{"as_of":"2026-08-07T23:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:861e0599f8bb11ac9892ba2d73bd44ebd4dea0b8c2fdf694668dd0a854be28a5","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":17,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":17,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":17,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:30:15.451054Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T20:00:07.706004Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-07T11:30:15.451054Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding.arXiv preprint arXiv:2304.06906,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02396","last_updated":"2025-06-03T03:23:43Z","snapshot_observed_at":"2026-08-07T11:22:36.104704Z","submitted_at":"2025-06-03T03:23:43Z","title":"Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T11:30:15.451054Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2506.02396"},"observation_digest":"sha256:beab48ad9e95301da5efeb3675a24b0bd6994d7e5f9dba6e6018b12d32687f13","observation_id":"331dbfe2-7400-4b18-9e50-5957f1ec1cba","resolution":{"observed_at":"2026-08-07T11:30:15.451054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-07T05:05:33.623154Z","title":"arXiv preprint arXiv:2304.06906 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.08979","last_updated":"2025-07-25T02:19:55Z","snapshot_observed_at":"2026-08-07T04:55:23.886746Z","submitted_at":"2025-06-10T16:48:27Z","title":"Towards Generalized Range-View LiDAR Segmentation in Adverse Weather","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:05:33.623154Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2506.08979"},"observation_digest":"sha256:770932f33db50acc3651f2cff4c206c98f23130184435bc1103693463bfc0f5d","observation_id":"74dbfbab-76b6-460e-9927-e5e2ad1601c1","resolution":{"observed_at":"2026-08-07T05:05:33.623154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-07T04:41:03.183247Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09952","last_updated":"2025-06-11T17:23:21Z","snapshot_observed_at":"2026-08-07T04:34:37.263376Z","submitted_at":"2025-06-11T17:23:21Z","title":"UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T04:41:03.183247Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2506.09952"},"observation_digest":"sha256:a74f2f92765a1c9d1ee607a3e62ff808b3964e6cd3bce130afddc0f348d857d3","observation_id":"9743ce23-6a1b-4d17-bb02-053fe55bdd20","resolution":{"observed_at":"2026-08-07T04:41:03.183247Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-06T22:26:50.804049Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21724","last_updated":"2025-06-26T19:17:10Z","snapshot_observed_at":"2026-08-06T22:18:02.271659Z","submitted_at":"2025-06-26T19:17:10Z","title":"Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T22:26:50.804049Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2506.21724"},"observation_digest":"sha256:14aaaa48fb86c91066e3822a361d33e6709355b61172bd4787b006a2237fd0b9","observation_id":"78453dc5-e387-475d-86d9-4516536e72cc","resolution":{"observed_at":"2026-08-06T22:26:50.804049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-06T19:50:23.580652Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13364","last_updated":"2025-07-06T18:51:22Z","snapshot_observed_at":"2026-08-06T19:43:47.990764Z","submitted_at":"2025-07-06T18:51:22Z","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T19:50:23.580652Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2507.13364"},"observation_digest":"sha256:22c7b520f2d0d5f85f822a97847f36aad3b53d4e7ce0d03766b36c6ec99ca4d3","observation_id":"f955fc72-ae65-4e44-bf53-cb3a6af81b53","resolution":{"observed_at":"2026-08-06T19:50:23.580652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-06T14:35:41.145174Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18575","last_updated":"2025-07-24T16:48:50Z","snapshot_observed_at":"2026-08-06T14:35:40.463338Z","submitted_at":"2025-07-24T16:48:50Z","title":"HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T14:35:41.145174Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2507.18575"},"observation_digest":"sha256:647d093b9b341d25739059a76f8fea715dbdc0f4c3d360db17ceecf0d13addc6","observation_id":"810e0957-57a8-40af-864a-1bd2b624a40e","resolution":{"observed_at":"2026-08-06T14:35:41.145174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-06T14:04:42.705551Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.19778","last_updated":"2025-07-26T04:04:22Z","snapshot_observed_at":"2026-08-06T14:04:38.317156Z","submitted_at":"2025-07-26T04:04:22Z","title":"HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T14:04:42.705551Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2507.19778"},"observation_digest":"sha256:7fc06c7d69bf98387a2b566a0a79d45ae13a6bb7ca7f511446a5edcf2fb8ab2f","observation_id":"fa010226-72b3-4531-a03d-dfd4e6b30ab1","resolution":{"observed_at":"2026-08-06T14:04:42.705551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-06T10:47:41.298899Z","title":"Swin3d++: Effec- tive multi-source pretraining for 3d indoor scene understand- ing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.23480","last_updated":"2025-07-31T12:02:40Z","snapshot_observed_at":"2026-08-06T10:47:39.563445Z","submitted_at":"2025-07-31T12:02:40Z","title":"FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T10:47:41.298899Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2507.23480"},"observation_digest":"sha256:16bb966643a998fd2a76ab17e1d29acad0c4081b38ec0e352b8759491e4798e0","observation_id":"cea7ae9c-38f3-4f5f-b16b-5849ffc1b58e","resolution":{"observed_at":"2026-08-06T10:47:41.298899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-06T05:58:28.438085Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.01045","last_updated":"2025-08-01T19:52:34Z","snapshot_observed_at":"2026-08-06T05:58:23.864890Z","submitted_at":"2025-08-01T19:52:34Z","title":"Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T05:58:28.438085Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2508.01045"},"observation_digest":"sha256:4b58d418149440b3e88838f05f55ce0d82580f7cbec80f8b2c75443fd1636db8","observation_id":"f58cc6f0-0f41-444c-987a-1edc04ff38b7","resolution":{"observed_at":"2026-08-06T05:58:28.438085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-05T18:41:26.689238Z","title":", author Guo, Y.X","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.14373","last_updated":"2025-08-20T03:02:16Z","snapshot_observed_at":"2026-08-05T18:40:28.603811Z","submitted_at":"2025-08-20T03:02:16Z","title":"TCFNet: Bidirectional face-bone transformation via a Transformer-based coarse-to-fine point movement network","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-05T18:41:26.689238Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2508.14373"},"observation_digest":"sha256:e7bc96cb3d5b9dc9dcb62c60e969b160b5dde7eea4e05025b323d487fac7d62f","observation_id":"f7d42215-dc79-4cbf-9d82-fbfe427620ec","resolution":{"observed_at":"2026-08-05T18:41:26.689238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-04T20:59:55.803751Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08280","last_updated":"2025-09-10T04:37:00Z","snapshot_observed_at":"2026-08-04T20:59:53.301349Z","submitted_at":"2025-09-10T04:37:00Z","title":"Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T20:59:55.803751Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2509.08280"},"observation_digest":"sha256:75b8e9355ef358166b79c23b49bdeb4930b091be96c1c540884e39c9b67814af","observation_id":"4a433f2e-00fd-4857-9ef0-c65134969f13","resolution":{"observed_at":"2026-08-04T20:59:55.803751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-08-04T10:20:03.411541Z","title":"Swin3D : A Pretrained Transformer Backbone for 3D Indoor Scene Understanding , August 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.10779","last_updated":"2026-06-21T10:31:34Z","snapshot_observed_at":"2026-08-07T18:57:33.090661Z","submitted_at":"2025-10-12T19:49:51Z","title":"Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans","version":5},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-04T10:20:03.411541Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2510.10779"},"observation_digest":"sha256:efb405b6ecef3af2922454666f0b55ee07a4537e8bb2e1c1da0b4879317e8bbe","observation_id":"a9f14d39-00d8-4708-8ba1-be1347487c8f","resolution":{"observed_at":"2026-08-04T10:20:03.411541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":"2304.06906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-07-04T20:00:07.706004Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":"1da95348-62ae-427c-8103-c1cb88a04716","year":2023},"citing_paper":{"arxiv_id":"2512.15369","last_updated":"2025-12-18T08:59:38Z","snapshot_observed_at":"2026-08-06T17:02:59.688620Z","submitted_at":"2025-12-17T12:17:11Z","title":"SemanticBridge - A Dataset for 3D Semantic Segmentation of Bridges and Domain Gap Analysis","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-16T21:49:35.263131Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2512.15369"},"observation_digest":"sha256:de2b218eaffaa9b563e0e54df57a7cd8d5b9fcc91dca4ef6982a64be1eb49db1","observation_id":"7e753b5c-de43-4508-99cd-144360d78f9e","resolution":{"observed_at":"2026-05-16T21:51:17.704538Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":"2304.06906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-07-04T20:00:07.706004Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":"1da95348-62ae-427c-8103-c1cb88a04716","year":2023},"citing_paper":{"arxiv_id":"2604.19609","last_updated":"2026-04-21T15:56:26Z","snapshot_observed_at":"2026-08-03T15:00:15.869225Z","submitted_at":"2026-04-21T15:56:26Z","title":"Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T03:33:56.211514Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2604.19609"},"observation_digest":"sha256:c0c796a0bd4b14f6af5950afb6fcf3c82b34964bdadadcd25a7361b53f1b01d9","observation_id":"31b30ec6-c2ef-423f-a7bb-e488ab7596cf","resolution":{"observed_at":"2026-05-11T12:31:03.188092Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":"2304.06906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-07-04T20:00:07.706004Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":"1da95348-62ae-427c-8103-c1cb88a04716","year":2023},"citing_paper":{"arxiv_id":"2605.07356","last_updated":"2026-05-08T07:09:08Z","snapshot_observed_at":"2026-08-07T21:01:54.044517Z","submitted_at":"2026-05-08T07:09:08Z","title":"UniD-Shift: Towards Unified Semantic Segmentation via Interpretable Share-Private Multimodal Decomposition","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-11T01:47:00.687552Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2605.07356"},"observation_digest":"sha256:42a7532e301530ec18907d9924b9ee23d7f680149f120e4ac7c26decb490630b","observation_id":"3f374255-2a08-4173-a1f3-186007f830ef","resolution":{"observed_at":"2026-05-11T04:20:57.989238Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":"2304.06906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-07-04T20:00:07.706004Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":"1da95348-62ae-427c-8103-c1cb88a04716","year":2023},"citing_paper":{"arxiv_id":"2605.22200","last_updated":"2026-05-21T09:04:17Z","snapshot_observed_at":"2026-07-06T23:32:35.159280Z","submitted_at":"2026-05-21T09:04:17Z","title":"OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-22T07:58:54.140228Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2605.22200"},"observation_digest":"sha256:8a484a52de1352ea87b0caf41c9cf21750fd782f7be384fd55944fe0d773d3a8","observation_id":"5daefbc1-298f-4152-8ff5-b2a195fcf51c","resolution":{"observed_at":"2026-05-22T08:01:15.835705Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","version":3},"cited_work":{"arxiv_id":"2304.06906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2304.06906","snapshot_observed_at":"2026-07-04T20:00:07.706004Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding","venue":null,"work_id":"1da95348-62ae-427c-8103-c1cb88a04716","year":2023},"citing_paper":{"arxiv_id":"2606.25278","last_updated":"2026-06-24T01:31:22Z","snapshot_observed_at":"2026-08-07T00:32:23.060736Z","submitted_at":"2026-06-24T01:31:22Z","title":"Heterogeneous and Adept Snapshot Distillation for 3D Semantic Segmentation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-06-25T20:57:29.637599Z"},"links":{"cited_paper":"/paper/2304.06906","citing_paper":"/paper/2606.25278"},"observation_digest":"sha256:000a1c8747ea4a96d321cad6f426d82d479002cb329f310041691a99758454db","observation_id":"cc78dd0f-9073-43a1-9868-f9bb36f0a353","resolution":{"observed_at":"2026-07-04T20:00:07.709867Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2304.06906/citation-record","integrity":"/paper/2304.06906/integrity","json":"/paper/2304.06906/citation-record.json","paper":"/paper/2304.06906"},"outbound":[],"paper":{"arxiv_id":"2304.06906","last_updated":"2023-08-16T01:53:02Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:15:34.051890Z","submitted_at":"2023-04-14T02:49:08Z","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:2304.06906."}