{"as_of":"2026-08-09T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:82cd70784cb2e288b0ab921354838d756985e0bd06651eed11434be08f0b8d5d","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T13:56:33.382609Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"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/2507.19908/citation-record","integrity":"/paper/2507.19908/integrity","json":"/paper/2507.19908/citation-record.json","paper":"/paper/2507.19908"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:42.219812Z","title":"nuscenes: A multi- modal dataset for autonomous driving","venue":null,"work_id":"81ac0867-b5e7-4a1e-9433-04c469e66d2f","year":2020},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.541729Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:f2777cc0eee37d6122c315daeca5d0bfc9b11cd4bcc2d34644ada470f619eba6","observation_id":"d72ef24f-7a2b-4ab1-9c21-5c2307709d93","resolution":{"observed_at":"2026-08-06T13:56:42.297764Z","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":"1512.03012","last_updated":"2015-12-09T19:42:48Z","snapshot_observed_at":"2026-08-07T11:28:03.211074Z","submitted_at":"2015-12-09T19:42:48Z","title":"ShapeNet: An Information-Rich 3D Model Repository","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03012","snapshot_observed_at":"2026-08-06T13:56:31.545612Z","title":"Shapenet: An information-rich 3d model repository","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.545612Z"},"links":{"cited_paper":"/paper/1512.03012","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:64baece09265b4b0232f0152124cf17b5fa1c3708ef996c861b3828b90092ac4","observation_id":"b24f4778-4da6-44bf-ba61-fdd87d671f72","resolution":{"observed_at":"2026-08-06T13:56:31.545612Z","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":"2026-08-06T13:56:42.029352Z","title":"Joint classification and regression for visual tracking with fully convolutional siamese networks","venue":null,"work_id":"01342c39-a970-4286-a05d-98c70d53f64d","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.549606Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:bcacc6ffde748a3dbbc939195448e48a19b78615d3f87de124f116c67ea235c9","observation_id":"febaea86-d2ab-460e-aeb1-5bb13598f651","resolution":{"observed_at":"2026-08-06T13:56:42.139752Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:41.888888Z","title":"Scannet: Richly-annotated 3d reconstructions of indoor scenes","venue":null,"work_id":"61dcca5d-55f3-426e-9351-dd51074bdb44","year":2017},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.553025Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:da1fb7a9aaf1225e646f5d65c74a236fd1502a1bff537cf2c25f6705da9f4329","observation_id":"969c7058-5dae-4091-bdcb-762a84a196aa","resolution":{"observed_at":"2026-08-06T13:56:41.978595Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:31.557547Z","title":"Bert: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.557547Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:49fc064cfdd085ae34b71d69cd9500bc6ea9785f793d234a36fd759761b18be5","observation_id":"a2d0b9a5-a9cb-48fa-9dcc-89fd9970cacb","resolution":{"observed_at":"2026-08-06T13:56:31.557547Z","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":"2026-08-06T13:56:41.741981Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":"189b2c89-a16c-4c2a-8d58-286724e36202","year":2020},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.561505Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:aae6fd1e839dc48fe25915608a4c0a9c622e6bbc4115df80fae9add678361e2d","observation_id":"2a5f7272-f11c-4855-ac57-797ada250f6c","resolution":{"observed_at":"2026-08-06T13:56:41.816799Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:41.621702Z","title":"3d-siamrpn: An end-to-end learning method for real-time 3d single object tracking using raw point cloud","venue":null,"work_id":"86ac11d2-16fe-4e36-ae9c-299fda68b683","year":2020},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.565205Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:68e30b4fe64d1c54094535f31c1bc8432232d46a9e7e6bb68333ce5f53a7fa65","observation_id":"587e65c7-d84e-4988-8704-06be6757db90","resolution":{"observed_at":"2026-08-06T13:56:41.684779Z","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":"2110.04544","last_updated":"2025-03-25T14:34:04Z","snapshot_observed_at":"2026-08-04T10:22:52.279940Z","submitted_at":"2021-10-09T11:39:30Z","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04544","snapshot_observed_at":"2026-08-06T13:56:31.568388Z","title":"Clip-adapter: Better vision-language models with feature adapters","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.568388Z"},"links":{"cited_paper":"/paper/2110.04544","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:40d7a6540980f11696c52b0058530f413ee2a42e5f63a226a1213434c691efc6","observation_id":"5b1d91b1-9982-4e84-9702-900d907448db","resolution":{"observed_at":"2026-08-06T13:56:31.568388Z","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":"2026-08-06T13:56:41.401960Z","title":"Are we ready for autonomous driving? the kitti vision benchmark suite","venue":null,"work_id":"196f7beb-db2c-47e1-b2ec-ac22259f8f08","year":2012},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.572048Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:1d6e5927efcdb92976d68fe6ba46e50c34155b87394ed445c77ce88385336da1","observation_id":"8454964d-d7c0-4491-93fc-6f3d673afae0","resolution":{"observed_at":"2026-08-06T13:56:41.503683Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:41.230118Z","title":"Lever- aging shape completion for 3d siamese tracking","venue":null,"work_id":"8fa3c25a-6a78-440a-9b22-7a66f1cf9f5f","year":2019},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.575923Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:70d6e24da2ee9ba1c3315e17c462bccf3c426b1f79f9dcc1e8dc089d1a1849ad","observation_id":"97836163-8ee4-435a-a32d-3857002932c9","resolution":{"observed_at":"2026-08-06T13:56:41.333487Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:41.092964Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"ee286e3b-d859-409e-94b5-71c133b8e099","year":2019},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.579226Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:ba64dbbf310b3c24436be327557fbb0bb55e2180185c0540b07168b5edc3feb0","observation_id":"5fbee345-be9a-4bde-8059-e5241da8b6be","resolution":{"observed_at":"2026-08-06T13:56:41.129194Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:31.582832Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.582832Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:57b6785535f6a75efdbba2b45550a022947f6d32148b23eaf048416697992e7b","observation_id":"b6c62bb7-729a-4a04-ac78-7f41552fda06","resolution":{"observed_at":"2026-08-06T13:56:31.582832Z","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":"2026-08-06T13:56:40.926590Z","title":"Clip2point: Transfer clip to point cloud classifica- tion with image-depth pre-training","venue":null,"work_id":"d199afe3-40ce-4cf7-bb34-ec7a5310bcb7","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.586571Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:b4808f2381eff073f7764dd6c3bc5756f3739d409a212f8dd8edd3df8f5e24d1","observation_id":"6e57feda-e6da-4813-a7f1-a585260fb4a9","resolution":{"observed_at":"2026-08-06T13:56:40.981464Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.766915Z","title":"3d siamese voxel-to-bev tracker for sparse point clouds","venue":null,"work_id":"fbec7c0b-1a7e-4da9-b4e8-d2cff9f81636","year":2021},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.589641Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:32dc64b9c1dade96927546e8768c20b088685b55fc06d98b30dcd233bc557d08","observation_id":"8a47b0b6-4beb-4693-add0-027896d6fb8c","resolution":{"observed_at":"2026-08-06T13:56:40.839793Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.634379Z","title":"3d siamese transformer network for single object tracking on point clouds","venue":null,"work_id":"b5952154-9e44-4732-a0d5-bea1e35e1ae2","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.592839Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:9ccce187974edd0988385db299ace1a8620460910989df71aab66fb81db59298","observation_id":"9cfcc572-51cf-464a-af86-d222f23aaf44","resolution":{"observed_at":"2026-08-06T13:56:40.734898Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.486659Z","title":"Vi- sual prompt tuning","venue":null,"work_id":"69c81337-d6fd-404f-8c95-7b5d7ad3ad0d","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.595893Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:e0825bd360189cbe5d86ee25604dd43ec05b379e475f2f1ad76b65dd04dc5643","observation_id":"c43aa39f-11d9-4780-b4a7-55158b5d7ff6","resolution":{"observed_at":"2026-08-06T13:56:40.561198Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.367958Z","title":"Maple: Multi-modal prompt learning","venue":null,"work_id":"34ed4ce4-7222-4027-80f7-18040fa07e0a","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.599212Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:1d2f73f2fa57eb08b70f327c2e8aeea78a41958908b510f4ddb046550ef78456","observation_id":"63372031-4381-474d-ba01-40a71ad31a47","resolution":{"observed_at":"2026-08-06T13:56:40.435504Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.273162Z","title":"Temporal-aware siamese tracker: Integrate temporal context for 3d object tracking","venue":null,"work_id":"462110c8-79d6-4e6e-a14a-20bdb200decc","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.602391Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:c768ec728e35575a924d891d7be5379f506a5040b7a7a4d02561f602e504c20a","observation_id":"f94e9d99-298f-4f66-97f5-9c22a12d7ec2","resolution":{"observed_at":"2026-08-06T13:56:40.307539Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.121644Z","title":"Citetracker: Correlating image and text for visual tracking","venue":null,"work_id":"09b2b707-e8fa-4c8f-82ef-bf93dfd639dc","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.606306Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:ffa948d2b303c2e51a2048bf8a7add3c010e0c3293ff8561aff3272996dbe1f7","observation_id":"36a211f7-866d-43b0-85d4-646556000e84","resolution":{"observed_at":"2026-08-06T13:56:40.193284Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:40.027433Z","title":"Seq- track3d: Exploring sequence information for robust 3d point cloud tracking","venue":null,"work_id":"cda8485d-c23d-42ce-aad3-477109826aab","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.609601Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:2accf0a39bf81efa0a7b0b1ae8532bc58f66edd342c4cfe57f2a485338b084e3","observation_id":"9b6ec41a-22f1-4b9b-b667-78cf1dab68ea","resolution":{"observed_at":"2026-08-06T13:56:40.082273Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:39.932823Z","title":"Visual instruction tuning","venue":null,"work_id":"6a7eefae-84e5-40ef-8f24-08846edfc7dd","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.613215Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:31f54e1bf18952ea3c9a08314779e2d218249d8b0f0762aec17d9801bc78264c","observation_id":"d0406810-c8dc-424f-8795-fe3e620284cb","resolution":{"observed_at":"2026-08-06T13:56:39.970666Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:39.670708Z","title":"M3sot: multi-frame, multi- field, multi-space 3d single object tracking","venue":null,"work_id":"d6ff0316-a6ef-42b4-b662-b55525b8637c","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.616486Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:72781c7f7a4244587df8c32a7f8d0a5e5639c522d58c9f5e09eed3e0f145a717","observation_id":"12350588-e199-4356-9309-e42a53a4c9e1","resolution":{"observed_at":"2026-08-06T13:56:39.774335Z","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":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-06T13:56:31.620530Z","title":"Roberta: A robustly optimized bert pretraining approach","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.620530Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:d90750fd444248cc636581443c54de3244c1edf51cd4a6968b2774a9c3393cf7","observation_id":"90ed459f-1d6e-49ec-a23a-e88570b0ed02","resolution":{"observed_at":"2026-08-06T13:56:31.620530Z","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":"2026-08-06T13:56:39.440634Z","title":"V oxeltrack: Exploring multi-level voxel representation for 3d point cloud object tracking","venue":null,"work_id":"ad958aee-a608-4757-bf63-fb391e70c548","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.624377Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:44ab02d5b035acbeec15747713bdd58cf99db992854ab13231a19297ca628f6b","observation_id":"d67b48f0-65ce-40e8-8c70-10f08fe693b0","resolution":{"observed_at":"2026-08-06T13:56:39.549018Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:39.187430Z","title":"Modeling con- tinuous motion for 3d point cloud object