{"as_of":"2026-08-08T09:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:80b1415f200e548beefddec0732430eeb8d7366133616ab6ae53aa56257c9601","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-15T00:16:35.376647Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2603.09420/citation-record","integrity":"/paper/2603.09420/integrity","json":"/paper/2603.09420/citation-record.json","paper":"/paper/2603.09420"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Lifelong vehicle trajectory prediction frame- work based on generative replay.IEEE Transactions on Intelligent Transportation Systems, 24(12):13729–13741, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:475d9ceb58472c1ad9e2a5bba9c1f3f24e45609262679e835fd7d057de8a5ea9","observation_id":"88803809-bd61-41a8-82e4-c12efa42ca2f","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"nuscenes: A multimodal dataset for autonomous driving","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:1b6fca1617e695670ae5f94ea7a81a51adbfe78af232e87b44e1bc58d89d5415","observation_id":"e177eb54-968d-4698-9b97-294514dab826","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"The importance of prior knowledge in precise multimodal prediction","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:e3a9c4ed93802dbbede1e7e82f5a809897fb9c11279c7eff57e0f4b11669ee1d","observation_id":"7de249cf-dd1d-4414-baea-519ccf37d009","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Modeling the background for incremental learning in semantic segmentation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:7197d6bde7723cdb4976b0e57f2c2add715f960387c084ecbbe926fb42877c42","observation_id":"62ad439a-0621-42d3-9f6a-094c61614421","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Traphic: Trajectory prediction in dense and heterogeneous traffic using weighted interactions","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:a171e34d740698696e3bbef13231d16448aac6edbb78c9e8d2944be00143c710","observation_id":"3f55c888-ada4-426a-82fd-b1a325bbfebb","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"A new knowledge distillation for incremental object detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:e59ef2322cfe9f7828b7a2c76c59679fb3121bed45c15f92f3e5cd1d2bf65f1a","observation_id":"cfd2b5ac-36cf-4df8-80b7-95419c1ef232","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Modeling vehicle interactions via modified lstm models for trajectory prediction.Ieee Access, 7:38287–38296, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:5d99260915d8adf0f58a05aa2bc49ed4af7190e53dd18ea30078cce1a4dda96c","observation_id":"9e5ca73c-f299-4c14-976f-8bcb58dc8f42","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Convolutional social pooling for vehicle trajectory prediction","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:35a994acb56f962d3ad8b0c95b96e8a6e9db7fa344f7c838e8b1c1349086dda6","observation_id":"4a82fdc1-a19d-4542-8f4f-7881c975cad0","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Multi-modal tra- jectory prediction of surrounding vehicles with maneuver based lstms","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:86851658fbfff594ac03f1af9f5f4c51e6c160cd34ea712071569d88b06734c0","observation_id":"98f4bd39-9a78-4122-b131-c234df518a74","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Motion forecasting via model-based risk minimization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:bd0541d439bbe2b8e40adb2cba700ecbf2e15adedc3b686fc65efaa1a60dc1df","observation_id":"be4b71b7-7020-4426-a447-d6a1ecf9ee91","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Stochasticity in motion: An information-theoretic approach to trajectory prediction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:1d11a985751aabf26f3addc2b9a7f49f0829a9c0520b517468a4fefe1467afef","observation_id":"4c78c43b-79f4-4edc-afca-d4c9819b625a","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Vectornet: Encoding hd maps and agent dynamics from vectorized representation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:e32754a51311376c8f1c0c0a24b09b58418f8b106eacd1ce78fe8bc2f735a18c","observation_id":"6ae319cf-b250-431e-baad-4ed08c6f15a3","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Vip3d: End-to- end visual trajectory prediction via 3d agent queries","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f3df6bb98b6e63f4d9fee0e87b675c9b403ed1c9412cc0193e3629e247f76aa2","observation_id":"c2bdc36e-c016-4da6-b8dc-21c903eff493","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:c4958dc6c8b7c65d43e2308bb49b0c1ae8f88c136f1ee953999a7ef8b36f4333","observation_id":"9d5e3dd1-7824-4f47-9439-5c7ce7f688d6","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Taxonomy-aware continual semantic segmentation in hyperbolic spaces for open-world perception.IEEE Robotics and Automation Letters, 10(2):1904–1911, 