-05T06:46:05.853245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:05.853245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bWvF6jlqERUTGjTogWPfVfrsgC+9emm9uQ1tnJ1v0Vz8eZuRTZFT6arl+oIZWZ225N7cAFvGEdzKID18hmilAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:05.853732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c27fd14c5dfaae586f535cd5b3b4d7949edc96dacf5ca88960a71d4fa26b4ce9","sha256:bdd866b62983966804ea5b0f0a2fdb394dc26490bd8117c9280e5c3e53913790"],"state_sha256":"25149abb240573259183a51d88d5a1ae0a42880f80fba61e6a4d763e07c926ac"}