tracking","venue":null,"work_id":"56b6f331-a620-4f46-92f9-54b46a1507c6","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.627553Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:4f433bde41ecc41025054f62203ac867ff5f511a340ec5c10f0bcd526b6927f9","observation_id":"1f539faa-cc48-40ed-b7aa-49314e93a6f7","resolution":{"observed_at":"2026-08-06T13:56:39.311946Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:38.911122Z","title":"Exploring point-bev fusion for 3d point cloud ob- ject tracking with transformer","venue":null,"work_id":"90e818c9-f79d-4cf6-8f80-b2bfd52877fe","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.634584Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:698fcbd2ae72640a545e342c2fbbd8acaeda8869adb748dbbd043453f3406a5d","observation_id":"de807e23-8206-48cb-adc2-4f85127e10e1","resolution":{"observed_at":"2026-08-06T13:56:39.042867Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:38.708770Z","title":"Synchronize feature extracting and matching: A single branch framework for 3d object tracking","venue":null,"work_id":"c24168a9-14c1-4373-8cff-b2341805ed53","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.647490Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:5d9352f6909923fd96a38166ffa011d433fd37c1023bd6432ef4c9c860e89dee","observation_id":"f7a3a29b-956d-4a53-a8be-b245e6a49e6d","resolution":{"observed_at":"2026-08-06T13:56:38.848877Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:38.521702Z","title":"Osp2b: One-stage point-to-box net- work for 3d siamese tracking","venue":null,"work_id":"a979cdef-2cf4-472c-ac87-2641ca7bd95c","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.661605Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:d0b6d9cfd3949becd2ba1def266b1835ff716258accee161afa864d73cb850e0","observation_id":"e2bfbe87-1483-4e8b-a8a4-3a1d38793817","resolution":{"observed_at":"2026-08-06T13:56:38.612626Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:38.387651Z","title":"Glt-t: Global-local transformer voting for 3d single object tracking in point clouds","venue":null,"work_id":"9003988d-1ffb-4ca6-b519-9e1387317269","year":1957},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.677001Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:a3c607f7e70433438ec49e10ba380b831f71120edeaf0cab076601316f3e7218","observation_id":"552b2d3f-4f57-4627-ad07-19bf220ea85c","resolution":{"observed_at":"2026-08-06T13:56:38.425473Z","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":"2401.11204","last_updated":"2024-09-08T05:31:38Z","snapshot_observed_at":"2026-07-06T17:18:16.042313Z","submitted_at":"2024-01-20T10:38:28Z","title":"Towards Category Unification of 3D Single Object Tracking on Point Clouds","version":2},"cited_work":{"arxiv_id":"2401.11204","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.11204","snapshot_observed_at":"2026-08-06T13:56:33.955283Z","title":"Towards Category Unification of 3D Single Object Tracking on Point Clouds","venue":"cs.CV","work_id":"89d0c072-8988-45a3-989a-f4bf4da2ef92","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.689869Z"},"links":{"cited_paper":"/paper/2401.11204","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:6052a8dd2755e696a21be069617494b10659f1fdb64bba7a65a15190b56397c0","observation_id":"e27c513a-f0f9-4735-a037-7ab31afa0fd4","resolution":{"observed_at":"2026-08-06T13:56:34.015675Z","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":"2407.05238","last_updated":"2025-04-23T02:03:58Z","snapshot_observed_at":"2026-08-03T21:31:46.066422Z","submitted_at":"2024-07-07T02:37:24Z","title":"P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds","version":3},"cited_work":{"arxiv_id":"2407.05238","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.05238","snapshot_observed_at":"2026-08-06T13:56:33.789205Z","title":"P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds","venue":"cs.CV","work_id":"fcab5c3d-25ad-4894-abee-77c779577d7c","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.704636Z"},"links":{"cited_paper":"/paper/2407.05238","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:5c43908eb090edaff4c83d415fc6832cb41c4056c0bd0cbceb6749e298a85e45","observation_id":"d225956c-ec66-4b29-80ad-f59b7ecaf067","resolution":{"observed_at":"2026-08-06T13:56:33.868900Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:38.183305Z","title":"St-adapter: Parameter-efficient image-to-video transfer