{"as_of":"2026-08-09T22:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9ed87dede08fe0589d7644092d259c1ab68c9bb9df11733df8fea8bcbe8d3793","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T00:21:15.767616Z","state":"measured"},{"denominator":72,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":72,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.03901/citation-record","integrity":"/paper/2502.03901/integrity","json":"/paper/2502.03901/citation-record.json","paper":"/paper/2502.03901"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:15.411499Z","title":"nuScenes: A Multimodal Dataset for Autonomous Driving,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.411499Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:4c698d5bed1551e1529de31b6ce48c8460f3671f21877b9c9e2e5a9f6cf1846b","observation_id":"60a64aa9-3d4c-4824-b1a9-1e2cad500784","resolution":{"observed_at":"2026-08-09T00:21:15.411499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.04838","last_updated":"2020-05-12T23:28:05Z","snapshot_observed_at":"2026-08-09T12:00:48.903128Z","submitted_at":"2019-12-10T17:28:55Z","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.04838","snapshot_observed_at":"2026-08-09T00:21:15.417130Z","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.417130Z"},"links":{"cited_paper":"/paper/1912.04838","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:2cf19bcced1034f7d02487ecd74959411d9a2da76116314fce3b7001d997e9ad","observation_id":"51cc88cf-d42f-407a-8f89-993b4ad27fb6","resolution":{"observed_at":"2026-08-09T00:21:15.417130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:15.422654Z","title":"Are we ready for autonomous driving? The KITTI vision benchmark suite,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.422654Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:dfeefb49a32fa917c92b5c496522e0d017c5f57d33a8cd48314ee1db97af4b39","observation_id":"a99eea1c-ac31-4d04-8018-9d11741ccd4f","resolution":{"observed_at":"2026-08-09T00:21:15.422654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.01416","last_updated":"2019-08-16T09:30:52Z","snapshot_observed_at":"2026-08-09T16:22:07.201745Z","submitted_at":"2019-04-02T13:53:16Z","title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.01416","snapshot_observed_at":"2026-08-09T00:21:15.427642Z","title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.427642Z"},"links":{"cited_paper":"/paper/1904.01416","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:2240a60890b27455b41b1241b0f140a945ea799bbc3b78c19aa808505be3f6b7","observation_id":"6aa10233-3666-47ac-b127-500adbf902f0","resolution":{"observed_at":"2026-08-09T00:21:15.427642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.13410","last_updated":"2022-06-03T07:09:53Z","snapshot_observed_at":"2026-07-06T11:51:58.310046Z","submitted_at":"2021-09-28T00:41:29Z","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.13410","snapshot_observed_at":"2026-08-09T00:21:15.433102Z","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.433102Z"},"links":{"cited_paper":"/paper/2109.13410","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:23cb607d6ae708c8cb6c672a10f6aa29b3d0884c1b12d629ff2bf01f6ead2134","observation_id":"159987c3-71ed-4e2d-a829-af71520b5972","resolution":{"observed_at":"2026-08-09T00:21:15.433102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08586","last_updated":"2025-04-15T03:03:46Z","snapshot_observed_at":"2026-07-06T16:32:07.186600Z","submitted_at":"2023-10-12T17:59:57Z","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08586","snapshot_observed_at":"2026-08-09T00:21:15.438601Z","title":"PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.438601Z"},"links":{"cited_paper":"/paper/2310.08586","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:37c7bdb8a833761f173b7cd6d5d9cf7549093ffee23bc782e0c382c87673b7fd","observation_id":"52bb1065-449b-4e6c-8520-b750a2b2eb46","resolution":{"observed_at":"2026-08-09T00:21:15.438601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01288","last_updated":"2024-05-04T14:21:01Z","snapshot_observed_at":"2026-08-09T12:00:43.278266Z","submitted_at":"2023-10-02T15:41:35Z","title":"Offline Tracking with Object Permanence","version":4},"cited_work":{"arxiv_id":"2310.01288","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.01288","snapshot_observed_at":"2026-08-09T00:21:18.050083Z","title":"Offline Tracking with Object Permanence","venue":"cs.CV","work_id":"867906f4-4a97-4eca-b674-7bead075f980","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.444794Z"},"links":{"cited_paper":"/paper/2310.01288","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:270b3937d24d2e1d9bb681be45bca0a1e64cd552091ced0796339c79718a6798","observation_id":"4611a4a9-561a-4b01-8887-e23048826bc8","resolution":{"observed_at":"2026-08-09T00:21:18.055670Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04133","last_updated":"2024-03-07T01:24:59Z","snapshot_observed_at":"2026-07-06T17:40:45.750926Z","submitted_at":"2024-03-07T01:24:59Z","title":"Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04133","snapshot_observed_at":"2026-08-09T00:21:15.450428Z","title":"Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.450428Z"},"links":{"cited_paper":"/paper/2403.04133","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:00fb87f5cad4cb637a1fa5dffd7f95d7d64c01f1630110d53bcb9fc8a2d270c2","observation_id":"f98d050d-668c-46c7-8445-d73db37478b6","resolution":{"observed_at":"2026-08-09T00:21:15.450428Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00020","last_updated":"2021-02-26T19:04:58Z","snapshot_observed_at":"2026-07-06T10:45:03.059688Z","submitted_at":"2021-02-26T19:04:58Z","title":"Learning Transferable Visual Models From Natural Language Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00020","snapshot_observed_at":"2026-08-09T00:21:15.456179Z","title":"Learning Transferable Visual Models From Natural Language Supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.456179Z"},"links":{"cited_paper":"/paper/2103.00020","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:17c4a0e01fb49c058ac9328615e1374236f688890457dae19391e4d977f38051","observation_id":"81544536-46de-4f67-8233-d695eea66009","resolution":{"observed_at":"2026-08-09T00:21:15.456179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.02643","last_updated":"2023-04-05T17:59:46Z","snapshot_observed_at":"2026-08-08T05:14:59.435033Z","submitted_at":"2023-04-05T17:59:46Z","title":"Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.02643","snapshot_observed_at":"2026-08-09T00:21:15.461657Z","title":"Segment