{"as_of":"2026-08-05T06:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0dc45960dc4e8a1a0d35b312c3b59767976703d529e2782a27f077cd0cdce375","coverage":[{"denominator":111,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T05:25:19.181337Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T17:23:26.151875Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"cited_work":{"arxiv_id":"2605.10706","doi":"10.48550/arxiv.2605.10706","metadata_source":"pith","pith_arxiv_id":"2605.10706","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","venue":"cs.LG","work_id":"829b096d-35d8-4b7c-b206-ade1b630e8e6","year":2026},"citing_paper":{"arxiv_id":"2607.26369","last_updated":"2026-07-29T01:07:27Z","snapshot_observed_at":"2026-08-01T23:23:42.317591Z","submitted_at":"2026-07-29T01:07:27Z","title":"ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T17:23:26.151875Z"},"links":{"cited_paper":"/paper/2605.10706","citing_paper":"/paper/2607.26369"},"observation_digest":"sha256:786f1c1e9f26d0091651d6d4d45bd786163000f9f1de41b37c7e991334386975","observation_id":"0a693711-3644-466d-ab19-1443bb48c33b","resolution":{"observed_at":"2026-08-01T17:28:41.017250Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2605.10706/citation-record","integrity":"/paper/2605.10706/integrity","json":"/paper/2605.10706/citation-record.json","paper":"/paper/2605.10706"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d semantic parsing of large-scale indoor spaces","venue":null,"work_id":"c58673a2-b2db-42d5-ac5f-cb30c3005cc9","year":2016},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:412e5ee2498eb4729fccdda67860d770fb1d0fb58b9e069b710c412ebc99b95a","observation_id":"e17d7e73-234e-4264-b8ab-6100392617f4","resolution":{"observed_at":"2026-05-12T11:21:31.829584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.10091","last_updated":"2018-03-27T14:06:16Z","snapshot_observed_at":"2026-07-06T06:30:26.313049Z","submitted_at":"2018-03-27T14:06:16Z","title":"Point Convolutional Neural Networks by Extension Operators","version":1},"cited_work":{"arxiv_id":"1803.10091","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.10091","snapshot_observed_at":"2026-06-29T00:02:50.333901Z","title":"Point Convolutional Neural Networks by Extension Operators","venue":"cs.CV","work_id":"e4129df3-4a1e-4d8c-a731-19eb3d3a9aa2","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/1803.10091","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:82a629ac641a913da3416ab6aca45e1ca061197d8f6a50a13e0f6bdff94a6240","observation_id":"f026fd73-272c-4ea5-899b-32971ecf6a79","resolution":{"observed_at":"2026-05-12T05:26:24.085639Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multimae: Multi-modal multi-task masked autoencoders","venue":null,"work_id":"2b7a482a-74ea-40ff-a815-5271051f24ed","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:c3b66ca380316d2cd0b6eb156d02935c6a6e3e3cf11aed178bf16b5c68dfc987","observation_id":"ec9916ab-8d70-4254-8757-5060079bc15b","resolution":{"observed_at":"2026-05-12T11:21:31.822849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":"2004.05150","doi":"10.48550/arxiv.2004.05150","metadata_source":"pith","pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Longformer: The Long-Document Transformer","venue":"cs.CL","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:7e23ced00d298e5d6a840d13e96171c617b9bf7d37339ee6e2bd904eb85f6835","observation_id":"a0b870fb-2bab-4b42-b6fb-cc9cb766bafe","resolution":{"observed_at":"2026-05-12T05:26:24.093069Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-12T21:49:59.161233+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T21:49:59.161233+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T03:24:28.880148Z","title":"nuscenes: A multimodal dataset for autonomous driving","venue":null,"work_id":"2c148a70-8b96-49e6-b0fe-0566eac37bd0","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:d07024122174f3f40b261cb72cf5d1a5f4f7d9f3602234d2805eb18270196525","observation_id":"b9801d25-e6bb-4c05-81c6-a541af055f39","resolution":{"observed_at":"2026-05-12T11:21:31.840170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shapeconv: Shape-aware convolutional layer for indoor rgb-d semantic segmentation","venue":null,"work_id":"a304c94f-82b7-4bf9-9c35-0c9e797b188a","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:c78f7db2c56164e92f52a306ffc526ced12184665e71f0a0d1ec63ee18002d9a","observation_id":"80302894-b693-4be7-83ba-f5294f681713","resolution":{"observed_at":"2026-05-12T11:21:31.826174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Spatial information guided convolution for real-time rgbd semantic segmentation.IEEE Transactions on Image Processing, 30:2313–2324","venue":null,"work_id":"1b3b5b09-adc1-4108-84c8-2afa803495fd","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:0e56195ee973e587f80a67282a9e35519801b505095767e21edc1e31d6d4d4af","observation_id":"c5b92366-5b10-486f-9b2f-41259ea377f1","resolution":{"observed_at":"2026-05-12T11:21:31.843469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bi-directional cross-modality feature propagation with separation-and-aggregation gate for rgb-d semantic segmentation","venue":null,"work_id":"1707b109-9a97-4be8-a1d7-1c50de4b75b4","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:5962dc19c0edc9fc53271c4d6c7c9a6ead64bda1176641afd4fafa2ac2993bb6","observation_id":"598cf6bc-3379-459d-9fe7-856032dcd4a9","resolution":{"observed_at":"2026-05-12T11:21:31.833213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10555","last_updated":"2023-03-22T12:43:10Z","snapshot_observed_at":"2026-07-06T13:23:11.566484Z","submitted_at":"2022-06-21T17:35:57Z","title":"LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs","version":2},"cited_work":{"arxiv_id":"2206.10555","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.10555","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scaling