learning","venue":null,"work_id":"99443724-97db-44bb-b894-ffc32107e15a","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.716330Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:0ec29bb06e7f49d8169979cc90def3d4aa38b6e2b0741a23ece4bd395ea96bcc","observation_id":"89db613e-c5bb-4ec1-87f9-4bc15f29869c","resolution":{"observed_at":"2026-08-06T13:56:38.258863Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:38.021631Z","title":"Masked autoencoders for point cloud self-supervised learning","venue":null,"work_id":"dcf38c87-307d-4cee-8cee-dedee364af0c","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.727798Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:d8ef5be37b365d6de7d9be95a81d1f5d33d7b90c9cb7aa6afa49844f3073834e","observation_id":"e79f93d1-338b-4da0-84ad-1d9c78e7b258","resolution":{"observed_at":"2026-08-06T13:56:38.109964Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:31.740431Z","title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.740431Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:73adfd422249dbfc62560b7d9dacaf9e4fc9dbab6b16f2ef38273074f8159f05","observation_id":"c32d41ca-d0a6-4b3e-a198-cf609fb0a5ea","resolution":{"observed_at":"2026-08-06T13:56:31.740431Z","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":"2026-08-06T13:56:37.868746Z","title":"Deep hough voting for 3d object detection in point clouds","venue":null,"work_id":"e1140214-16e2-4e71-a03b-81f50e85f22f","year":2019},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.751419Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:a06ba6b6fa16dfca8c437e38a5b1ea19567f92160f4990fe7a4db50a49241b85","observation_id":"e3ba968a-7607-4933-8b7b-ee6acce2c0b5","resolution":{"observed_at":"2026-08-06T13:56:37.935576Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:37.704668Z","title":"P2b: Point-to-box network for 3d object tracking in point clouds","venue":null,"work_id":"a8220c78-f8ed-4ff1-923b-2519febf9dc5","year":null},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.761508Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:3ff978fc6b07a4789264f132200aa7621c969db1e228d1230f04b02c56ee2f3e","observation_id":"1513e9d5-c94a-4d49-8c9d-e0da35ce6f4b","resolution":{"observed_at":"2026-08-06T13:56:37.775506Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:37.546004Z","title":"Contrast with reconstruct: Contrastive 3d representation learning guided by generative pretraining","venue":null,"work_id":"02b4c84b-1332-43d9-8584-e9a15dab1e48","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.773969Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:94b107ba37569b7b4636582c9994eb42345da913f0bb46bfc4756ebc15a94b9e","observation_id":"19bbe229-cff3-45f3-a1a6-6d47c423ff53","resolution":{"observed_at":"2026-08-06T13:56:37.614844Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:37.368361Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":"2908500a-1d20-45b3-a815-66e278b8bc4f","year":2021},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.784969Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:04b0eb26604b51b9fcac1311f9726185d0c5e5df7dadbdd06911931ee3916f31","observation_id":"93a8af8b-e6e8-4950-820a-417930847b90","resolution":{"observed_at":"2026-08-06T13:56:37.460460Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:37.264759Z","title":"Ptt: Point-track-transformer module for 3d single object tracking in point clouds","venue":null,"work_id":"da517f69-2f72-483b-86d9-284a19069585","year":2021},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.794476Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:16786d69c88fe83d1616c6a835c0ec14790ae399861037b53caa3146e89fe6e5","observation_id":"d11ae026-8a21-4e77-be75-721474429847","resolution":{"observed_at":"2026-08-06T13:56:37.288217Z","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":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-07-06T05:27:13.416519Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-06T13:56:31.813760Z","title":"Outra- geously large neural networks: The sparsely-gated mixture- of-experts layer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.813760Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:41d33040c83eb13d91a527440042d13ea998796cba85ca929852b9e903392f7f","observation_id":"930e8e08-b6e3-4eb1-bcfc-f071fcb46009","resolution":{"observed_at":"2026-08-06T13:56:31.813760Z","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":"2026-08-06T13:56:31.828206Z","title":"Scalability in perception for autonomous driving: Waymo