Anything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.461657Z"},"links":{"cited_paper":"/paper/2304.02643","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:67361921ea58804ce176b6fa136981f4f5134440a524b3d53c0aa2d87fbc0bc6","observation_id":"28886f5c-4706-4bc4-a644-d08f4afb1950","resolution":{"observed_at":"2026-08-09T00:21:15.461657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10891","last_updated":"2024-04-07T06:52:21Z","snapshot_observed_at":"2026-08-01T22:50:12.319180Z","submitted_at":"2024-01-19T18:59:52Z","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10891","snapshot_observed_at":"2026-08-09T00:21:15.467101Z","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.467101Z"},"links":{"cited_paper":"/paper/2401.10891","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:23e59f493e64c3d53f3f33913ff15a2453c2d2ada91c09872b6fc6fda8a4b5be","observation_id":"e77f8d4d-5adf-4bce-bfe7-aca97bd38409","resolution":{"observed_at":"2026-08-09T00:21:15.467101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/9878980","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:17.953263Z","title":"PointCLIP: Point Cloud Understanding by CLIP,","venue":null,"work_id":"b33342e2-4b1e-4b30-93e9-1c11031dbd5b","year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.472192Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:cb1f679ea9752bc9547275f4fe79588b5867f71b1e096d349046b03a9218774a","observation_id":"fbf95e82-94d3-499f-a48e-ea2308f65409","resolution":{"observed_at":"2026-08-09T00:21:17.961925Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.15654","last_updated":"2023-04-06T15:35:13Z","snapshot_observed_at":"2026-08-01T19:17:16.721333Z","submitted_at":"2022-11-28T18:58:36Z","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.15654","snapshot_observed_at":"2026-08-09T00:21:15.476143Z","title":"OpenScene: 3D Scene Understanding with Open V ocabularies,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.476143Z"},"links":{"cited_paper":"/paper/2211.15654","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:1076bf7b3d86723882140be5c8552ab9d488f19980ed76bfc0de7a21bb903722","observation_id":"a576ed46-42b0-4ca4-ab23-80a1f24bf1d6","resolution":{"observed_at":"2026-08-09T00:21:15.476143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.04926","last_updated":"2023-04-06T09:56:10Z","snapshot_observed_at":"2026-07-06T14:40:38.903938Z","submitted_at":"2023-01-12T10:42:39Z","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","version":2},"cited_work":{"arxiv_id":"2301.04926","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.04926","snapshot_observed_at":"2026-08-09T00:21:17.845317Z","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","venue":"cs.CV","work_id":"f2a62368-1797-40ae-96de-40da9b9051cb","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.480424Z"},"links":{"cited_paper":"/paper/2301.04926","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:81d29b8946a45593f27a9edf0fcd2bc1f3ad42646062bd60a0af7b7172f9481f","observation_id":"7681a34f-6c1a-436c-975c-1de8c891c6b4","resolution":{"observed_at":"2026-08-09T00:21:17.851071Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16133","last_updated":"2023-06-14T17:30:54Z","snapshot_observed_at":"2026-07-06T15:33:23.984280Z","submitted_at":"2023-05-25T15:07:25Z","title":"OVO: Open-Vocabulary Occupancy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16133","snapshot_observed_at":"2026-08-09T00:21:15.484766Z","title":"OVO: Open-V ocabulary Occupancy,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.484766Z"},"links":{"cited_paper":"/paper/2305.16133","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:7a491f0e3c0953c149ff18ab423c9c8bdfec5725facebd63240433a3ce7ab0c0","observation_id":"c6b7f1df-45d7-4976-a757-718a0c98a69b","resolution":{"observed_at":"2026-08-09T00:21:15.484766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09413","last_updated":"2024-01-17T18:51:53Z","snapshot_observed_at":"2026-07-06T17:16:55.291514Z","submitted_at":"2024-01-17T18:51:53Z","title":"POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.09413","snapshot_observed_at":"2026-08-09T00:21:15.489082Z","title":"POP-3D: Open-V ocabulary 3D Occupancy Prediction from Images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.489082Z"},"links":{"cited_paper":"/paper/2401.09413","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:16b4a9b397e9a82b5207c1b7b002a1688169f8d02542eb842f942859547a3fe5","observation_id":"a75c7ca6-4b79-43a6-bc7c-eba1913346a8","resolution":{"observed_at":"2026-08-09T00:21:15.489082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/1048420","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:17.782580Z","title":"LidarCLIP or: How I Learned to Talk to Point Clouds,","venue":null,"work_id":"c1d2c52d-d41c-4c50-a2a4-473e56f4a953","year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.494230Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:72dbf36c4924d818cb1f3f2194625b2ab7dde5ef7387a4aadbca1c7e0dd5006d","observation_id":"e7dae428-4841-4f95-901c-22ef7625fffb","resolution":{"observed_at":"2026-08-09T00:21:17.791624Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.09718","last_updated":"2024-07-21T20:50:06Z","snapshot_observed_at":"2026-07-06T16:07:49.197575Z","submitted_at":"2023-08-18T17:59:57Z","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.09718","snapshot_observed_at":"2026-08-09T00:21:15.499494Z","title":"Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.499494Z"},"links":{"cited_paper":"/paper/2308.09718","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:7625f7b510b3b6532af5cc08a6f82ae68e84f4baa476a40622a4b7f45ced290b","observation_id":"221cb6fc-8f8b-4fe7-ac7c-6252c5a51cbd","resolution":{"observed_at":"2026-08-09T00:21:15.499494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.05499","last_updated":"2024-07-19T06:00:41Z","snapshot_observed_at":"2026-07-06T15:00:58.804337Z","submitted_at":"2023-03-09T18:52:16Z","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.05499","snapshot_observed_at":"2026-08-09T00:21:15.504820Z","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.504820Z"},"links":{"cited_paper":"/paper/2303.05499","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:eaefadb2f8b6399de5fba84b1513c212d9a1d864745f87fcb39594abb7d5a301","observation_id":"5f987f46-0ebb-47f4-b5d0-00d90acc9530","resolution":{"observed_at":"2026-08-09T00:21:15.504820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/7353481","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:17.626667Z","title":"V