2024","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:c1c404811d5c9a75b26c8e97904af0bf59101e92b00d0d0847326eb4fb6ac55b","observation_id":"6fd15666-36ed-46da-bc8f-e0cbb33cd065","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Fiery: Future instance prediction in bird’s-eye view from surround monocular cameras","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:fd627a66281034f0dc594592de2e1772bfb80bf104256b42fe23e58d8b248770","observation_id":"8cf1916e-7607-449c-a209-3955419de717","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Planning-oriented autonomous driving","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:5801e83b5fca393544f645a59e5b1baa0b1afce20c2afabb521f8806e3beef80","observation_id":"9adbfba0-23c7-4640-bf41-9585a894d7ce","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Multi-modal motion prediction with transformer-based neural network for autonomous driving","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:c2785a3682a56b321ea46b53db9f4b906d34ec00cec19180abca3f4e2e36023a","observation_id":"560dd106-1edc-42b7-af25-6b2ed4c74844","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.02181","last_updated":"2022-12-05T11:37:41Z","snapshot_observed_at":"2026-07-06T14:26:51.875190Z","submitted_at":"2022-12-05T11:37:41Z","title":"Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.02181","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Perceive, interact, predict: Learning dynamic and static clues for end-to-end motion prediction.arXiv preprint arXiv:2212.02181, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2212.02181","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:c8996495119fc887932f0322cb86130bba53e53fbacb1a84dcce9d27a96b1d0f","observation_id":"ea01a4f3-8e99-447d-8a75-603341f60acb","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Far3d: Expanding the horizon for surround-view 3d object detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f857a7aab3182f49a1b29faccc89acb7115acc8a848f8f6125747d036681db69","observation_id":"585513ed-8d0f-407e-bcd1-20a5f3e52797","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Towards open world object detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:29be695243002b9d512620a60209c2844709ab5b37855d780b9449831e518027","observation_id":"f2141bf8-1631-4d32-920a-40338722f288","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Con- tinual learning for motion prediction model via meta- representation learning and optimal memory buffer reten- tion strategy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:31102bf385d61bd985913f7b50ab1ccc780eedd43fe81d29285ad7b3fb8a9d89","observation_id":"29a14985-3a92-410a-8995-4ea31ccb6b3b","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"An energy and gpu-computation efficient backbone network for real-time object detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:2ecb84a119b2353ac01befd2538aa9851434f27961630f3d99db784dc8655441","observation_id":"80a52b01-fb85-4fb9-b527-81af802a46d0","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17917","last_updated":"2026-05-16T14:31:34Z","snapshot_observed_at":"2026-08-03T10:52:29.870115Z","submitted_at":"2024-11-26T22:20:22Z","title":"DECODE: Domain-aware Continual Domain Expansion for Motion Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17917","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Decode: Domain- aware continual domain expansion for motion prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2411.17917","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:1ac04a679b3116eaa858449437a87f80b26d24fe5a54e1e36e83e7841c0661a4","observation_id":"5026ae4e-2d80-4338-82ff-3f31431fd0d6","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"End-to- end contextual perception and prediction with interaction transformer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:09d12b18d008a4fbf885f2919efd3dd01a8c2b9f89b587c1d84bf001ab33bdbb","observation_id":"e266b087-f408-4919-946d-ae15c4fc6f5a","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Learning lane graph representations for motion forecasting","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f1b3b4dd9c6f768dff21dda738f35c94da0610e684013b1d9eae7e6bd57ba406","observation_id":"f45e8875-5b2d-4fd3-b392-76b878d84992","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11722","last_updated":"2023-11-20T12:37:58Z","snapshot_observed_at":"2026-07-06T16:49:53.770544Z","submitted_at":"2023-11-20T12:37:58Z","title":"Sparse4D v3: Advancing End-to-End 3D Detection and Tracking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11722","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Sparse4d v3: Advancing end-to-end 3d detection and tracking.arXiv preprint