up kernels in 3d cnns.arXiv preprint arXiv:2206.10555, 1(2):5","venue":null,"work_id":"4045a41f-cd1e-49eb-b69e-48950c75a9b5","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/2206.10555","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:58cf5082be762832d2ec5cd53dd1155da6933b454c48e41ca81ebc185d8c22bc","observation_id":"4129399c-55e2-44f7-9d97-63d529a055f9","resolution":{"observed_at":"2026-05-12T05:26:24.072977Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A unified point- based framework for 3d segmentation","venue":null,"work_id":"9ccc0139-1afb-4c93-8bb6-07ffda8ce0b9","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:4c5e3c93fff726849acdc6559eac667f12cfb20bab12a0a9e1851dc1301fbf79","observation_id":"4ed03fa7-f3d3-4860-9dc6-56236170963c","resolution":{"observed_at":"2026-05-12T11:21:31.846918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"From block-toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked transformers","venue":null,"work_id":"bece4e63-2b8f-4054-aee3-6a72f1321719","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:0e4b0b5249c1886cbb8576fd25b2a28244858b398041981783adeff9beb1daa7","observation_id":"35757edc-aad2-4a2e-a038-8274f53070d0","resolution":{"observed_at":"2026-05-12T11:21:31.836493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rethinking attention with performers","venue":null,"work_id":"094404cd-9b03-44fc-8500-b1f48aa4cb4d","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:54c319c697ee80fb65ada719be3b066ec89a10b91be51dabc1411a51eda32495","observation_id":"f7f2a44f-1f43-44f3-a788-8a84ee7eccb0","resolution":{"observed_at":"2026-05-12T11:21:31.660053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fast tree-field integra- tors: From low displacement rank to topological transformers","venue":null,"work_id":"cffaad15-ec10-474d-861d-4bf5b7e8e98b","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:090649f1bbf1bed83867dcf833897469470d3aa07fca0254f4946b9fcf8c5fad","observation_id":"d0cec2c3-1b19-4044-917d-502a298e1178","resolution":{"observed_at":"2026-05-12T11:21:31.669476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"4d spatio-temporal convnets: Minkowski convolutional neural networks","venue":null,"work_id":"83f9bad4-76da-4ff7-887b-c417fabb97e3","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:30f8b3d81b9f3c68b2b49e0f2498cc6d0b200b4a7b5b514efce7c38151dcfff2","observation_id":"74f2ab04-b33e-43f7-a604-944e8cad9325","resolution":{"observed_at":"2026-05-12T11:21:31.686249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T02:27:52.700504Z","title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes","venue":null,"work_id":"bd3ab136-ed56-4b8a-ad59-ce85a033bf3b","year":2017},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:2feb62a6249444bc74975526bb71949e0f18022cc2507f5fe623d981c9423b2f","observation_id":"99a9a0c6-b90b-4cfd-98fb-edc618c2f0f6","resolution":{"observed_at":"2026-05-12T11:21:31.708516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":"2010.11929","doi":"10.1175/jcli-d-22-0357.1","metadata_source":"pith","pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","venue":"cs.CV","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:d0b3bf6afc514bffcfb5a3827c67bf11610e89442dc1c28403914d2ad02d06f6","observation_id":"6181f4e7-bf31-4e82-8526-84e4922c22c3","resolution":{"observed_at":"2026-05-12T05:26:24.024617Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fast kernel methods: Sobolev, physics-informed, and additive models","venue":null,"work_id":"5ca5b861-4f52-4f60-8d19-3f733d41c159","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:561452c233ec27947ca32db2fba51a5708cd4943dc8b35b695f8d091b9741a70","observation_id":"102b2081-3244-4d19-8333-b6951bc32b53","resolution":{"observed_at":"2026-05-12T11:21:31.812747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Asymformer: Asymmetrical cross-modal representation learning for mobile platform real-time rgb-d se- mantic segmentation","venue":null,"work_id":"5d23f761-bd10-44ad-9fbe-85958b3dac12","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:de1005e0a139ddd8137c9f07d5f02bb2a0a4bfb05660b92eea991aad423fa0e4","observation_id":"5e9eaa7e-4741-4407-a7dd-9a723dc44340","resolution":{"observed_at":"2026-05-12T11:21:31.797886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"American Mathematical Soc","venue":null,"work_id":"b69f0a00-51cd-419a-a989-b58e1d2c8217","year":2009},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:7cac0dce7a441afd28fe67d33b85978282a1878b73bae27740c52352a7745093","observation_id":"550d0912-7f44-4055-a27d-cf663cf506a9","resolution":{"observed_at":"2026-05-12T11:21:31.774456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Omnivore: A single model for many visual modalities","venue":null,"work_id":"868c87bf-809b-43a6-b82d-b16bfa0d0037","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:256adc55c4226986271634040feb068fa631f10c77eb51c6b9d0b107cdfb52fa","observation_id":"45a5cd45-5b9f-49f4-8551-28660c2d98f1","resolution":{"observed_at":"2026-05-12T11:21:31.764700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d semantic segmentation with submanifold sparse convolutional networks","venue":null,"work_id":"0a967982-534e-4c02-9d0d-7a7e37510d89","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:d836bdd1fd8a85096cb628302fffa54276e42394a42dadafeaafb0928b56e89e","observation_id":"d4061575-af44-490d-a8b0-27e83045707f","resolution":{"observed_at":"2026-05-12T11:21:31.788069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Accelerating the nonuniform fast fourier transform.SIAM Review, 