oxNet: A 3D Convolutional Neural Network for real-time object recognition,","venue":null,"work_id":"af30defe-24ce-4f13-a81a-2b34da0ed84f","year":2015},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.510082Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:80c8c78efb2e421fc0c9cbe93c996b75cf0e6b3f23c5f1bd35af636692db6fd8","observation_id":"46148819-ff77-42d9-84d0-c64bbc46d9b0","resolution":{"observed_at":"2026-08-09T00:21:17.635304Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.10275","last_updated":"2017-11-28T13:21:58Z","snapshot_observed_at":"2026-07-06T06:11:35.990430Z","submitted_at":"2017-11-28T13:21:58Z","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10275","snapshot_observed_at":"2026-08-09T00:21:15.515184Z","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.515184Z"},"links":{"cited_paper":"/paper/1711.10275","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:977210ee4db442bc3130eca7823d3962e049401d4220f9c3b31839af0210eaa9","observation_id":"6904442e-efe0-4bab-8b54-0b6e084d563c","resolution":{"observed_at":"2026-08-09T00:21:15.515184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.16100","last_updated":"2020-08-13T13:53:20Z","snapshot_observed_at":"2026-08-05T00:52:20.231738Z","submitted_at":"2020-07-31T14:27:27Z","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","version":2},"cited_work":{"arxiv_id":"2007.16100","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.16100","snapshot_observed_at":"2026-08-09T00:21:17.509642Z","title":"Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution","venue":"cs.CV","work_id":"c7a66a31-4d4e-4764-83d1-dc6248d220bd","year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.520525Z"},"links":{"cited_paper":"/paper/2007.16100","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:bd544e1d3468e3d2ce33a5cdcd4999157b0c3562d8465261f43f87945848a049","observation_id":"e5ba1b1c-628e-4a50-9be3-b0fb719e3ee3","resolution":{"observed_at":"2026-08-09T00:21:17.515570Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.10033","last_updated":"2020-11-19T18:53:11Z","snapshot_observed_at":"2026-08-08T11:47:40.062549Z","submitted_at":"2020-11-19T18:53:11Z","title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.10033","snapshot_observed_at":"2026-08-09T00:21:15.525833Z","title":"Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.525833Z"},"links":{"cited_paper":"/paper/2011.10033","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:2299450e0912f070c8f984d6e7d2923b19223970b2a0f13dcd8092512da3be36","observation_id":"e5d14215-619f-485d-a96c-47b564b1a93e","resolution":{"observed_at":"2026-08-09T00:21:15.525833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:18.325876Z","title":"SV ASeg: Sparse V oxel-Based Attention for 3D LiDAR Point Cloud Semantic Segmentation,","venue":null,"work_id":"1d9891fb-17f0-46e9-a11f-d11d65a971c2","year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.531101Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e4058664684a1531247601dea152eabbf0c809cfb406410dbcdb50025db1e461","observation_id":"23e074ac-95cd-4d3a-9a84-b848957a9f07","resolution":{"observed_at":"2026-08-09T00:21:18.331088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12766","last_updated":"2023-03-22T17:30:14Z","snapshot_observed_at":"2026-07-06T15:06:49.250456Z","submitted_at":"2023-03-22T17:30:14Z","title":"Spherical Transformer for LiDAR-based 3D Recognition","version":1},"cited_work":{"arxiv_id":"2303.12766","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.12766","snapshot_observed_at":"2026-08-09T00:21:17.466598Z","title":"Spherical Transformer for LiDAR-based 3D Recognition","venue":"cs.CV","work_id":"d10c290f-0e92-4f38-a96e-c3d31e2565c9","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.535969Z"},"links":{"cited_paper":"/paper/2303.12766","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e6035df66930092cc67783d250ca3430a6864fbc91dfcdc35c5cb981c339f739","observation_id":"6e526c4d-38b0-4f73-bf3d-b0dfbc98a989","resolution":{"observed_at":"2026-08-09T00:21:17.472326Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.05316","last_updated":"2023-04-11T16:15:50Z","snapshot_observed_at":"2026-07-06T15:14:28.574778Z","submitted_at":"2023-04-11T16:15:50Z","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.05316","snapshot_observed_at":"2026-08-09T00:21:15.541222Z","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.541222Z"},"links":{"cited_paper":"/paper/2304.05316","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:0ea96f54c74fbe2ec54eb99e3bde47d1b2a629a9a525e175f16681f9d17ad3e3","observation_id":"3a8b42bc-e8a0-485e-ade9-e81b3c550b48","resolution":{"observed_at":"2026-08-09T00:21:15.541222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.00726","last_updated":"2022-03-29T17:59:46Z","snapshot_observed_at":"2026-08-01T22:00:39.020096Z","submitted_at":"2021-12-01T18:59:57Z","title":"MonoScene: Monocular 3D Semantic Scene Completion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.00726","snapshot_observed_at":"2026-08-09T00:21:15.546503Z","title":"MonoScene: Monocular 3D Semantic Scene Completion,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.546503Z"},"links":{"cited_paper":"/paper/2112.00726","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:2712a0e29810c34829e4ba2c8b04bcc19bc2e9c331166480310a7102d4685e32","observation_id":"6eaa1d1e-233a-4192-b283-8521168e930c","resolution":{"observed_at":"2026-08-09T00:21:15.546503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.08495","last_updated":"2018-09-22T22:04:49Z","snapshot_observed_at":"2026-08-09T10:32:53.729144Z","submitted_at":"2018-09-22T22:04:49Z","title":"SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.08495","snapshot_observed_at":"2026-08-09T00:21:15.551564Z","title":"SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.551564Z"},"links":{"cited_paper":"/paper/1809.08495","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:f961c9b30f73385ab70c4e8b4c0fe3bc3809593dfbc8745a8cee9529736e721f","observation_id":"3eccbcbd-ad38-4330-974d-97cc93a9bd70","resolution":{"observed_at":"2026-08-09T00:21:15.551564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/8967762","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:17.388761Z","title":"RangeNet ++: Fast and Accurate LiDAR Semantic Segmentation,","venue":null,"work_id":"d78eaab2-7756-48d8-86c1-efdfa4001067","year":2019},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.556817Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:b8515d0659a1772f0fe8d6e81f8505a709a9c21760d114a2c2831891ae88f3c3","observation_id":"a39c34ee-884d-4b68-a7e5-14812304f548","resolution":{"observed_at":"2026-08-09T00:21:17.397943Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.03653","last_updated":"2024-11-20T20:47:25Z","snapshot_observed_at":"2026-08-09T12:24:20.273063Z","submitted_at":"2020-03-07T20:17:06Z","title":"SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.03653","snapshot_observed_at":"2026-08-09T00:21:15.561750Z","title":"SalsaNext: Fast, 7 Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.561750Z"},"links":{"cited_paper":"/paper/2003.03653","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:27282d3304ef474ea40664387ef2b44af883f3d930c0c71ee0ddcb28b381cb04","observation_id":"48296489-b7da-4b17-8f26-8adc150991c3","resolution":{"observed_at":"2026-08-09T00:21:15.561750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14032","last_updated":"2020-04-26T08:44:11Z","snapshot_observed_at":"2026-07-06T09:08:40.123903Z","submitted_at":"2020-03-31T08:58:45Z","title":"PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"2003.14032","doi":null,"metadata_source":"pith","pith_arxiv_id":"2003.14032","snapshot_observed_at":"2026-08-09T00:21:17.296131Z","title":"PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation","venue":"cs.CV","work_id":"5a0e6fe3-2490-441d-b53d-e1271932fb6c","year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.566965Z"},"links":{"cited_paper":"/paper/2003.14032","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:0fb3a59a3891708c1ac795a764bddcf5af8ed36956a6677611b8dfd61a5f8b9f","observation_id":"1ba31ed7-6c01-48df-a928-109660d592dc","resolution":{"observed_at":"2026-08-09T00:21:17.301679Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.05367","last_updated":"2023-09-03T05:02:00Z","snapshot_observed_at":"2026-08-06T11:44:44.514738Z","submitted_at":"2023-03-09T16:13:27Z","title":"Rethinking Range View Representation for LiDAR Segmentation","version":3},"cited_work":{"arxiv_id":"2303.05367","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.05367","snapshot_observed_at":"2026-08-09T00:21:17.273142Z","title":"Rethinking Range View Representation for LiDAR Segmentation","venue":"cs.CV","work_id":"1515f16e-4f4f-434e-b159-5e4a8f366393","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.572217Z"},"links":{"cited_paper":"/paper/2303.05367","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e4b2b891e5deef5c32a1f3a52ff5b7fb290a5b5a0441bb27909c8bfaa0464e0a","observation_id":"cf06d035-b172-45e9-a85b-564de90959cd","resolution":{"observed_at":"2026-08-09T00:21:17.278613Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.10559","last_updated":"2020-10-25T15:26:18Z","snapshot_observed_at":"2026-07-06T09:49:44.919864Z","submitted_at":"2020-08-24T16:52:16Z","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","version":2},"cited_work":{"arxiv_id":"2008.10559","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.10559","snapshot_observed_at":"2026-08-09T00:21:17.249837Z","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","venue":"cs.CV","work_id":"69713870-e157-43ba-a664-d3c116432cd6","year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.577297Z"},"links":{"cited_paper":"/paper/2008.10559","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:f8beabe4c5e646e6c853c5794ac0794eb92f465e0eeee2906604ab2a4f6db3e8","observation_id":"c8a075a0-028b-4ff2-944d-f86ac1cf6797","resolution":{"observed_at":"2026-08-09T00:21:17.255397Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09242","last_updated":"2020-12-16T20:14:41Z","snapshot_observed_at":"2026-07-06T10:25:14.308394Z","submitted_at":"2020-12-16T20:14:41Z","title":"S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds","version":1},"cited_work":{"arxiv_id":"2012.09242","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.09242","snapshot_observed_at":"2026-08-09T00:21:17.224757Z","title":"S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds","venue":"cs.CV","work_id":"2f00c022-02d5-400e-a6a4-2b1ac02133e7","year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.582442Z"},"links":{"cited_paper":"/paper/2012.09242","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:b03056168d808fe959aae11a0b6621f0c28af0c5196cf25aae3d41c9f3c838e9","observation_id":"0b2c28e7-b3a7-431d-803d-e6c51af4f211","resolution":{"observed_at":"2026-08-09T00:21:17.231232Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16896","last_updated":"2023-08-31T17:57:17Z","snapshot_observed_at":"2026-08-03T00:19:11.236614Z","submitted_at":"2023-08-31T17:57:17Z","title":"PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16896","snapshot_observed_at":"2026-08-09T00:21:15.587482Z","title":"PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.587482Z"},"links":{"cited_paper":"/paper/2308.16896","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:60adb22e1e384157c6a2571c7958b2b682ef401cd4cf5819c5f0bcf3c344b968","observation_id":"56a975bf-9ad9-43c8-9d9b-7a885a9e2463","resolution":{"observed_at":"2026-08-09T00:21:15.587482Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.07817","last_updated":"2023-03-02T16:41:45Z","snapshot_observed_at":"2026-07-06T14:52:11.722960Z","submitted_at":"2023-02-15T17:58:10Z","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.07817","snapshot_observed_at":"2026-08-09T00:21:15.591816Z","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.591816Z"},"links":{"cited_paper":"/paper/2302.07817","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e9b777e644db555be7193fa4f71b34b9b4bc59a64b98b7502617e2ead414e68e","observation_id":"edf6a45f-810d-4259-8505-f53ad4fa2fcf","resolution":{"observed_at":"2026-08-09T00:21:15.591816Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02413","last_updated":"2017-06-07T23:37:44Z","snapshot_observed_at":"2026-07-06T05:46:01.107746Z","submitted_at":"2017-06-07T23:37:44Z","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