{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6MUI2EJ37FTAYUORAMK3FCMUO2","short_pith_number":"pith:6MUI2EJ3","schema_version":"1.0","canonical_sha256":"f3288d113bf9660c51d10315b2899476926224c15ec6ff7fcfc0fd9de4814a16","source":{"kind":"arxiv","id":"2304.06906","version":3},"attestation_state":"computed","paper":{"title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Hao Pan, Jian-Yu Xiong, Peng-Shuai Wang, Xin Tong, Yang Liu, Yu-Qi Yang, Yu-Xiao Guo","submitted_at":"2023-04-14T02:49:08Z","abstract_excerpt":"The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\\SST}, for 3D indoor scene understanding. We design a 3D Swin transformer as our backbone network, which enables efficient self-attention on sparse voxels with linear memory complexity, making the backbone scalable to large models and datasets. We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point s"},"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":"2304.06906","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-14T02:49:08Z","cross_cats_sorted":[],"title_canon_sha256":"3b3a0bad6c519d19ee689deb74a189b1c0eef4be24386a2e1882075096f31a3b","abstract_canon_sha256":"7ec67fb0d0bfa4a40bbe74dcab47af10603cb577b7b85f983dbf635338d2a614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:48.735311Z","signature_b64":"CzJcok7S/y4qfZ/Lto5NQEe0sGXFW3f7evSvK8jkIaF2xAHfYgKeV6LHjVLKW15SWxOWCkN0UTx4+1ExwL+ECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3288d113bf9660c51d10315b2899476926224c15ec6ff7fcfc0fd9de4814a16","last_reissued_at":"2026-07-05T06:41:48.734624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:48.734624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Hao Pan, Jian-Yu Xiong, Peng-Shuai Wang, Xin Tong, Yang Liu, Yu-Qi Yang, Yu-Xiao Guo","submitted_at":"2023-04-14T02:49:08Z","abstract_excerpt":"The use of pretrained backbones with fine-tuning has been successful for 2D vision and natural language processing tasks, showing advantages over task-specific networks. In this work, we introduce a pretrained 3D backbone, called {\\SST}, for 3D indoor scene understanding. We design a 3D Swin transformer as our backbone network, which enables efficient self-attention on sparse voxels with linear memory complexity, making the backbone scalable to large models and datasets. We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06906","kind":"arxiv","version":3},"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/2304.06906/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":"2304.06906","created_at":"2026-07-05T06:41:48.734713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06906v3","created_at":"2026-07-05T06:41:48.734713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06906","created_at":"2026-07-05T06:41:48.734713+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MUI2EJ37FTA","created_at":"2026-07-05T06:41:48.734713+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MUI2EJ37FTAYUOR","created_at":"2026-07-05T06:41:48.734713+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MUI2EJ3","created_at":"2026-07-05T06:41:48.734713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25278","citing_title":"Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22200","citing_title":"OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15369","citing_title":"SemanticBridge - A Dataset for 3D Semantic Segmentation of Bridges and Domain Gap Analysis","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19609","citing_title":"Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07356","citing_title":"UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2","json":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2.json","graph_json":"https://pith.science/api/pith-number/6MUI2EJ37FTAYUORAMK3FCMUO2/graph.json","events_json":"https://pith.science/api/pith-number/6MUI2EJ37FTAYUORAMK3FCMUO2/events.json","paper":"https://pith.science/paper/6MUI2EJ3"},"agent_actions":{"view_html":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2","download_json":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2.json","view_paper":"https://pith.science/paper/6MUI2EJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06906&json=true","fetch_graph":"https://pith.science/api/pith-number/6MUI2EJ37FTAYUORAMK3FCMUO2/graph.json","fetch_events":"https://pith.science/api/pith-number/6MUI2EJ37FTAYUORAMK3FCMUO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2/action/storage_attestation","attest_author":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2/action/author_attestation","sign_citation":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2/action/citation_signature","submit_replication":"https://pith.science/pith/6MUI2EJ37FTAYUORAMK3FCMUO2/action/replication_record"}},"created_at":"2026-07-05T06:41:48.734713+00:00","updated_at":"2026-07-05T06:41:48.734713+00:00"}