open dataset","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.828206Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:b4249797a302d3481a102322c2b65dd2d9b49e12021a4e3ca227c79430f32cef","observation_id":"21c691a3-112e-43a2-a23c-3ec029f46a0e","resolution":{"observed_at":"2026-08-06T13:56:31.828206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-06T13:56:31.843748Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.843748Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:45f414e2d1d92c1372786694a5d8f0cd3cb3c1ff2c439a7c5673ab9ab9e92638","observation_id":"b28d8a60-3066-456d-ad60-463fb3446b80","resolution":{"observed_at":"2026-08-06T13:56:31.843748Z","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":"2026-08-06T13:56:37.100523Z","title":"Correlation pyramid network for 3d single ob- ject tracking","venue":null,"work_id":"773c9210-5109-46de-a954-89c5fe3fc793","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.859123Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:67884f10989969711098dcd04204c3d234f2409d461b65fc902963e7b26ac38f","observation_id":"00553f43-b2e5-41c3-a992-12797b607d73","resolution":{"observed_at":"2026-08-06T13:56:37.173335Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.936773Z","title":"Actionclip: Adapting language-image pretrained models for video action recognition","venue":null,"work_id":"a2642270-ff28-41ae-a2a1-fb1bb537ff74","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.873731Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:681080b18311fe3c62fdff710847a472e82d2e7ac1517845a5d3f4d51b7b8f33","observation_id":"819b2707-a359-4471-9361-5141f5cba1f1","resolution":{"observed_at":"2026-08-06T13:56:37.012684Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.791892Z","title":"M2-clip: A multimodal, multi-task adapting framework for video action recognition","venue":null,"work_id":"2fc5d52e-e4ee-42b6-a976-431b17f7d62f","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.890734Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:7e1c28944fcd7d9bbd9522893a15bfc599aa49e6eda09ff1d3a1deb21457b213","observation_id":"e9d39a8f-928c-4949-917a-ec213928a1a2","resolution":{"observed_at":"2026-08-06T13:56:36.836936Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.617173Z","title":"Dynamic graph cnn for learning on point clouds","venue":null,"work_id":"354e6d16-7cfd-48ad-8608-31e35c6376b5","year":2019},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.907844Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:4e96b7d39ca47898aaa0f2f85e3014f191210018a9c59f2461cebb6e719da18b","observation_id":"16cbe66e-6d49-4a32-b5b5-dec72ab1979b","resolution":{"observed_at":"2026-08-06T13:56:36.682972Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.413395Z","title":"Vita-clip: Video and text adaptive clip via multimodal prompting","venue":null,"work_id":"f1c6f085-cd93-4b29-b30a-158d797c4960","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:31.977714Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:ed086bb11b0369f366b92c6a91bc9c4d3e95041dc5375d216e3d9ee25666121c","observation_id":"81781aed-a55b-4271-80af-10387108ba6e","resolution":{"observed_at":"2026-08-06T13:56:36.510522Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.346740Z","title":"Boosting 3d single object tracking with 2d matching distilla- tion and 3d pre-training","venue":null,"work_id":"af879dfe-ea0c-4e52-8c9b-4d93337547e1","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.049304Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:22dc070f768bb16cdc2587549d58fca6f900546bd072559aff837998059e80d2","observation_id":"2df80ed3-345d-4152-b82a-42d7a4992cba","resolution":{"observed_at":"2026-08-06T13:56:36.370120Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.170686Z","title":"Pointcontrast: Unsupervised pre- training for 3d point cloud understanding","venue":null,"work_id":"977bb941-e625-476c-82e9-feeefecb61a0","year":2020},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.084438Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:17ad4d5f095e82215064f05869e55e7b212d77f8d3d8ea854cc42dae38ddd175","observation_id":"d51db03b-1032-48fe-b8c2-1190e1185fe8","resolution":{"observed_at":"2026-08-06T13:56:36.266139Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:36.014570Z","title":"Cxtrack: Improving 3d point cloud tracking with contextual