{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6MUI2EJ37FTAYUORAMK3FCMUO2","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":"7ec67fb0d0bfa4a40bbe74dcab47af10603cb577b7b85f983dbf635338d2a614","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-14T02:49:08Z","title_canon_sha256":"3b3a0bad6c519d19ee689deb74a189b1c0eef4be24386a2e1882075096f31a3b"},"schema_version":"1.0","source":{"id":"2304.06906","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06906","created_at":"2026-07-05T06:41:48Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06906v3","created_at":"2026-07-05T06:41:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06906","created_at":"2026-07-05T06:41:48Z"},{"alias_kind":"pith_short_12","alias_value":"6MUI2EJ37FTA","created_at":"2026-07-05T06:41:48Z"},{"alias_kind":"pith_short_16","alias_value":"6MUI2EJ37FTAYUOR","created_at":"2026-07-05T06:41:48Z"},{"alias_kind":"pith_short_8","alias_value":"6MUI2EJ3","created_at":"2026-07-05T06:41:48Z"}],"graph_snapshots":[{"event_id":"sha256:d09b2c426a597275be7332106b4c8849c4ea6361676076250bcb382f72602189","target":"graph","created_at":"2026-07-05T06:41:48Z","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/2304.06906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baining Guo, Hao Pan, Jian-Yu Xiong, Peng-Shuai Wang, Xin Tong, Yang Liu, Yu-Qi Yang, Yu-Xiao Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06906","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:a1b9075b7970bd6a50e048754d15fb9f5be4365613488f91f9a5332af67c8b1e","target":"record","created_at":"2026-07-05T06:41:48Z","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":"7ec67fb0d0bfa4a40bbe74dcab47af10603cb577b7b85f983dbf635338d2a614","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-14T02:49:08Z","title_canon_sha256":"3b3a0bad6c519d19ee689deb74a189b1c0eef4be24386a2e1882075096f31a3b"},"schema_version":"1.0","source":{"id":"2304.06906","kind":"arxiv","version":3}},"canonical_sha256":"f3288d113bf9660c51d10315b2899476926224c15ec6ff7fcfc0fd9de4814a16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3288d113bf9660c51d10315b2899476926224c15ec6ff7fcfc0fd9de4814a16","first_computed_at":"2026-07-05T06:41:48.734624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:48.734624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CzJcok7S/y4qfZ/Lto5NQEe0sGXFW3f7evSvK8jkIaF2xAHfYgKeV6LHjVLKW15SWxOWCkN0UTx4+1ExwL+ECA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:48.735311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06906","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1b9075b7970bd6a50e048754d15fb9f5be4365613488f91f9a5332af67c8b1e","sha256:d09b2c426a597275be7332106b4c8849c4ea6361676076250bcb382f72602189"],"state_sha256":"e7c588728c3d252baac7b6b967e70a2bc6b12c37687b5ac5ee7bd66e6ab5dc35"}