02413","snapshot_observed_at":"2026-08-09T00:21:15.596109Z","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.596109Z"},"links":{"cited_paper":"/paper/1706.02413","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:0538dd9d35f8acea81eb71afce83e516abc48761ba849c0e6eed7abcde7371d6","observation_id":"97682cf1-519c-4ca2-a18f-6222af35490f","resolution":{"observed_at":"2026-08-09T00:21:15.596109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.00593","last_updated":"2017-04-10T22:25:25Z","snapshot_observed_at":"2026-07-06T05:21:06.342737Z","submitted_at":"2016-12-02T08:40:40Z","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.00593","snapshot_observed_at":"2026-08-09T00:21:15.600262Z","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.600262Z"},"links":{"cited_paper":"/paper/1612.00593","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e9fe954720cc6e9889047110032bc30759a05292e3ed58ed17c795764a9e1ac2","observation_id":"6e739dea-f2fc-42b4-a54c-87b94262352a","resolution":{"observed_at":"2026-08-09T00:21:15.600262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.08889","last_updated":"2019-08-19T14:45:58Z","snapshot_observed_at":"2026-08-09T03:36:30.026773Z","submitted_at":"2019-04-18T16:55:44Z","title":"KPConv: Flexible and Deformable Convolution for Point Clouds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.08889","snapshot_observed_at":"2026-08-09T00:21:15.604689Z","title":"KPConv: Flexible and Deformable Convolution for Point Clouds,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.604689Z"},"links":{"cited_paper":"/paper/1904.08889","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:23ca57e94450c302533b5a3cd261c4a21b76ffa28b08354ffb3b539136d72de1","observation_id":"0f0c423a-4e7c-4f16-87b7-9f8b574b5639","resolution":{"observed_at":"2026-08-09T00:21:15.604689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.11236","last_updated":"2020-05-01T21:29:02Z","snapshot_observed_at":"2026-07-06T08:39:55.658012Z","submitted_at":"2019-11-25T21:15:52Z","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.11236","snapshot_observed_at":"2026-08-09T00:21:15.609814Z","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.609814Z"},"links":{"cited_paper":"/paper/1911.11236","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e84fd47caa7da5c21616e54023ed0718b247eaf3f56a22b3485859a4446c67fc","observation_id":"885b5f1f-95c1-427b-8322-78fe1e78c0bf","resolution":{"observed_at":"2026-08-09T00:21:15.609814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.05666","last_updated":"2022-10-12T17:44:57Z","snapshot_observed_at":"2026-07-06T14:03:49.583141Z","submitted_at":"2022-10-11T17:58:03Z","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.05666","snapshot_observed_at":"2026-08-09T00:21:15.614691Z","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.614691Z"},"links":{"cited_paper":"/paper/2210.05666","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e097e3d2fdb6df1503b1cec8283d6cf37072baab858cf3dd0ebc93d4d642b62b","observation_id":"1f9adfae-a589-4684-b568-89c03ecadf51","resolution":{"observed_at":"2026-08-09T00:21:15.614691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.04530","last_updated":"2021-02-08T21:04:21Z","snapshot_observed_at":"2026-08-07T10:02:05.887060Z","submitted_at":"2021-02-08T21:04:21Z","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.04530","snapshot_observed_at":"2026-08-09T00:21:15.620176Z","title":"(AF) 2 -S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.620176Z"},"links":{"cited_paper":"/paper/2102.04530","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:df70bd1bf98ae3c9d50ad3da9e14c31442a6c06134ff28a5a27712ef63ca6d1b","observation_id":"34e5abf3-37ed-4d6e-8f26-4ff2f9c88c22","resolution":{"observed_at":"2026-08-09T00:21:15.620176Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.12978","last_updated":"2021-03-24T04:24:12Z","snapshot_observed_at":"2026-08-09T08:01:35.639316Z","submitted_at":"2021-03-24T04:24:12Z","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","version":1},"cited_work":{"arxiv_id":"2103.12978","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.12978","snapshot_observed_at":"2026-08-09T00:21:17.067541Z","title":"RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation","venue":"cs.CV","work_id":"bdd40cfc-11ed-41e6-a318-bb83b1004628","year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.625269Z"},"links":{"cited_paper":"/paper/2103.12978","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:5e86ad5fea02679c4838ffe9a0c5a6ae9fec6d6dc093b9cf8ab039fa2295e833","observation_id":"2494b17f-c9a0-4c3f-91cd-0176ac1bad41","resolution":{"observed_at":"2026-08-09T00:21:17.073146Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.09385","last_updated":"2023-03-21T20:30:25Z","snapshot_observed_at":"2026-08-08T10:13:50.061629Z","submitted_at":"2022-09-19T23:39:15Z","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.09385","snapshot_observed_at":"2026-08-09T00:21:15.630087Z","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.630087Z"},"links":{"cited_paper":"/paper/2209.09385","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:fab06ca28b71151e8a7c083f5ecc15dd4362f504deecc8fb30b843c7f31ba5b7","observation_id":"e917c460-af91-491d-b691-e46f47adf7fc","resolution":{"observed_at":"2026-08-09T00:21:15.630087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/1061389","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:17.025176Z","title":"LiDAR-Camera Continuous Fusion in V oxelized Grid for Semantic Scene