information","venue":null,"work_id":"0ede4207-e4d0-4418-9f2a-017f6acd1ce8","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.199003Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:3c75ef9e8b7455f2d116b2293beb731be5ecdc1331cd0c776a30e70764b6a1d3","observation_id":"e58d9aa5-d45b-4c0e-91e9-f2282ed97d35","resolution":{"observed_at":"2026-08-06T13:56:36.079042Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:35.875136Z","title":"Mbptrack: Improving 3d point cloud tracking with memory networks and box priors","venue":null,"work_id":"b6179fa2-ef35-43bb-a0e1-f7847d90cc26","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.278869Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:10ab627fc7fa02bc0fb17b788ac44a09d0a717dd42b715f0e2e94fd8f3df0fcf","observation_id":"ee3de25b-7e3c-4261-84c1-2651117b93a9","resolution":{"observed_at":"2026-08-06T13:56:35.935765Z","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":"2408.01688","last_updated":"2024-09-09T05:24:27Z","snapshot_observed_at":"2026-08-05T14:12:51.064493Z","submitted_at":"2024-08-03T07:02:01Z","title":"SiamMo: Siamese Motion-Centric 3D Object Tracking","version":2},"cited_work":{"arxiv_id":"2408.01688","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.01688","snapshot_observed_at":"2026-08-06T13:56:33.617890Z","title":"SiamMo: Siamese Motion-Centric 3D Object Tracking","venue":"cs.CV","work_id":"a7c3402e-d5c3-442a-b046-ab88196dc512","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.346215Z"},"links":{"cited_paper":"/paper/2408.01688","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:3f006b5754e1d2f4b7ae93f906a6c5b1bbb8506b704d27578ca2ceb1cba2f2b9","observation_id":"c35e99c3-6d55-4f64-a017-b5183b17642c","resolution":{"observed_at":"2026-08-06T13:56:33.679201Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:35.722560Z","title":"Joint feature learning and relation modeling for tracking: A one-stream framework","venue":null,"work_id":"2fbc2ba0-a094-4b4e-b5e7-dc128b45aac3","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.444505Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:dfc3b742cdf132dd14bddec169349b3b430280f27e5140c8b805582acfd60a0d","observation_id":"835ff202-a65a-4e32-82bb-e75c9f444942","resolution":{"observed_at":"2026-08-06T13:56:35.779583Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:35.509959Z","title":"Point-bert: Pre-training 3d point cloud transformers with masked point modeling","venue":null,"work_id":"585a5c6e-bd75-4827-a59e-490ec1ed02af","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.580055Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:0554c319c29764035631acd0ccc4efac0a1ce0bb43861a10f7957c20d3fdd2b8","observation_id":"266cac8f-0521-4875-9c53-ceb6067d1af5","resolution":{"observed_at":"2026-08-06T13:56:35.623718Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:35.392128Z","title":"Instance-aware dynamic prompt tuning for pre-trained point cloud models","venue":null,"work_id":"82f98979-cdd6-4d03-bab8-385f2c2ac13d","year":2023},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.656763Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:e91bea1b4c578b10565ddbd1c458949ce9803b6f3aa7a1ad57238b7f1a86d4c9","observation_id":"be2fca86-63dd-4775-b02f-7aa809f34786","resolution":{"observed_at":"2026-08-06T13:56:35.468482Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:35.248100Z","title":"Robust 3d tracking with quality-aware shape completion","venue":null,"work_id":"eb61f72a-dcdc-4fc1-b623-fa016e2c9d13","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.739870Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:c7f5e414d960fcd234afc60a7d422974faa0535c7ad880fedb66fff97c859f0f","observation_id":"2fbea7e5-6dc8-49f8-90ec-199bf5949909","resolution":{"observed_at":"2026-08-06T13:56:35.321656Z","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":"2111.03930","last_updated":"2021-11-15T04:58:28Z","snapshot_observed_at":"2026-07-31T03:05:21.352948Z","submitted_at":"2021-11-06T18:09:22Z","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.03930","snapshot_observed_at":"2026-08-06T13:56:32.818393Z","title":"Tip-adapter: Training-free clip-adapter for better vision- language