arXiv:2311.11722, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2311.11722","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:daac0258df36f807fb66cde002cb953ad47d94a19e3178e540eeec2c168371cd","observation_id":"98545164-889c-4543-ba78-9b8eba6a263c","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:b3478ed04e9e20bbc1e0a9c56b595c83711bca8eb2bf427802405cfa4271b97b","observation_id":"6f7413ba-50ad-42ea-8796-043192961c8c","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05347","last_updated":"2020-11-18T20:31:18Z","snapshot_observed_at":"2026-08-06T16:41:37.864655Z","submitted_at":"2020-02-13T04:58:37Z","title":"Multi-Task Incremental Learning for Object Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05347","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Multi-task incremental learn- ing for object detection.arXiv preprint arXiv:2002.05347, 2020","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2002.05347","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:2358ec6a47ea3e06c99d0c953ecb63485c21ae9d0475d638c22b9bfcea2dda68","observation_id":"f3998bd9-b66d-4a2d-a8ee-0780a836b515","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Continual detection transformer for incremen- tal object detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:9ae15ccce95fc762e99ec3a25dcf0cbcee3dcf7385c26a357daddc40892e73e1","observation_id":"fd253679-7d14-439e-80f2-3947c9816682","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Multimodal motion prediction with stacked transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:6246412598f3f1fa6d6ed82167d85c82d3086327aa8bc1095a61a21201eda4a7","observation_id":"67ebb54e-167e-47b7-811b-61af08d7350d","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Cooler: class-incremental learning for appearance-based multiple object tracking","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:3e3de66be2eed59a51346ed5142ccac72ccdddeae8e5b530b222a9b0832b169b","observation_id":"a65f2e22-9821-42a3-ba58-c7aa30e5372c","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:bc27772216a6fbdb8b22323f55a5d81bb575832989a6fe412ecc3c2c26c6efe0","observation_id":"102b294f-b881-482c-a080-75bcfc3d4df7","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Evidential uncertainty estimation for multi-modal trajectory prediction","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:031ba60680952e977e59ffc8d8b0dd00358ac3b0245c9c99f4a023301b0d44da","observation_id":"31f3a86a-f93e-41f9-872b-77bbe7fc8349","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.05844","last_updated":"2022-07-12T21:19:04Z","snapshot_observed_at":"2026-08-01T11:42:19.399562Z","submitted_at":"2022-07-12T21:19:04Z","title":"Wayformer: Motion Forecasting via Simple & Efficient Attention Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.05844","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Wayformer: Motion forecasting via simple & efficient attention networks.arXiv preprint arXiv:2207.05844, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2207.05844","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f11fec2d5822254f29175563960ccd2e22445f5aca601cdc01a5bb21c65706a4","observation_id":"ccf2fc91-ccf9-4eca-8331-f788d92e42d4","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Forecasting from lidar via future object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:e76ab55f4a7faffa877d0bcedf155a0d685d48d58a061eec7188e294ffcf0c97","observation_id":"4c81af6e-76bd-4576-9808-1dacdc8cf087","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14159","last_updated":"2024-01-25T13:12:09Z","snapshot_observed_at":"2026-07-06T17:20:25.138890Z","submitted_at":"2024-01-25T13:12:09Z","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14159","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Grounded sam: Assembling open- world models for diverse visual tasks.arXiv preprint arXiv:2401.14159, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2401.14159","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f7d01638e91095b02ba874afb9de582e7194c95ac93b86a920b3d08986855a1e","observation_id":"f916142f-8135-4e18-9218-93869c430781","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Incremental learning of object detectors without catastrophic forgetting","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:7a0e415e8e192c15b23ea1c72dc8c493976dbb056ed1b3dae50cfd81cf030e12","observation_id":"f2cbabfe-3f48-4683-aa59-cabeb83a6823","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.10104","last_updated":"2025-08-13T18:00:55Z","snapshot_observed_at":"2026-07-06T22:12:35.584339Z","submitted_at":"2025-08-13T18:00:55Z","title":"DINOv3","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.10104","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Dinov3.arXiv preprint arXiv:2508.10104, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2508.10104","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:2995b8703dfd5b85cf909f3b7df4c70f5af822a15f59e8eb33de57096c72e4f5","observation_id":"886808d4-d67f-4114-a30d-46f06299f229","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Sparsedrive: End-to-end autonomous driving via sparse scene