Completion,","venue":null,"work_id":"b846fcf7-2703-45e3-aeaf-aecd924e6531","year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.635085Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:9ab3dd94352b42704540fcabdd6b87ac361980117922dcc923816215d1fa8ac9","observation_id":"8108755b-746b-4843-abce-7d7c0f17be2e","resolution":{"observed_at":"2026-08-09T00:21:17.033077Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16404","last_updated":"2023-05-25T18:11:21Z","snapshot_observed_at":"2026-08-02T18:54:47.339514Z","submitted_at":"2023-05-25T18:11:21Z","title":"GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds","version":1},"cited_work":{"arxiv_id":"2305.16404","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.16404","snapshot_observed_at":"2026-08-09T00:21:16.937649Z","title":"GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds","venue":"cs.CV","work_id":"5953d8a3-18ca-4489-afec-f97aea542eb9","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.639968Z"},"links":{"cited_paper":"/paper/2305.16404","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:6c40ae06b9954d06860b309beb17dbfac386c6950aad85b761bf4801129cb0f4","observation_id":"66c24aba-a8fe-4c12-aa1c-48c35bb6faeb","resolution":{"observed_at":"2026-08-09T00:21:16.943187Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06018","last_updated":"2023-11-10T12:05:35Z","snapshot_observed_at":"2026-07-06T16:45:40.019771Z","submitted_at":"2023-11-10T12:05:35Z","title":"U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation","version":1},"cited_work":{"arxiv_id":"2311.06018","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.06018","snapshot_observed_at":"2026-08-09T00:21:16.913934Z","title":"U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation","venue":"cs.CV","work_id":"48dcc0fa-340d-4bcc-a1bb-12e2b9f70500","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.644988Z"},"links":{"cited_paper":"/paper/2311.06018","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:d557da3d3a17ea2101f8891cc76ace7d38a01e5ebdcb0de1ccdfa277a65840f8","observation_id":"7c585b93-7ed4-4bde-b961-fed023ed10b2","resolution":{"observed_at":"2026-08-09T00:21:16.918821Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.10985","last_updated":"2020-11-21T00:42:46Z","snapshot_observed_at":"2026-07-31T16:47:30.797355Z","submitted_at":"2020-07-21T17:59:22Z","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.10985","snapshot_observed_at":"2026-08-09T00:21:15.650253Z","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.650253Z"},"links":{"cited_paper":"/paper/2007.10985","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:f1f8033791641736572f3e39d373afff5db206c866004c9c2ab28de31f9d7ed3","observation_id":"675af4aa-bab6-454c-8f8d-151138d5df21","resolution":{"observed_at":"2026-08-09T00:21:15.650253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/9710368","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:16.868169Z","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud,","venue":null,"work_id":"392bc8d8-f05b-4956-bed5-de8a98ff67fa","year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.655356Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:fd7efa0196e03a0d525ccb2231b8f08882fb8ee9f5e5a86bccf0edb1b4d91d93","observation_id":"b4276787-2d4c-4120-9d1f-5e5380d3e54a","resolution":{"observed_at":"2026-08-09T00:21:16.877858Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/9681336","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:16.773534Z","title":"SegContrast: 3D Point Cloud Feature Representation Learning Through Self-Supervised Segment Discrimination,","venue":null,"work_id":"91b63145-64db-4da9-bb1f-ab80511d21d7","year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.660416Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:9ccd6c697d78c5859d0eb60de3b7dde9216eca726142a4f9719bca9e2c068b91","observation_id":"215d71d4-f583-43ab-a52d-1e715b100b98","resolution":{"observed_at":"2026-08-09T00:21:16.782460Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07522","last_updated":"2023-10-12T08:02:18Z","snapshot_observed_at":"2026-08-01T15:03:35.981502Z","submitted_at":"2023-10-11T14:19:05Z","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","version":2},"cited_work":{"arxiv_id":"2310.07522","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.07522","snapshot_observed_at":"2026-08-09T00:21:16.683173Z","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","venue":"cs.CV","work_id":"5b1ba891-b307-4323-9b09-64fdafcf3b76","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.665364Z"},"links":{"cited_paper":"/paper/2310.07522","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:71177767b81e1344bc80b16a32c27934c577e10f4549d93be2bfeb012dc14713","observation_id":"84032960-1f51-4456-9a2e-6b73060059a0","resolution":{"observed_at":"2026-08-09T00:21:16.689032Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09243","last_updated":"2024-08-21T12:24:49Z","snapshot_observed_at":"2026-08-06T07:01:21.861896Z","submitted_at":"2023-12-14T18:58:52Z","title":"OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09243","snapshot_observed_at":"2026-08-09T00:21:15.670429Z","title":"OccNeRF: Self-Supervised Multi-Camera Occupancy Prediction with Neural Radiance Fields,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.670429Z"},"links":{"cited_paper":"/paper/2312.09243","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:63c5261cdbd4721fb8cf095113eea4164977af7de704854293b712b99aac8b3a","observation_id":"a79acaca-85fb-434a-b618-774449ee1220","resolution":{"observed_at":"2026-08-09T00:21:15.670429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:15.675496Z","title":"Learning 3D Semantic Segmentation with only 2D Image Supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.675496Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:03bb2ee65b959d9cccba5285a814e11ca49ae7e083ee4f1c6c57ff4c83b86982","observation_id":"26792d01-dc17-4591-b56f-b0fe3dbda0bb","resolution":{"observed_at":"2026-08-09T00:21:15.675496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:18.309315Z","title":"Real-time multi- modal semantic fusion on unmanned aerial vehicles with label propagation for cross-domain adaptation,","venue":null,"work_id":"74bc57bf-2247-473f-bfb6-c9fef286dba2","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.680508Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:386f658421cd7a9dd9bf58af5207a439acb304c25370c6da8eb25ee366b6a5ee","observation_id":"0546ccd3-f00c-4a2a-bad5-26a07583cb7d","resolution":{"observed_at":"2026-08-09T00:21:18.314768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/9879430","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:16.555253Z","title":"Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data,","venue":null,"work_id":"cc169e77-5c24-4a91-92f2-818b7c29345c","year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.685298Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:fa4b8bad2cf1d5ead214b54a40fbfe62af398d48a9417493d5fe34b149069fc0","observation_id":"f791c5ea-ef06-4613-bb69-9366b2d29af8","resolution":{"observed_at":"2026-08-09T00:21:16.563769Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.05709","last_updated":"2023-03-24T15:53:21Z","snapshot_observed_at":"2026