{"as_of":"2026-08-11T15:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:47e400496a3388c73d24b07aa0de4900066be7ff310db559ef44527388298916","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:31:12.182086Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.04815/citation-record","integrity":"/paper/2501.04815/integrity","json":"/paper/2501.04815/citation-record.json","paper":"/paper/2501.04815"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:31:12.664361Z","title":"nuscenes: A multimodal dataset for autonomous driving","venue":null,"work_id":"7bc328fe-5a65-47cf-8b24-7f33c24d93b2","year":2020},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.019204Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:f8e9ab5973f8fa16991ad04b03e4753c3b59243fbcc4e0ce162cce024e92791a","observation_id":"d9de73ed-4961-4fb5-bc73-e97dbebf1506","resolution":{"observed_at":"2026-08-10T21:31:12.668144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00493","last_updated":"2023-01-02T00:36:22Z","snapshot_observed_at":"2026-07-06T14:36:37.805357Z","submitted_at":"2023-01-02T00:36:22Z","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00493","snapshot_observed_at":"2026-08-10T21:31:12.023705Z","title":"Argoverse 2: Next generation datasets for self-driving perception and forecasting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.023705Z"},"links":{"cited_paper":"/paper/2301.00493","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:bb447d248b52bf1a4fd03069cf07a5374c1deca94c295120c6f503b13e7e61dd","observation_id":"1bfc2c24-c20f-48b2-88ca-c965fb33855f","resolution":{"observed_at":"2026-08-10T21:31:12.023705Z","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":"2026-08-10T21:31:12.654446Z","title":"Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset","venue":null,"work_id":"10b8c4a3-8d22-4c72-9296-1b9358d21529","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.029292Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:92c063fe1cbb3a765113819b07895039325c9223ab81bafaa44bedf10b56ac26","observation_id":"ecc16cf5-bd49-4f25-a123-10ebc3b77d85","resolution":{"observed_at":"2026-08-10T21:31:12.658092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.644410Z","title":"Pretram: Self-supervised pre-training via connecting trajectory and map","venue":null,"work_id":"e5936b81-30f7-4b02-b8c4-af3622efb91f","year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.033125Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:1ab0203ecbf88a5fdba9b0c2e96236c1c2551d1ca76050d2a29fee6c79957089","observation_id":"5801f6fc-4a4e-4598-9ff1-6c532c5de682","resolution":{"observed_at":"2026-08-10T21:31:12.647958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15289","last_updated":"2023-12-19T14:14:22Z","snapshot_observed_at":"2026-08-02T09:31:39.707315Z","submitted_at":"2023-09-26T21:56:03Z","title":"SEPT: Towards Efficient Scene Representation Learning for Motion Prediction","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15289","snapshot_observed_at":"2026-08-10T21:31:12.037062Z","title":"Sept: Towards efficient scene representation learning for motion prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.037062Z"},"links":{"cited_paper":"/paper/2309.15289","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:c92e9527a324579254677eed5d45b948c63917dbd8383fee431c5f1e57667536","observation_id":"40789518-260b-427e-8d2f-7ff97f0d7613","resolution":{"observed_at":"2026-08-10T21:31:12.037062Z","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":"2026-08-10T21:31:12.632897Z","title":"Forecast-MAE: Self-supervised pre-training for motion forecasting with masked autoencoders","venue":null,"work_id":"25840f4b-5ee2-41ea-9d18-40db6147be52","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.041498Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:49421d992b4eaa75e2aa4cd6737ae1c0fca24adf875cd9227fca43a2d7461e00","observation_id":"c7b36f60-a85a-4302-86a7-5725b417c1cc","resolution":{"observed_at":"2026-08-10T21:31:12.637296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.621405Z","title":"Dyset: A dynamic masked self-distillation approach for robust trajectory prediction","venue":null,"work_id":"eb64f29f-28b4-4fcd-8cf8-b1530377189a","year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.045432Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:351849f6e75df093818c17395a9cf8f757e9386eaf62d90b317e104663c9aa46","observation_id":"ca9906bd-2aa7-49fe-afb8-d9d92d1fa189","resolution":{"observed_at":"2026-08-10T21:31:12.626192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.610753Z","title":"Smartpretrain: Model-agnostic and dataset-agnostic representation learning for motion