modeling","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.818393Z"},"links":{"cited_paper":"/paper/2111.03930","citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:8f39ced84de3557100f7bddb119b2993783e315a558f866d10c8a9140cbbb7df","observation_id":"10e830ff-1b4f-4dfa-8abf-d5aa7db31531","resolution":{"observed_at":"2026-08-06T13:56:32.818393Z","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":"2026-08-06T13:56:35.101802Z","title":"Pointclip: Point cloud understanding by clip","venue":null,"work_id":"4240889e-0e6a-40b0-ace3-382ab5577bf5","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:32.935143Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:b392da05fd7a881405b7a0d62c8dd51a789cdfde02ac88c378794104abe2becf","observation_id":"a5cf4468-0c26-4a72-8d36-23cb2fa10f13","resolution":{"observed_at":"2026-08-06T13:56:35.173477Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:35.007550Z","title":"Box-aware feature en- hancement for single object tracking on point clouds","venue":null,"work_id":"dcef92ea-c3ea-48cf-89c1-88a1f87011a4","year":2021},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:33.002593Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:b274e0e80919966338450fb754798104169de524a0a096a08c8926d35a17650e","observation_id":"2dbcc65a-4348-4b31-9828-843e3890f9e9","resolution":{"observed_at":"2026-08-06T13:56:35.040892Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:34.855891Z","title":"Beyond 3d siamese tracking: A motion-centric paradigm for 3d single object tracking in point clouds","venue":null,"work_id":"c7446ef3-7290-4c8e-b598-0065b815ed8a","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:33.085273Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:390c4ea8894bc940722a83a24a94ebbaa2a88d5d42a6a4965b06702393e294a0","observation_id":"28e17a64-3c71-4cd8-ba54-03ced89d2103","resolution":{"observed_at":"2026-08-06T13:56:34.890149Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:34.689225Z","title":"Odtrack: Online dense temporal token learning for visual tracking","venue":null,"work_id":"78f30cdf-e719-4cd8-8464-026ca5281faa","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:33.185662Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:3bb36e52c3d24e06a4e160d7665f3a4bf9e70012798433dc3bcb16bde2f72171","observation_id":"f45a1654-3266-41bf-8ea5-f030eb1e28c3","resolution":{"observed_at":"2026-08-06T13:56:34.778005Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:34.496722Z","title":"Pttr: Relational 3d point cloud object tracking with transformer","venue":null,"work_id":"f80f18b3-ee39-4ba2-b047-41ed6443e3db","year":2022},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:33.246022Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:2c582b343bf50fbd0550d4ff58f0d1af9bbbef96986029f6ddb50e5d82081b76","observation_id":"857194c5-f124-48ae-b1d1-5de614899427","resolution":{"observed_at":"2026-08-06T13:56:34.604003Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:34.311398Z","title":"Learning to prompt for vision-language models","venue":null,"work_id":"0c846418-7182-4bed-8e96-a090633c2556","year":null},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:33.282731Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:837e8b97b479c5e3482039f806ae2afcf4e9a7cda521870c570f7bb346de572a","observation_id":"ee6c56b4-16af-4f85-bbbc-db75cdb483ee","resolution":{"observed_at":"2026-08-06T13:56:34.397250Z","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":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:56:34.129644Z","title":"Dynamic adapter meets prompt tuning: Parameter-efficient transfer learning for point cloud analysis","venue":null,"work_id":"60ac8735-a8c0-4950-ac08-b62c2047f4c6","year":2024},"citing_paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T13:56:33.382609Z"},"links":{"citing_paper":"/paper/2507.19908"},"observation_digest":"sha256:ceb7729e726900f32a956d543515ab33b763c67d7562994b78bbff7fa365b3ca","observation_id":"94b194a9-7157-4c0f-832c-2734366993de","resolution":{"observed_at":"2026-08-06T13:56:34.190919Z","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"}}],"paper":{"arxiv_id":"2507.19908","last_updated":"2025-07-26T10:41:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T13:56:30.980881Z","submitted_at":"2025-07-26T10:41:55Z","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":3,"verified_fuzzy":51},"total_outbound_references":64},"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 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2507.19908."}