representation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:c10c4dcd992697877c776b6bd6c097701c940630c64e187672917b92eee54dec","observation_id":"b59988b1-6002-47a2-b692-29ba560d9f25","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Covio: Online continual learning for visual-inertial odometry","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:1ddde170f568c004837c8d1fee956cd921b218c6a6dafa990d3a43b5d2a73970","observation_id":"17e91677-7f59-4c2c-ad1d-e82b2ee4c969","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Codeps: Online continual learning for depth estimation and panoptic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:d27cb9362bca6a16583c5dbfb2e4d19405855ad8d8430c66dae6d190e850d2b7","observation_id":"f78c23f7-d84e-413b-b162-e2ccd7f4a49d","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Parkdiffusion: Heterogeneous multi- agent multi-modal trajectory prediction for automated parking using diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:9a301b8f5b6194411ec2eeec47b80b17fa8424cf1bd348aa56cb2c71ac2be458","observation_id":"17d6b14f-a8a8-4676-b59f-74a49a679d33","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Parkdiffusion++: Ego intention conditioned joint multi-agent trajectory prediction for automated parking using diffusion models.arXiv preprint arXiv:2602.20923, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:dfc2fb3cffed434c4bb3a421c7370b206a04a3f1e5fb5e15c2d05f080b1f9bd7","observation_id":"b31b7f6c-2cd6-4338-96dd-2f847c5b6374","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f28b2e0d498620ef964177259d28057e504f32e6ffb9e79fead2ea6c0e0789ce","observation_id":"e00efccb-cb14-4459-87ee-02eb1490700c","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Motion trajectory prediction based on a cnn-lstm sequential model.Science China Information Sciences, 63(11):212207, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:f3742d172e8393ad748cb5d25b18abd1fd841128890847d1417d8a1e7a27f68e","observation_id":"6d18d01d-cd57-4425-9991-efd542a9cdb3","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Towards motion forecasting with real-world perception inputs: Are end-to-end approaches competitive? In Int","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:16c8b9c696361e59d50e9904f109739b99f16eaa710e6c89acfcc85e547a7e3f","observation_id":"7184476d-41d2-4a1e-ac81-86244289b9be","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Multi-view correlation distillation for incremental object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:6000e022c04d4e8e5d7112b36bbcdc8538916c0f0d01e48ddddd0fa2135a75f8","observation_id":"cca0b00e-0e75-465b-a64e-d00adf45cccc","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Vehicle motion prediction at intersections based on the turning intention and prior trajectories model","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:e3a0622a6367fc593c94df96a3a605a380018198b9013821bae1d4b6aeee0f52","observation_id":"7746fbf4-d200-4d1f-b412-425e35ee4372","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.09743","last_updated":"2022-05-19T17:55:35Z","snapshot_observed_at":"2026-08-04T03:03:57.465654Z","submitted_at":"2022-05-19T17:55:35Z","title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.09743","snapshot_observed_at":"2026-07-15T00:16:35.376647Z","title":"Bev- erse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving.arXiv preprint arXiv:2205.09743, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"cited_paper":"/paper/2205.09743","citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:e0b8b6430e5c58e5dfb9199d7baad411b3e1a1fbe6123c0a9a6e77d891847700","observation_id":"c9564b7f-74f6-4bc5-991a-b21ea1904027","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"Hivt: Hierarchical vector transformer for multi- agent motion prediction","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:fbadfc88e06dfe7ec345b5f618c582efd64d86e54879b7ded96d73a9940b0c05","observation_id":"d0da6e99-76bf-49ee-8a9b-1199b936c859","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","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":"2026-07-15T00:16:35.376647Z","title":"A recurrent neural network solution for predicting driver intention at unsignalized intersections.IEEE Robotics and Automation Letters, 3(3):1759–1764, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-15T00:16:35.376647Z"},"links":{"citing_paper":"/paper/2603.09420"},"observation_digest":"sha256:05a2164d4af19077c1456871f7826fb536445afd73aae212593e7fef24efb03a","observation_id":"fa17dcb0-c14a-44ac-8870-6622c6e49da3","resolution":{"observed_at":"2026-07-15T00:16:35.376647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.09420","last_updated":"2026-06-18T12:01:08Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T23:56:59.501054Z","submitted_at":"2026-03-10T09:35:08Z","title":"Class-Incremental Motion Forecasting"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":52},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2603.09420."}