46(3):443–454","venue":null,"work_id":"4f266ea4-044b-479c-b2e8-bc6724f57266","year":2004},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f9814cc3cb5de6519264e4d2f9a4e5531f12b483ab49393802336fa88d952293","observation_id":"83213618-7939-4401-9c80-9cb860b4f599","resolution":{"observed_at":"2026-05-12T11:21:31.816688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Martin, and Shi-Min Hu","venue":null,"work_id":"681db873-b674-46a2-a4df-a22aba2d55ce","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:8b2ceb3ef7f76c838717046b1e4af77df10670068ca44275661076be82b2ecc7","observation_id":"711769c2-326f-4260-9f69-1d14d5c7e8e4","resolution":{"observed_at":"2026-05-12T11:21:31.734502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning rich features from rgb-d images for object detection and segmentation","venue":null,"work_id":"5abe393e-61fe-405d-b5ea-533e99389ea2","year":2014},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:84eb4b98b3f154319a000dbc55621d3d7279faf3fb5a7fabf997ca5966ccece0","observation_id":"414369c0-e02d-4b84-8058-412feb5d0ac2","resolution":{"observed_at":"2026-05-12T11:21:31.741098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deberta: Decoding-enhanced bert with disentangled attention","venue":null,"work_id":"1038941d-167c-4f2f-a5df-328343ee3508","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:9b841534a301b55a7129fafa223bb06d4b2866a65840eead9463cf3ce7fac250","observation_id":"b2e8fecb-8537-4721-98d6-7aff54c12c2a","resolution":{"observed_at":"2026-05-12T11:21:31.732443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point-to-voxel knowledge distillation for lidar semantic segmentation","venue":null,"work_id":"6bd61f18-fc73-4f58-a3e4-60aa24e8d1ba","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:3570ab993402f923629dbd10f6b4d65eae0f01b2f1754457101f6cabe559e89b","observation_id":"b449a578-4764-4b39-a91a-b2797286ba30","resolution":{"observed_at":"2026-05-12T11:21:31.727577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Acnet: Attention based network to exploit complementary features for rgbd semantic segmentation","venue":null,"work_id":"e7a2fb6d-a8f3-4b3c-906e-6d60dcba45e0","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:60b128b2bb4eaca2e26205799cdbd7686dd72184391f1c4b467b9e3427d52173","observation_id":"7f4ea39b-f4dd-4ab3-8990-e1d0a2cc440c","resolution":{"observed_at":"2026-05-12T11:21:31.730053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fourier position embedding: enhancing atten- tion’s periodic extension for length generalization","venue":null,"work_id":"fe48d0e3-7939-4e56-8afb-e8355e55685c","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:8c5f7e7bf657d860688479cc025c55ba15ad052c9dd243d5b0912ec069eedd11","observation_id":"a38593d8-d08f-47c8-8c37-3ff78cc929b7","resolution":{"observed_at":"2026-05-12T11:21:31.683515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hierarchical point-edge interaction network for point cloud semantic segmentation","venue":null,"work_id":"99c40aaf-bd04-4ef8-be8a-0b8f4db843a6","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:fef3c0f7e2ef3f60a5c71fedcc02407e71525af4583d790e626e54b12ef4c08e","observation_id":"157071bf-4987-4b20-b50a-161c588f053c","resolution":{"observed_at":"2026-05-12T11:21:31.711289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Transformers are rnns: fast autoregressive transformers with linear attention","venue":null,"work_id":"e10c192e-a1f7-451b-85f1-edfd5a66a1ea","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:e29b2d2640d099995ccb036d624d7bcab0516d6b1516d0de7a18726af6e95695","observation_id":"1648d094-a5fc-41f5-bac7-641f8c01b4ec","resolution":{"observed_at":"2026-05-12T11:21:31.758403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T15:26:18.882600Z","title":"Reformer: The efficient transformer","venue":null,"work_id":"adf0b21e-4f59-4801-b411-e1e6d7fe266e","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:b8e95fbc340c3541a852b84359f818b60d83eb621b0dde216ec3a32a94098444","observation_id":"1845b759-ea63-438a-909d-bbac0d612fd0","resolution":{"observed_at":"2026-05-12T11:21:31.751969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Rethinking range view representation for lidar segmentation","venue":null,"work_id":"9816cf22-c606-464c-9184-6de7e7bad0e6","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:c672b5b4ce0af9fdc348261d60901b1aa8aefd373ccd23d0a5e76e11ea421ba8","observation_id":"b02ec138-d15b-4c87-bd25-21a7d26f0881","resolution":{"observed_at":"2026-05-12T11:21:31.819730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Spherical transformer for lidar-based 3d recognition","venue":null,"work_id":"6c5e9853-8bcf-4dca-92b1-f37d4b456871","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:87514028a112a68baf02e95183062f813b39ad9d17301ecab5bcf9a5ab64347e","observation_id":"bf2c9ee1-b3a7-4c49-94df-c6f741965bd3","resolution":{"observed_at":"2026-05-12T11:21:31.630777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stratified transformer for 3d point cloud segmentation","venue":null,"work_id":"b57b4cbf-4f94-4d4d-bdaa-0b2cb1c7d22d","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:1dfde402f8cbd0768859eab520eefdebf6e46ff176384727936424bfe1efd159","observation_id":"bf52a95d-f37a-4b01-953a-1c5f98bc043a","resolution":{"observed_at":"2026-05-12T11:21:31.604567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Large-scale point cloud semantic segmentation with superpoint graphs","venue":null,"work_id":"9df6eb13-f4db-4a10-a848-9d183c761fe5","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:ef94d88e07839dcb559894ba3c75257f1908c3f086915472faf450389190cf2d","observation_id":"c0484989-e704-47dd-af02-0105838c668e","resolution":{"observed_at":"2026-05-12T11:21:31.784911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointgrid: A deep network for 3d shape