{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HYXCKNACDAHJD3KYJPJR2DPADC","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":"b46e0b0385acda30940a49069f3ccf85638a60b8ba54d9e92d226c8238762987","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-31T18:55:57Z","title_canon_sha256":"f0c2807cb2b87b370e44e9a1c1e5adf69e58893032de95c86029397f29b2db3d"},"schema_version":"1.0","source":{"id":"2012.15840","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15840","created_at":"2026-07-05T03:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15840v3","created_at":"2026-07-05T03:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15840","created_at":"2026-07-05T03:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"HYXCKNACDAHJ","created_at":"2026-07-05T03:00:29Z"},{"alias_kind":"pith_short_16","alias_value":"HYXCKNACDAHJD3KY","created_at":"2026-07-05T03:00:29Z"},{"alias_kind":"pith_short_8","alias_value":"HYXCKNAC","created_at":"2026-07-05T03:00:29Z"}],"graph_snapshots":[{"event_id":"sha256:28ccb5d908b844ffcf3f88cce4d4377bd0d3955a4d989baf70a269131a04eb9e","target":"graph","created_at":"2026-07-05T03:00:29Z","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/2012.15840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution and learns more abstract/semantic visual concepts with larger receptive fields. Since context modeling is critical for segmentation, the latest efforts have been focused on increasing the receptive field, through either dilated/atrous convolutions or inserting attention modules. However, the encoder-decoder based FCN architecture remains unchanged. In this paper, we aim to provide an alternative perspective by treatin","authors_text":"Hengshuang Zhao, Jiachen Lu, Jianfeng Feng, Li Zhang, Philip H.S. Torr, Sixiao Zheng, Tao Xiang, Xiatian Zhu, Yabiao Wang, Yanwei Fu, Zekun Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-31T18:55:57Z","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15840","kind":"arxiv","version":3},"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:a5c72d950defbda0eac6fbe9c0a677113a8f7b5025af21ceaca068767ab53184","target":"record","created_at":"2026-07-05T03:00:29Z","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":"b46e0b0385acda30940a49069f3ccf85638a60b8ba54d9e92d226c8238762987","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-31T18:55:57Z","title_canon_sha256":"f0c2807cb2b87b370e44e9a1c1e5adf69e58893032de95c86029397f29b2db3d"},"schema_version":"1.0","source":{"id":"2012.15840","kind":"arxiv","version":3}},"canonical_sha256":"3e2e253402180e91ed584bd31d0de018967df21a2bc4703b03b3d93ee88b0467","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e2e253402180e91ed584bd31d0de018967df21a2bc4703b03b3d93ee88b0467","first_computed_at":"2026-07-05T03:00:29.697377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:29.697377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2jwHNQNS6n9bJHMaxVKIhzuE6m7SDvIkgs3Dqv0GsZI/kJ+uDqmt1jIUZ1nRKsXSbLhby0pWH9SU7s0NVMr1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:29.697763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15840","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c72d950defbda0eac6fbe9c0a677113a8f7b5025af21ceaca068767ab53184","sha256:28ccb5d908b844ffcf3f88cce4d4377bd0d3955a4d989baf70a269131a04eb9e"],"state_sha256":"550ae55535445c69e94e7818cdd574990523f4903183647ee627ffdc101ee279"}