-07-06T14:41:10.087407Z","submitted_at":"2023-01-12T19:58:54Z","title":"Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss","version":2},"cited_work":{"arxiv_id":"2301.05709","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.05709","snapshot_observed_at":"2026-08-09T00:21:16.478935Z","title":"Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss","venue":"cs.CV","work_id":"38555448-8192-42b8-bc95-a2fc854f43c0","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.689994Z"},"links":{"cited_paper":"/paper/2301.05709","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:90f7e49012b55856b4cd917dda506c2f92b7198b6122cebb9aad2e763c3e919b","observation_id":"507e3f1c-4092-4718-aa08-99e46b515a3b","resolution":{"observed_at":"2026-08-09T00:21:16.484631Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09347","last_updated":"2023-10-24T09:51:00Z","snapshot_observed_at":"2026-08-04T08:57:38.242639Z","submitted_at":"2023-06-15T17:59:54Z","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09347","snapshot_observed_at":"2026-08-09T00:21:15.695219Z","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.695219Z"},"links":{"cited_paper":"/paper/2306.09347","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:43c73a0f55e4695499a909b912c2a396e2da5e9bf0f53af4990c0fa2efc7d8d6","observation_id":"5cdccce3-e9bb-4a17-98d4-4d75906cf8cf","resolution":{"observed_at":"2026-08-09T00:21:15.695219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.10150","last_updated":"2020-05-06T17:17:18Z","snapshot_observed_at":"2026-07-06T08:39:21.331834Z","submitted_at":"2019-11-22T17:19:50Z","title":"PointPainting: Sequential Fusion for 3D Object Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.10150","snapshot_observed_at":"2026-08-09T00:21:15.701262Z","title":"PointPainting: Sequential Fusion for 3D Object Detection,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.701262Z"},"links":{"cited_paper":"/paper/1911.10150","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:20366e90baa6f35b972d484cc691833eda99a9080c78a0266c1f6f78036b5afd","observation_id":"f763e50b-2c76-4457-94bd-2ec63ee4bda3","resolution":{"observed_at":"2026-08-09T00:21:15.701262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.06197","last_updated":"2023-09-12T13:04:41Z","snapshot_observed_at":"2026-07-06T16:17:26.924098Z","submitted_at":"2023-09-12T13:04:41Z","title":"360$^\\circ$ from a Single Camera: A Few-Shot Approach for LiDAR Segmentation","version":1},"cited_work":{"arxiv_id":"2309.06197","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.06197","snapshot_observed_at":"2026-08-09T00:21:16.418774Z","title":"360$^\\circ$ from a Single Camera: A Few-Shot Approach for LiDAR Segmentation","venue":"cs.CV","work_id":"16aa15b0-a830-489f-b811-bc5192349c8f","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.705543Z"},"links":{"cited_paper":"/paper/2309.06197","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:61b55170aeb09b4ba8492200c98efd3fb580c2e1cda19dd465c019fde00339d4","observation_id":"251003e1-ae1a-4683-a882-4fa3d201b623","resolution":{"observed_at":"2026-08-09T00:21:16.424559Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10115","last_updated":"2024-10-15T14:54:01Z","snapshot_observed_at":"2026-08-06T05:57:15.010459Z","submitted_at":"2024-06-14T15:21:57Z","title":"Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10115","snapshot_observed_at":"2026-08-09T00:21:15.709740Z","title":"Shelf-Supervised 8 Multi-Modal Pre-Training for 3D Object Detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.709740Z"},"links":{"cited_paper":"/paper/2406.10115","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:ef1a14fc58d26da23f4de3d2fa1fdca38466d50d0261132cc0ece51a8b49cb26","observation_id":"05699700-528c-4e82-81a2-89c34cee9987","resolution":{"observed_at":"2026-08-09T00:21:15.709740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02245","last_updated":"2024-01-29T12:14:04Z","snapshot_observed_at":"2026-07-06T15:37:39.433980Z","submitted_at":"2023-06-04T03:09:21Z","title":"SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02245","snapshot_observed_at":"2026-08-09T00:21:15.714057Z","title":"SAM3D: zero-shot 3D object detection via the segment anything model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.714057Z"},"links":{"cited_paper":"/paper/2306.02245","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:9132d9351a1296495912dafc1781e2fea9c2f23f2985725e1d7c6899c218dda6","observation_id":"bf0814b6-8520-48ff-a453-a2a13b9d2804","resolution":{"observed_at":"2026-08-09T00:21:15.714057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.14491","last_updated":"2023-09-25T19:33:52Z","snapshot_observed_at":"2026-07-06T16:23:34.422580Z","submitted_at":"2023-09-25T19:33:52Z","title":"Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving","version":1},"cited_work":{"arxiv_id":"2309.14491","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.14491","snapshot_observed_at":"2026-08-09T00:21:16.359270Z","title":"Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving","venue":"cs.CV","work_id":"df10b18f-7a99-4d21-a97b-e6a8ea7f1697","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.718227Z"},"links":{"cited_paper":"/paper/2309.14491","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:01e3bd472decda3cef59de4658303330ac2d6c630baa0718c52fcaa255c92fa8","observation_id":"5a080da4-5ac0-499d-9648-5e296ee2b261","resolution":{"observed_at":"2026-08-09T00:21:16.364730Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/1061077","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:16.336575Z","title":"OpenAnnotate3D: Open-V ocabulary Auto-Labeling System for Multi-modal 3D Data,","venue":null,"work_id":"4086e13c-9324-4ff9-aef0-c588afa5dff7","year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.723156Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:21a9f2f618b6abc8ff58f74ad56dcfa6dca9951a4cfcc4058f830158d2a317e8","observation_id":"38fec1ee-cdd2-4268-a8ff-cd5c879dbac3","resolution":{"observed_at":"2026-08-09T00:21:16.343812Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/1048024","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:16.253841Z","title":"OpenAnnotate2: Multi-Modal Auto-Annotating for Autonomous