understanding","venue":null,"work_id":"2bdd792a-c3ef-43c6-bace-e4bf5a8d447c","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:84867caa71aba40811b606a26b152bed66eb280f1bcdac0e82b0849526115043","observation_id":"8d8929dc-8e2a-45f2-b2c2-6abf6df7f393","resolution":{"observed_at":"2026-05-12T11:21:31.705875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Seggcn: Efficient 3d point cloud segmentation with fuzzy spherical kernel","venue":null,"work_id":"84816a2f-662c-45d7-915e-1cd25b736f6a","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:377b4ca64ebe5c8fdd62a80b069127c0c89fb72f64d1ccee29bee650c5210200","observation_id":"e7fa03f5-cd4d-4896-ac20-ca87273044ec","resolution":{"observed_at":"2026-05-12T11:21:31.553172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointcnn: Convolution on x-transformed points.Advances in neural information processing systems, 31","venue":null,"work_id":"9a292815-bce8-481c-b41f-5de9ad809454","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:6f1144ce3366457680778ebb0aa578607d60032dbe591498660322eab81b63ab","observation_id":"7c34d8ea-78fc-4c47-9bac-ad16866eed2f","resolution":{"observed_at":"2026-05-12T11:21:31.602020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pamba: enhancing global interaction in point clouds via state space model","venue":null,"work_id":"22c02184-513e-4dd1-b265-f248c1662043","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:e465f87a9bd5f363724c675ef4003f923fe5f87b125812620e96a251a72e703e","observation_id":"bcdcf909-a2d9-4e57-9726-49d229ba5092","resolution":{"observed_at":"2026-05-12T11:21:31.599428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointmamba: A simple state space model for point cloud analysis.Advances in neural information processing systems, 37:32653–32677","venue":null,"work_id":"6df7bc27-12ff-4776-ac53-252df0814780","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:8f333e50e5acb7f26294665d457a668857f81ec25b95886225b3ee05e083d7c1","observation_id":"6674da57-ccfd-4ba6-bd7e-7f5658c22a58","resolution":{"observed_at":"2026-05-12T11:21:31.666546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Meta architecture for point cloud analysis","venue":null,"work_id":"dfca51a5-1ef3-4604-9265-d1dfebf871a3","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:90ca9f17c00c102fccce11105048a2f5bff4e22d38ea5cd017d31f5fa44dedbd","observation_id":"92400f1b-0218-4973-be92-a467dab2451b","resolution":{"observed_at":"2026-05-12T11:21:31.672645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Masked discrimination for self-supervised learning on point clouds","venue":null,"work_id":"f522232c-b6b7-4e89-8ea9-11b3ac15455e","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:4441ccb0a18094a0d9b3396818676b9a8be43ac93a78de5f8f24c24d318f0383","observation_id":"cc0208f2-cfd8-44cd-aedc-b08a3a1d4870","resolution":{"observed_at":"2026-05-12T11:21:31.656579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.06467","last_updated":"2024-03-18T02:56:26Z","snapshot_observed_at":"2026-07-06T17:42:24.853273Z","submitted_at":"2024-03-11T07:07:39Z","title":"Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy","version":2},"cited_work":{"arxiv_id":"2403.06467","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.06467","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2403.06467 (2024)","venue":null,"work_id":"e9ec3796-5db9-49d4-91d6-49eeb56ff68c","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/2403.06467","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:7dca297d16f382c6e29ee2f14c4ed756d5dcd7b9728c4ff91845747464df8eb6","observation_id":"319bc936-1934-44a1-ba6c-2513006fc32a","resolution":{"observed_at":"2026-05-12T05:26:24.029470Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point2sequence: Learning the shape representation of 3d point clouds with an attention-based sequence to sequence network","venue":null,"work_id":"97f68b33-dee3-4559-b3c6-aee6206a14e0","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:156d0753257300f37d179ab64a5e6cac182e110473a2ce16540c2eee4b681d59","observation_id":"ac856287-4639-4de1-8557-34a7ccf6c0c4","resolution":{"observed_at":"2026-05-12T11:21:31.714233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Relation-shape convolutional neural network for point cloud analysis","venue":null,"work_id":"433d7e21-6f67-4187-aea1-d3c2cb7116bf","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:0d16fb275b77ee81571a020d2931f5ed2a59d8e08316ea7b041236266bc4801a","observation_id":"b3b22b10-48bc-4d07-af84-d859316fed02","resolution":{"observed_at":"2026-05-12T11:21:31.768181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-space alignments towards universal lidar segmentation","venue":null,"work_id":"77e9839b-5d5e-461e-a3d4-961a31060c2c","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:e70ecae1c293cfc5571b0b314ba187c5d5740cb9a1c14ece663599153baebb65","observation_id":"236488dd-0b65-4971-b111-83ca63aa66e0","resolution":{"observed_at":"2026-05-12T11:21:31.663131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T23:54:19.119275Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"d577574a-ec23-4a36-89fc-494c4f56328e","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:5184193679370bf737e1898335d94412136d18e39a84895ad6b17cae33dd9cea","observation_id":"02e0d1e1-0628-47d6-9a57-f42f10ac09f8","resolution":{"observed_at":"2026-05-12T11:21:31.617930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.07417","last_updated":"2022-09-21T15:10:21Z","snapshot_observed_at":"2026-08-04T20:49:41.596889Z","submitted_at":"2022-05-16T01:32:18Z","title":"Transformers in 3D Point Clouds: A Survey","version":2},"cited_work":{"arxiv_id":"2205.07417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.07417","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Transformers in 3d point clouds: A