{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AX2UTUT44R2AR3BWSYG2FMSDVU","short_pith_number":"pith:AX2UTUT4","schema_version":"1.0","canonical_sha256":"05f549d27ce47408ec36960da2b243ad1ea8fc1662aedf39ab3905ed779aac3c","source":{"kind":"arxiv","id":"2312.06272","version":1},"attestation_state":"computed","paper":{"title":"U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Julian von Klitzing, Seul-Ki Yeom","submitted_at":"2023-12-11T10:19:42Z","abstract_excerpt":"Semantic segmentation has witnessed remarkable advancements with the adaptation of the Transformer architecture. Parallel to the strides made by the Transformer, CNN-based U-Net has seen significant progress, especially in high-resolution medical imaging and remote sensing. This dual success inspired us to merge the strengths of both, leading to the inception of a U-Net-based vision transformer decoder tailored for efficient contextual encoding. Here, we propose a novel transformer decoder, U-MixFormer, built upon the U-Net structure, designed for efficient semantic segmentation. Our approach "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.06272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T10:19:42Z","cross_cats_sorted":[],"title_canon_sha256":"ff95974c48264b9cbcacd561280763c548f6634aec6dda1851d26914b19310a6","abstract_canon_sha256":"e551c4196538014e63ea18392be882348a7b15a2d33de78efe64a67c8394b458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:41.774059Z","signature_b64":"z2N9Asa6tktmAJpipftC/6cStd4VwYYJPrKgyai3dlwsb3XgWdDSXH1g4OlFz6wGLOlZqxwasddHb0QHVG6DBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f549d27ce47408ec36960da2b243ad1ea8fc1662aedf39ab3905ed779aac3c","last_reissued_at":"2026-07-05T07:22:41.773576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:41.773576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U-MixFormer: UNet-like Transformer with Mix-Attention for Efficient Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Julian von Klitzing, Seul-Ki Yeom","submitted_at":"2023-12-11T10:19:42Z","abstract_excerpt":"Semantic segmentation has witnessed remarkable advancements with the adaptation of the Transformer architecture. Parallel to the strides made by the Transformer, CNN-based U-Net has seen significant progress, especially in high-resolution medical imaging and remote sensing. This dual success inspired us to merge the strengths of both, leading to the inception of a U-Net-based vision transformer decoder tailored for efficient contextual encoding. Here, we propose a novel transformer decoder, U-MixFormer, built upon the U-Net structure, designed for efficient semantic segmentation. Our approach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06272","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.06272/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.06272","created_at":"2026-07-05T07:22:41.773635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06272v1","created_at":"2026-07-05T07:22:41.773635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06272","created_at":"2026-07-05T07:22:41.773635+00:00"},{"alias_kind":"pith_short_12","alias_value":"AX2UTUT44R2A","created_at":"2026-07-05T07:22:41.773635+00:00"},{"alias_kind":"pith_short_16","alias_value":"AX2UTUT44R2AR3BW","created_at":"2026-07-05T07:22:41.773635+00:00"},{"alias_kind":"pith_short_8","alias_value":"AX2UTUT4","created_at":"2026-07-05T07:22:41.773635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.17061","citing_title":"SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU","json":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU.json","graph_json":"https://pith.science/api/pith-number/AX2UTUT44R2AR3BWSYG2FMSDVU/graph.json","events_json":"https://pith.science/api/pith-number/AX2UTUT44R2AR3BWSYG2FMSDVU/events.json","paper":"https://pith.science/paper/AX2UTUT4"},"agent_actions":{"view_html":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU","download_json":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU.json","view_paper":"https://pith.science/paper/AX2UTUT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06272&json=true","fetch_graph":"https://pith.science/api/pith-number/AX2UTUT44R2AR3BWSYG2FMSDVU/graph.json","fetch_events":"https://pith.science/api/pith-number/AX2UTUT44R2AR3BWSYG2FMSDVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU/action/storage_attestation","attest_author":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU/action/author_attestation","sign_citation":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU/action/citation_signature","submit_replication":"https://pith.science/pith/AX2UTUT44R2AR3BWSYG2FMSDVU/action/replication_record"}},"created_at":"2026-07-05T07:22:41.773635+00:00","updated_at":"2026-07-05T07:22:41.773635+00:00"}