{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR","short_pith_number":"pith:QTFWOPCZ","schema_version":"1.0","canonical_sha256":"84cb673c59d5a4886799d3d3a1f89a0c59fe0d51c1f179688ae84a1aae7b69d0","source":{"kind":"arxiv","id":"2112.11325","version":6},"attestation_state":"computed","paper":{"title":"iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marc Niethammer, Qin Liu, Yining Jiao, Zhenlin Xu","submitted_at":"2021-12-21T16:16:30Z","abstract_excerpt":"We propose iSegFormer, a memory-efficient transformer that combines a Swin transformer with a lightweight multilayer perceptron (MLP) decoder. With the efficient Swin transformer blocks for hierarchical self-attention and the simple MLP decoder for aggregating both local and global attention, iSegFormer learns powerful representations while achieving high computational efficiencies. Specifically, we apply iSegFormer to interactive 3D medical image segmentation."},"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":"2112.11325","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-21T16:16:30Z","cross_cats_sorted":[],"title_canon_sha256":"e9fd058bd89454ed7883fa63d78d2a4e786de92b955ccf2aacad94746219cc37","abstract_canon_sha256":"8ac9078c49b2694365a4d973c9e98d591eaade62185085d2e16eaff5508fac6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:49.247374Z","signature_b64":"TwcFMjMw7Y0DHBNbK76/CmKoXqj7/veeIjxEpUjaYCgOnHGxnXpqlrhzVtMM9tHwwb+YaPYcd+O1tRuFwiFKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84cb673c59d5a4886799d3d3a1f89a0c59fe0d51c1f179688ae84a1aae7b69d0","last_reissued_at":"2026-07-05T04:40:49.246886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:49.246886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Marc Niethammer, Qin Liu, Yining Jiao, Zhenlin Xu","submitted_at":"2021-12-21T16:16:30Z","abstract_excerpt":"We propose iSegFormer, a memory-efficient transformer that combines a Swin transformer with a lightweight multilayer perceptron (MLP) decoder. With the efficient Swin transformer blocks for hierarchical self-attention and the simple MLP decoder for aggregating both local and global attention, iSegFormer learns powerful representations while achieving high computational efficiencies. Specifically, we apply iSegFormer to interactive 3D medical image segmentation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11325","kind":"arxiv","version":6},"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/2112.11325/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":"2112.11325","created_at":"2026-07-05T04:40:49.246942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11325v6","created_at":"2026-07-05T04:40:49.246942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11325","created_at":"2026-07-05T04:40:49.246942+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTFWOPCZ2WSI","created_at":"2026-07-05T04:40:49.246942+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTFWOPCZ2WSIQZ4Z","created_at":"2026-07-05T04:40:49.246942+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTFWOPCZ","created_at":"2026-07-05T04:40:49.246942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02075","citing_title":"Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR","json":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR.json","graph_json":"https://pith.science/api/pith-number/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/graph.json","events_json":"https://pith.science/api/pith-number/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/events.json","paper":"https://pith.science/paper/QTFWOPCZ"},"agent_actions":{"view_html":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR","download_json":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR.json","view_paper":"https://pith.science/paper/QTFWOPCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11325&json=true","fetch_graph":"https://pith.science/api/pith-number/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/graph.json","fetch_events":"https://pith.science/api/pith-number/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/action/storage_attestation","attest_author":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/action/author_attestation","sign_citation":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/action/citation_signature","submit_replication":"https://pith.science/pith/QTFWOPCZ2WSIQZ4Z2PJ2D6E2BR/action/replication_record"}},"created_at":"2026-07-05T04:40:49.246942+00:00","updated_at":"2026-07-05T04:40:49.246942+00:00"}