survey","venue":null,"work_id":"4a25f419-b0f2-43e6-8be1-a192d91c87d3","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/2205.07417","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:2877f6233dc23659fe07caac8967bac2361eb77c6a1aaf08c094eca16ef25fb2","observation_id":"8fbbd184-f1a4-4828-8c02-240879438564","resolution":{"observed_at":"2026-05-12T05:26:24.051379Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stable, fast and accurate: Kernelized attention with relative positional encoding","venue":null,"work_id":"eb894021-4bd9-420b-8f1e-2fec7f23cadf","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:8f836f6dd1a55c45e2c28d2f865304cec632eb4626075591e6f37074106b7b21","observation_id":"0076c983-24d3-4ec3-91b9-a5c9b15375b5","resolution":{"observed_at":"2026-05-12T11:21:31.650191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07123","last_updated":"2022-11-29T07:07:37Z","snapshot_observed_at":"2026-08-02T22:08:27.106810Z","submitted_at":"2022-02-15T01:39:07Z","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","version":2},"cited_work":{"arxiv_id":"2202.07123","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2202.07123","snapshot_observed_at":"2026-07-04T20:00:07.697178Z","title":"Rethinking network design and local geometry in point cloud: A simple resid- ual mlp framework","venue":null,"work_id":"64512226-f7fd-4e43-8731-9b00608d193e","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"cited_paper":"/paper/2202.07123","citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:af19b038f2282a67fc6e6ef7a4a33010171d138cb23c7f9199d6ddcf39cf79d9","observation_id":"a57a68f6-1c64-423f-aac2-35f318468e64","resolution":{"observed_at":"2026-05-12T05:26:24.061914Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"db03366c-e0c4-49fd-8326-2f49653e2ce2","year":2012},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:b4ca64f9a0c21694cd2a70563c12702072d1d42e2405afeefc2ce6f5a7786430","observation_id":"33ad24c6-2534-4615-a06e-0e0376cfe093","resolution":{"observed_at":"2026-05-12T11:21:31.633689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Masked autoencoders for 3d point cloud self-supervised learning.World Scientific Annual Review of Artificial Intelligence, 1:2440001","venue":null,"work_id":"586c7b92-887c-461f-badb-700cbae83d53","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f4a4569031857f3c6fa5da212d13d996be5b2d9c7e33461c5e4f7db8ceefc679","observation_id":"8b0c48a3-0c95-4976-82f7-7d2a70f7af86","resolution":{"observed_at":"2026-05-12T11:21:31.644420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Oa-cnns: Omni-adaptive sparse cnns for 3d semantic segmentation","venue":null,"work_id":"9afa75b9-e4db-4698-be98-cb44675bce1f","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:9c8bcc4d39b95c339e5ae81238f19f84c5fa1629bb3d0ec7af9464f63fa1b751","observation_id":"411761af-39cd-47a0-afaa-f868bf65c37c","resolution":{"observed_at":"2026-05-12T11:21:31.636909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointcept: A codebase for point cloud perception research","venue":null,"work_id":"7a91be3a-7819-404b-b932-b5374345d3b9","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:b88f244e8ebc5bd87adb5848533306ccdd4b473caf2aa72c5dfc3ed432f339bc","observation_id":"5b612b32-980d-4444-a441-ebfd8cedb23c","resolution":{"observed_at":"2026-05-12T11:21:31.610050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Train short, test long: Attention with linear biases enables input length extrapolation","venue":null,"work_id":"272f0250-4373-420b-8395-bd17bd037930","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:496f6e28bf5c2a7011a8e7ad7baae5efb25a823d46b5ccf88c7b2e891da8b469","observation_id":"7cc19d77-2a92-4aa5-90f9-902b77f141f5","resolution":{"observed_at":"2026-05-12T11:21:31.805435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Qi, Hao Su, Kaichun Mo, and Leonidas J","venue":null,"work_id":"019062ae-bc47-4f2b-a083-51d77a1755e6","year":2017},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:6b578349bcbd92c31fd60401d1ea36962d0985ad4f2c2e9f97404610f29be791","observation_id":"cddb1f87-f058-437b-8844-b931b6c47de8","resolution":{"observed_at":"2026-05-12T11:21:31.576303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T05:44:36.348772Z","title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space.Advances in neural information processing systems, 30","venue":null,"work_id":"20799e7f-1c59-4a17-b58e-0c0626f114eb","year":2017},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:0742dab5dbddbffb1f6b8e4b77b2f239158b924ea5bdc5b67d99c8d821a7aa75","observation_id":"0200186f-1dca-4b6b-a7ad-2e4252580fa8","resolution":{"observed_at":"2026-05-12T11:21:31.746325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointnext: Revisiting pointnet++ with improved training and scaling strategies.Advances in neural information processing systems, 35:23192–23204","venue":null,"work_id":"b29e5ac0-9c7a-4a8c-ba3c-f0cd8db35efc","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:fda884fa47cf6cd70440b86d8f9363341466613ca3a4591472c448da93390f79","observation_id":"2620fb77-eb39-4ba3-9589-9ab748d0d330","resolution":{"observed_at":"2026-05-12T11:21:31.720109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"3765c204-e38d-4ab7-92ed-f03b5c780c5e","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:61be2fdc1ebef9e2c9205b215cba842b758ed462e089315c4ec0e6539a2e177c","observation_id":"fdb00e1a-ad79-46d1-8b2c-95ad087fe1fa","resolution":{"observed_at":"2026-05-12T11:21:31.794217Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Turner, René Wagner, Adrian Weller, and Krzysztof Marcin Choromanski","venue":null,"work_id":"d6e6fb5f-dea0-42a8-8973-f73a9769f946","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:535f99f066114d9be4974f11de64c264ff0a5c9fe74071d6d61442158d669d0b","observation_id":"0901e746-ce18-4de7-b7ac-84f4f213c73f","resolution":{"observed_at":"2026-05-12T11:21:31.550240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient 3d semantic segmentation with su- perpoint