Driving,","venue":null,"work_id":"4ff625db-a7f9-43ae-96e4-3c8612cfb567","year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.728138Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:88d474463319746a82071f1f8724a9d1c32b1b6a840e1c22b14cead98a050605","observation_id":"e41d27de-8e33-446f-b3ea-669286cc56f8","resolution":{"observed_at":"2026-08-09T00:21:16.261791Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.05130","last_updated":"2016-09-28T14:32:45Z","snapshot_observed_at":"2026-08-04T16:53:24.799376Z","submitted_at":"2016-09-16T16:46:21Z","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","version":2},"cited_work":{"arxiv_id":"1609.05130","doi":null,"metadata_source":"pith","pith_arxiv_id":"1609.05130","snapshot_observed_at":"2026-08-09T00:21:16.148698Z","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","venue":"cs.CV","work_id":"e3092587-e3ab-48d1-aa3b-6e11d337f80a","year":2016},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.732746Z"},"links":{"cited_paper":"/paper/1609.05130","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:1d39f5c6e5f1fc043f3e1581cef8311fe869dbfff117a93b5fa1febbb46104c6","observation_id":"31463c03-ffa5-4640-8841-f27d1a249d8b","resolution":{"observed_at":"2026-08-09T00:21:16.154187Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:15.738334Z","title":"Real-time 3D reconstruction at scale using voxel hashing,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.738334Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:e91b7f4878fadb95316c7c123501703a03bb4f068bdebd55ee7d7f3ea097418f","observation_id":"95788f76-b013-4034-9d11-a0aeafc1ca2f","resolution":{"observed_at":"2026-08-09T00:21:15.738334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-09T00:21:15.743145Z","title":"Distilling the Knowledge in a Neural Network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.743145Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:7fecf541e853cc9835c53efaa6f45d4fc933ea4409072940ff393cfd7ce92df5","observation_id":"644442ec-c323-4219-a3e6-66be3309ad05","resolution":{"observed_at":"2026-08-09T00:21:15.743145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/9879816","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:21:16.026661Z","title":"Learning to Detect Mobile Objects from LiDAR Scans Without Labels,","venue":null,"work_id":"8fd4844f-11db-4fca-9daf-823600d04dce","year":2022},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.748226Z"},"links":{"citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:bb41fab157ef731b6dcc6c787393bde4cc7481c2ee367370d16ff7f14da875d1","observation_id":"7b402094-2189-468a-8c83-60c06a44a181","resolution":{"observed_at":"2026-08-09T00:21:16.035204Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06256","last_updated":"2024-04-09T12:29:16Z","snapshot_observed_at":"2026-07-06T17:57:44.174936Z","submitted_at":"2024-04-09T12:29:16Z","title":"Label-Efficient 3D Object Detection For Road-Side Units","version":1},"cited_work":{"arxiv_id":"2404.06256","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.06256","snapshot_observed_at":"2026-08-09T00:21:15.873739Z","title":"Label-Efficient 3D Object Detection For Road-Side Units","venue":"cs.CV","work_id":"4c787cb7-ad9b-425f-801e-2af85b2f6bd0","year":2024},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.753100Z"},"links":{"cited_paper":"/paper/2404.06256","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:c6d594807913203cc76b9717b08fa3d2839082a97f16977ebcb938cfd9d974ec","observation_id":"196d6369-a73e-4b14-b696-01b62c2cbc58","resolution":{"observed_at":"2026-08-09T00:21:15.885669Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.10100","last_updated":"2023-09-25T12:10:42Z","snapshot_observed_at":"2026-08-04T20:07:04.295826Z","submitted_at":"2023-01-24T16:10:08Z","title":"Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation","version":2},"cited_work":{"arxiv_id":"2301.10100","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.10100","snapshot_observed_at":"2026-08-09T00:21:15.850015Z","title":"Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation","venue":"cs.CV","work_id":"192fe1a8-eee6-4baf-8b34-6fde6b7862c0","year":2023},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.758022Z"},"links":{"cited_paper":"/paper/2301.10100","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:57e339b7cd25095a8aef5b72e64c58b93d6afd136eb3a218eee64c5bec77ee04","observation_id":"cc770e94-9158-4cee-a092-37fd460933f2","resolution":{"observed_at":"2026-08-09T00:21:15.855459Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.05065","last_updated":"2017-07-18T05:30:28Z","snapshot_observed_at":"2026-07-06T05:42:36.249572Z","submitted_at":"2017-05-15T04:06:22Z","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.05065","snapshot_observed_at":"2026-08-09T00:21:15.762833Z","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.762833Z"},"links":{"cited_paper":"/paper/1705.05065","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:3445fe788a710854ede36cd96f7fe4a2c4bf4b7ee55efa4800b81a497d5e3bb1","observation_id":"27f00ced-6d44-423c-bbb2-649062fcb5e7","resolution":{"observed_at":"2026-08-09T00:21:15.762833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.09783","last_updated":"2022-03-21T21:23:32Z","snapshot_observed_at":"2026-07-06T11:31:03.037112Z","submitted_at":"2021-07-20T21:57:18Z","title":"Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters","version":3},"cited_work":{"arxiv_id":"2107.09783","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.09783","snapshot_observed_at":"2026-08-09T00:21:15.807406Z","title":"Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters","venue":"cs.CV","work_id":"8480b291-4061-439e-a964-319f599e9b1d","year":2021},"citing_paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-09T00:21:15.767616Z"},"links":{"cited_paper":"/paper/2107.09783","citing_paper":"/paper/2502.03901"},"observation_digest":"sha256:55fdcbf575feac30b3002e406e32fe8a22df054210131965830ef1e274a2942f","observation_id":"d51a3d75-8e88-4958-9271-4265befddcd0","resolution":{"observed_at":"2026-08-09T00:21:15.814678Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.03901","last_updated":"2025-02-06T09:24:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T12:00:42.825498Z","submitted_at":"2025-02-06T09:24:47Z","title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":40,"verified_exact":30,"verified_fuzzy":2},"total_outbound_references":72},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 0 inbound Pith citation observations for arXiv:2502.03901."}