transformer","venue":null,"work_id":"a817a854-9b93-443a-9fc3-fc4edbee09af","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f01c3ab5cd5c0757c20f1a9cc51feff8888db61eec6a6eef161418935ec71c25","observation_id":"3bd1fab8-5556-4504-88d2-dd2fab2fcc46","resolution":{"observed_at":"2026-05-12T11:21:31.625780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Language-grounded indoor 3d semantic segmentation in the wild","venue":null,"work_id":"46ef1360-477c-4aac-9e71-865ab3ca4813","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f33dad5725cc3f223df0c62db6477925b3f943e047d83253fcc23bb00b31c24b","observation_id":"f682a6ce-d5a9-4096-8c3a-6763d939ed32","resolution":{"observed_at":"2026-05-12T11:21:31.771418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gritsenko, Matthias Minderer, Dmitry Kalashnikov, Jonathan Tompson, Vikas Sindhwani, and Krzysztof Marcin Choromanski","venue":null,"work_id":"42b6075b-5e37-4069-8a1c-98ad9ace8efc","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:dd916816b913d2f285c21dd6c0356cd71f10b6b754efedc425ad12833707cd2c","observation_id":"87833ebc-687e-4818-9268-1e690545ef1f","resolution":{"observed_at":"2026-05-12T11:21:31.801014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient multi-task rgb-d scene analysis for indoor environments","venue":null,"work_id":"bab0f471-18e0-4017-b0ad-6fe0127ec5b6","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:6eb3bc0b771d444803206d074920bf6cede8b70eabd02c20ae778092ed1a8b03","observation_id":"5f917a67-b94b-4ee6-bbf1-0d58e46cc0f6","resolution":{"observed_at":"2026-05-12T11:21:31.556104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient rgb-d semantic segmentation for indoor scene analysis","venue":null,"work_id":"b5cbd397-5493-483f-b69c-74ead763c640","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:ea244a78ac838aab7c157955cf68809f6920f8c8671a057d6b7b550ee58a3732","observation_id":"57a28055-f2cf-4a03-92d9-1d5f53df3e48","resolution":{"observed_at":"2026-05-12T11:21:31.738425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Self-attention with relative position representations","venue":null,"work_id":"39ee76eb-613f-4208-a3c3-6f45946cec5c","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:712c6ffb85235d3a97ec5a00ff2bcd5b292923ebd090536373a0e80fd5f49a42","observation_id":"9d53da78-10c4-4756-a0de-18a08cfca430","resolution":{"observed_at":"2026-05-12T11:21:31.743618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sun rgb-d: A rgb-d scene under- standing benchmark suite","venue":null,"work_id":"cc1d49bd-9ed9-46f2-8f02-12448f257964","year":2015},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:481a4b8c0e0d36f70bd9a23600f9b3403b057a1496b54405a37e4a3be0f6c105","observation_id":"381aca78-a025-436e-b76c-c7014321fe8d","resolution":{"observed_at":"2026-05-12T11:21:31.754965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Roformer: Enhanced transformer with rotary position embedding.Neurocomput., 568(C), February 2024","venue":null,"work_id":"f9ad8602-7eb9-4240-a113-70d0d32547cc","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f27547d5ea878d91e57babc8f1e7c1f9d91e6c146bd9831af8068cb11c1a1885","observation_id":"3c7c3db4-8482-437c-acac-c430077e2f83","resolution":{"observed_at":"2026-05-12T11:21:31.749042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Searching efficient 3d architectures with sparse point-voxel convolution","venue":null,"work_id":"6e0cb818-ae96-4fd6-b2cd-ba4b4a141109","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:586a1dc3d193c4af865ae90d0c02a32ed262aaac73bcdb58556554649ce5d740","observation_id":"b6f808a7-f71a-4fed-a667-270f3f98b532","resolution":{"observed_at":"2026-05-12T11:21:31.761541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tangent convolutions for dense prediction in 3d","venue":null,"work_id":"3e3fd384-2a3d-42a1-9920-12cc1c33e4c8","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:8ad5e2b50428d44f05979e54335412671191f2b813fd15436f1662aa579b4c8e","observation_id":"d33c3e8c-770f-430c-9757-fdee85119b51","resolution":{"observed_at":"2026-05-12T11:21:31.628250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Segcloud: Semantic segmentation of 3d point clouds","venue":null,"work_id":"aff7b6b3-e19a-48bf-9a97-7f4d00b2c644","year":2017},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f4d445ac692f3ebe8d58f7dc7e9f9f061ad108d319dfb831d7ec8a07cbb1ce8f","observation_id":"a2854725-7889-4927-9397-9b00b2b96695","resolution":{"observed_at":"2026-05-12T11:21:31.703156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Kpconv: Flexible and deformable convolution for point clouds","venue":null,"work_id":"22e8a2fa-3cdc-4c42-9310-79885075eae1","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:3ffce87bd300b636731b89837ad4368d5af7809343dc9f49c75a93d5f5eb6b53","observation_id":"b91d66f3-f44d-419c-9225-ea2ae1f3a881","resolution":{"observed_at":"2026-05-12T11:21:31.777855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data","venue":null,"work_id":"162cf916-ba98-4884-8a00-c332cdfe69dc","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:19cc5756086cc5a9508aa14cdd5f9ef536207f160c3f1f5fa5096eaf2786cc44","observation_id":"ebc8dcc5-a613-45cc-9c41-98840517c647","resolution":{"observed_at":"2026-05-12T11:21:31.615401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gomez, Łukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"e0063fad-3887-44e1-a725-1c6af1372db8","year":2017},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:3a1491dd1f704b7639d26a43ba1df219f1680f4a878804a868d8b8ae656a5dc1","observation_id":"b1b55f92-146a-4248-9c70-bbeddf185b58","resolution":{"observed_at":"2026-05-12T11:21:31.612595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Graph attention convo- lution for point cloud semantic segmentation","venue":null,"work_id":"9758adca-fa4f-4470-a758-34152beac31a","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:0f17e123e324f7862706bdd4c34194c22a6833b7d3d6b3be8787d10ddc301a57","observation_id":"5e789a47-aedb-423a-ac5e-70e0a7ee00a9","resolution":{"observed_at":"2026-05-12T11:21:31.639548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Octformer: Octree-based transformers for 3d point clouds.ACM Transac- tions on Graphics (TOG), 42(4):1–11","venue":null,"work_id":"79c12888-b3c1-43c2-bf15-835c4f7d48b5","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:1baee424a4fefef1b4dc45745166b0683744e66f0be1f1eb998776da2080fa47","observation_id":"8081e231-9e9f-42cf-8c57-71aae980f3dd","resolution":{"observed_at":"2026-05-12T11:21:31.623226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep parametric continuous convolutional neural networks","venue":null,"work_id":"de01c5fb-62b9-470f-8af2-9d14775e54ea","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f679937723244d8ec0e5ecf2a74fbd94709ac764bfb8e866c6991b84b9062785","observation_id":"9d460081-ff35-43d6-8847-f52bc8893a65","resolution":{"observed_at":"2026-05-12T11:21:31.647092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multimodal token fusion for vision transformers","venue":null,"work_id":"deab21ac-748c-498d-8691-a807634dfcec","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:8c39f104229257c07485b93028a9ed7451e1b852fc017d0bc5cc4d8514f1918c","observation_id":"dec7c5b0-a7cc-4bb4-b4dd-218141eb4fa8","resolution":{"observed_at":"2026-05-12T11:21:31.725016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep multimodal fusion by channel exchanging.Advances in neural information processing systems, 33:4835–4845","venue":null,"work_id":"f5db5b5f-a21e-4406-a118-33570808ae99","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:a3bb504d5a2775212fadd9ed38a99da99ed01c79a774e24f8cd7b54150885cf6","observation_id":"db42266f-43a6-44a7-b236-604dc26ff656","resolution":{"observed_at":"2026-05-12T11:21:31.695192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sarma, Michael M","venue":null,"work_id":"0e44fb81-22dc-484a-a944-b38fcad78c91","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:b4081ec76039674413ef90a0d47f9f4e1674a28ac11bf4ee679a204c1512dd23","observation_id":"55d368ea-e4d0-4646-9295-462c0f482f1f","resolution":{"observed_at":"2026-05-12T11:21:31.675181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointconvformer: Revenge of the point-based convolu- tion","venue":null,"work_id":"1add5245-9336-46cd-b9ec-aba2ab7a622f","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:88c5f8f1710d40474b9370d3697f75d8d30617116fdc2288a1283baf377f395f","observation_id":"d9e2cd38-5e84-4d22-861f-b99b5269a8f0","resolution":{"observed_at":"2026-05-12T11:21:31.689335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointconv: Deep convolutional networks on 3d point clouds","venue":null,"work_id":"fcc3518d-5954-412c-ba5f-d4fbe81ae2cc","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:76a90806f6a5f11b5ad1ad406e0184f0d990e30e054f902c20654a94210bc705","observation_id":"c8ae81ae-152c-48a3-bce9-764f1b740123","resolution":{"observed_at":"2026-05-12T11:21:31.717243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point transformer v3: Simpler faster stronger","venue":null,"work_id":"23296a92-337e-48df-a2d2-5c9bd3ec5bc0","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:03cac11c26edacf23e56065b1187622dfea70240788390e433c05fe541810cd9","observation_id":"e9d3451f-b81e-47e0-ac15-717eb0fbe684","resolution":{"observed_at":"2026-05-12T11:21:31.781485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point transformer v2: Grouped vector attention and partition-based pooling.Advances in Neural Information Processing Systems, 35:33330–33342","venue":null,"work_id":"dbbf8ae4-92ba-4b3d-91f6-2884898205f6","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:978443e97bc7e790b66fac87454c672d154a4639a0f78908d05783cd48f0db04","observation_id":"45552188-7b44-45db-ae8a-9288c756bf22","resolution":{"observed_at":"2026-05-12T11:21:31.596268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards large-scale 3d representation learning with multi-dataset point prompt training","venue":null,"work_id":"c4df42ec-0938-4d4a-a015-589f46490560","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:f583d12415331f3ecc92611bb3be814005f9438001d375a03d2f1a7391cfb673","observation_id":"b348bddd-0a27-499d-ab7f-bcc0535e2d87","resolution":{"observed_at":"2026-05-12T11:21:31.546923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"3d shapenets: A deep representation for volumetric shapes","venue":null,"work_id":"5b8236c6-f115-4fad-93b9-deef4e755c78","year":1912},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:9a5470389e3ceb8436b506d378277926170ae1d68f244cdbb6efc4a8cb69262b","observation_id":"ab10ceb8-a855-4c5f-8adb-aafbea2dcd78","resolution":{"observed_at":"2026-05-12T11:21:31.722578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Attentional shapecontextnet for point cloud recognition","venue":null,"work_id":"ed9a682a-ed93-4cb3-9666-fe4c84cc5113","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:bd78661f2aaa13795f9a1cba9d7ed307afc051fb06f668e8bacdb590f35d28ed","observation_id":"9a5e46b0-c253-43df-90ab-aa23be3d9052","resolution":{"observed_at":"2026-05-12T11:21:31.809083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Paconv: Position adaptive convolution with dynamic kernel assembling on point clouds","venue":null,"work_id":"091ab607-8a97-4d1e-bdd9-717b90a00f7d","year":2021},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:552721e8347a8671624ffa402d538755cdfc32a720cf18f71051260ccfacd98b","observation_id":"2cb99c91-e682-4a70-aa5c-c87820fcd5f8","resolution":{"observed_at":"2026-05-12T11:21:31.653377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Spidercnn: Deep learning on point sets with parameterized convolutional filters","venue":null,"work_id":"4aa2f263-d01f-49c8-b969-57969cee4681","year":2018},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:b455fc09442d94d40afb250c44eceec84ba67176ca3184366ee805f4e1e3843f","observation_id":"7eb91e47-41c2-4e9a-86ba-7699da41b4d3","resolution":{"observed_at":"2026-05-12T11:21:31.586260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"2dpass: 2d priors assisted semantic segmentation on lidar point clouds","venue":null,"work_id":"0e59d7cb-d27c-4bba-bbd7-28af444384bc","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:29df145c7f8c8b1f3f77f4689d93d55efe904fbfbaa34497d51b2fb649141b8a","observation_id":"0eb234b4-0aa0-4b0a-8df5-95e58b16f826","resolution":{"observed_at":"2026-05-12T11:21:31.569478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Pointasnl: Robust point clouds processing using nonlocal neural networks with adaptive sampling","venue":null,"work_id":"fdb46496-baec-4aad-8fe4-1cd14da18f3c","year":2020},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:1bd1087d6d6d9f2a952cbb2764415523160bacc5f7686accd43f3685f571642c","observation_id":"f5282848-dc3e-49e1-9345-4b657f8a51e4","resolution":{"observed_at":"2026-05-12T11:21:31.573014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"One inlier is first: Towards efficient position encoding for point cloud registration","venue":null,"work_id":"02ed54d9-ae80-497f-af7d-eb6bd8e5ed62","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:a23ea0541692bcc5b1a1f80b331e13f54214b81c260ce67c2472b05901d88149","observation_id":"7efa3888-dc80-4d3b-90e0-fbb6bb113315","resolution":{"observed_at":"2026-05-12T11:21:31.791304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Modeling point clouds with self-attention and gumbel subset sampling","venue":null,"work_id":"8029ed5c-5aff-421c-b57e-1a18d5964c96","year":2019},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:7af71e9e2c5a05c3fa459969f400ec261c83b80d3e5fe30d954d8c5f17886c78","observation_id":"4304ab44-da28-4fdb-acaf-09452f85857a","resolution":{"observed_at":"2026-05-12T11:21:31.592888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Swin3d: A pretrained transformer backbone for 3d indoor scene understanding.Computational Visual Media, 11(1):83–101","venue":null,"work_id":"d4d83c2d-5128-4ff3-812a-3b8b0e4e079b","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:327b1bef71952b44bc8c88a6ed94ffe2f143d2e198fbea9f411d94ee6cbea78a","observation_id":"9389db65-5e74-4316-8076-498167cc234a","resolution":{"observed_at":"2026-05-12T11:21:31.579629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-08T10:54:50.332198Z","title":"Scannet++: A high-fidelity dataset of 3d indoor scenes","venue":null,"work_id":"acc8e282-655c-4c23-b74a-3ecacf69e326","year":2023},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:3d8304894d50ad1f21f2ecc36c9d43077b44594dacc031deb2fdefa999bbde5e","observation_id":"b4ee2522-8614-432f-96ae-a787e5e338d7","resolution":{"observed_at":"2026-05-12T11:21:31.700709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dformerv2: Geometry self-attention for rgbd semantic segmentation","venue":null,"work_id":"fa6ba55a-7aee-4d77-b604-1a586afd1c9e","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:94b2b11623bf58d12d227ee900eeb5ed0cf9e6f47014db4763796a081de5572e","observation_id":"108d27eb-b8e3-4cc3-b050-7ed17253364c","resolution":{"observed_at":"2026-05-12T11:21:31.582914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Omnisegmentor: A flexible multi-modal learning framework for semantic segmentation","venue":null,"work_id":"21e7062b-1ede-4461-b1b2-58abc061679a","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:e9697f5ea45015b9224e7783efd67bb94b8b52fa45acd1dabb5c09a804b8e07a","observation_id":"95f5f433-8160-4aa8-874d-6b682db5b7b6","resolution":{"observed_at":"2026-05-12T11:21:31.680413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DFormer: Rethinking RGBD representation learning for semantic segmentation","venue":null,"work_id":"4d0c7fdb-94f1-4013-8a4e-b3e84da6fc99","year":2024},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:004a8df42d96109119a203ff2bdc22628ebc893db7c8d2f50dd4bc95b3c9088a","observation_id":"fe1002a3-e46f-4fdc-85d2-cb7177fda331","resolution":{"observed_at":"2026-05-12T11:21:31.566140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Point-bert: Pre-training 3d point cloud transformers with masked point modeling","venue":null,"work_id":"520c64f1-8693-4c62-bbe0-15f1aed5cecd","year":2022},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:27254a585be148a1f31db30f8a1206580276b112862e08911a05a3c0979c6097","observation_id":"b6203a35-77c9-41aa-9768-274446ae5c40","resolution":{"observed_at":"2026-05-12T11:21:31.559044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2512.13689","doi":"10.48550/arxiv.2512.13689","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Litept: Lighter yet stronger point transformer","venue":"arXiv (Cornell University)","work_id":"57d86cdf-2dca-49a5-b4c9-989abe430aff","year":2025},"citing_paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-05-12T05:25:19.181337Z"},"links":{"citing_paper":"/paper/2605.10706"},"observation_digest":"sha256:331a097cbb18f32969f91d0603b64ab50047dcd55f5e4a7b417e84e9b32f2dbc","observation_id":"c45ecf6a-1ed3-4a85-a630-7f996bb77781","resolution":{"observed_at":"2026-05-12T05:26:24.019699Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.10706","last_updated":"2026-05-11T15:20:01Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T23:22:37.355450Z","submitted_at":"2026-05-11T15:20:01Z","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":1,"verified_exact":7,"verified_fuzzy":91},"total_outbound_references":111},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 100 of 111 outbound references and 1 inbound Pith citation observation for arXiv:2605.10706."}