prediction, 10 2024","venue":null,"work_id":"df10837d-8f33-45f5-9eb8-14080655d565","year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.049350Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:232186789493c749546f2147764306669a477bee4ac5e3f9d0766c1086ff037e","observation_id":"154f2285-3948-446a-8d02-8ca4faac9ee0","resolution":{"observed_at":"2026-08-10T21:31:12.614490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.600594Z","title":"SSL-lanes: Self-supervised learning for motion fore- casting in autonomous driving","venue":null,"work_id":"ea6b81c1-dde8-4218-a030-3ae77020102b","year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.052972Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:be91d173dbeffdbcdb41ecae03343ede3dc0ebe6e469ce0eeb4f77406eccf9be","observation_id":"3fb2598d-6492-4e0a-bda6-3f282f9d94f8","resolution":{"observed_at":"2026-08-10T21:31:12.604247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.590082Z","title":"Social nce: Contrastive learning of socially-aware motion representations","venue":null,"work_id":"ebcdffeb-aa1d-4e46-9356-40703c64f559","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.056513Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:0d7d0fe4dbc188fec0d1715041e3f9c08cfb019d9e2ad4f5f6ae8f209e65ce34","observation_id":"1ca59c47-aaef-48b0-bc8d-14e892902013","resolution":{"observed_at":"2026-08-10T21:31:12.594055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.580359Z","title":"Perceiver: General percep- tion with iterative attention","venue":null,"work_id":"e68676ee-79cd-4fd9-9294-5701e640ebce","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.060209Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:7e4b58f9ee25b541bc3a94feb298cfbe72a7b24f9dc8f31de2866d286ebcfb41","observation_id":"587eaf52-1d9c-4770-adf1-3b75ff072c1e","resolution":{"observed_at":"2026-08-10T21:31:12.583841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.14795","last_updated":"2022-03-15T22:37:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-07-30T17:53:34Z","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.14795","snapshot_observed_at":"2026-08-10T21:31:12.063650Z","title":"Perceiver io: A general architecture for structured inputs & outputs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.063650Z"},"links":{"cited_paper":"/paper/2107.14795","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:31014bf648262db6e8efd858bb06be6cd5b2077258941d1cff389947444c8a3e","observation_id":"6a8ebaad-b9ad-4634-ad63-7b55a51f1eb5","resolution":{"observed_at":"2026-08-10T21:31:12.063650Z","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":"2026-08-10T21:31:12.569996Z","title":"Hivt: Hierarchical vector transformer for multi-agent motion prediction","venue":null,"work_id":"4a6a1bee-8c4b-47dd-a0a5-7cb7420e8e64","year":null},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.068746Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:b1abe1509d025bff64e35359c3e9b9355fecaa964d6fca3022992f0c059157f9","observation_id":"9be7401c-d1ab-4415-8150-db9b525ca223","resolution":{"observed_at":"2026-08-10T21:31:12.573674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.559636Z","title":"Motion transformer with global intention localization and local movement refinement","venue":null,"work_id":"38ca257a-55b3-4e13-aadb-e5cfedb09b94","year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.073478Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:82f998a59e205af25411fe3e1e550baae592db1c8dd0eb09b5d9a6c520088a6e","observation_id":"268b6684-9108-443d-ae43-ef76c0b3ce7f","resolution":{"observed_at":"2026-08-10T21:31:12.563405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.550076Z","title":"Hpnet: Dynamic trajectory forecasting with historical prediction attention","venue":null,"work_id":"c78a71bb-0dca-4214-b15a-2ba3b532410c","year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.077007Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:1e5cbaf7af8955b55c6534c5bf459e50e6e14fe817aa5c501bd80dea54df685b","observation_id":"1dba0b7f-3ba3-4dca-9907-0822da04d285","resolution":{"observed_at":"2026-08-10T21:31:12.553594Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.540265Z","title":"Mtr++: Multi-agent motion prediction with symmetric scene modeling and guided intention querying","venue":null,"work_id":"0afabe57-0a02-4380-9ea0-1596bba75272","year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.080475Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:2e536e8938032694e00ea9921906e10fa59d0bb8ce3f114c240136a5331798bd","observation_id":"ccfede1d-bd8b-412f-9cd6-56be715c0f54","resolution":{"observed_at":"2026-08-10T21:31:12.543770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.530034Z","title":"Wayformer: Motion forecasting via simple & efficient attention networks","venue":null,"work_id":"d49476be-9b02-4cea-8d5c-c06ccedf2000","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.084120Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:724fb98c3cbec352aff53453a9b08c237b65701ee8d681bdf0e60137d26ec160","observation_id":"5040b8d3-52e8-4b9e-a3bb-2185a7fb704a","resolution":{"observed_at":"2026-08-10T21:31:12.533653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.520361Z","title":"Motionlm: Multi-agent motion forecasting as language modeling","venue":null,"work_id":"f9f3ca02-6109-43c9-856b-b53ca7320ad7","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.087586Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:250cb0eaa13107f875090b0606cb2a9154666c5e2dddb8afb942a1de8da7c130","observation_id":"37541a20-695c-402f-9f51-3a032afc93ad","resolution":{"observed_at":"2026-08-10T21:31:12.523909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.509970Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":"ee0b13af-0bf8-4b8b-8332-fe9341e2758a","year":2020},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.090893Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:5c107e137e1ab7ed3d2fe672cab01346d42a0f2850c2434f14ab487a3d549fd9","observation_id":"e2660654-585f-4fe3-b34a-778f25e7120a","resolution":{"observed_at":"2026-08-10T21:31:12.513946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15098","last_updated":"2024-08-07T17:03:30Z","snapshot_observed_at":"2026-07-06T17:48:59.440247Z","submitted_at":"2024-03-22T10:36:50Z","title":"UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.15098","snapshot_observed_at":"2026-08-10T21:31:12.094659Z","title":"Unitraj: A unified framework for scalable vehicle trajectory prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.094659Z"},"links":{"cited_paper":"/paper/2403.15098","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:cfe74ea0c805310cc73c1244bc8420079a7fc8418557f690d43c94c8e69014e8","observation_id":"43ceb9fb-4373-4b1f-a15c-9b4eae03f020","resolution":{"observed_at":"2026-08-10T21:31:12.094659Z","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":"2026-08-10T21:31:12.499709Z","title":"Vision transformers need registers","venue":null,"work_id":"81dc3e49-20c3-48e6-87fb-61bb40c37892","year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.098697Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:18471a1648707062e65add8caa0e7a34d760b2e0c2fded342ba95a85712a69b0","observation_id":"b1522105-c620-4f55-abcc-f1e8bdb712e8","resolution":{"observed_at":"2026-08-10T21:31:12.503347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.489237Z","title":"Multimodal trajectory prediction conditioned on lane-graph traversals","venue":null,"work_id":"087993fb-ebe1-4fae-bfeb-f14c00daa66e","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.102499Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:4743eabd299cdc3a081495ae0ac12be598dc2ead8320b087ebe6e2c547746958","observation_id":"ee9ce18c-845f-49cc-8290-620d7d19dfd4","resolution":{"observed_at":"2026-08-10T21:31:12.493170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.477976Z","title":"Multimodal trajectory predictions for autonomous driving using deep convolutional networks","venue":null,"work_id":"1cb8fd97-8ac6-4679-a351-9dbb93499d71","year":2019},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.106095Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:cdc2de122644621f8a3279075d58f5e45b6608deaee6538d0d6a0b54504170e8","observation_id":"3d26d769-930e-41eb-b98c-b9be14cac843","resolution":{"observed_at":"2026-08-10T21:31:12.482160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.467587Z","title":"Latent variable sequential set transformers for joint multi-agent motion prediction","venue":null,"work_id":"f1dbe47a-751a-4559-b17d-81717de4caeb","year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.109543Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:61f7bab26444f8d102b5c85bf093ac13e5ba468c1520ee96bcd9609ea633722a","observation_id":"98e1e2e0-12ca-45dd-a0ca-9490134dc497","resolution":{"observed_at":"2026-08-10T21:31:12.471196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.456796Z","title":"Scene transformer: A unified architecture for predicting future trajectories of multiple agents","venue":null,"work_id":"c59ce549-4e47-4a76-93a5-ae4e80c0b491","year":null},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.113177Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:f6ce3a084d35ad14dedfe615983420777354607f1fb1580d196a8c5bcd97ae8b","observation_id":"54a29f08-facf-466f-af54-3d243925ccd1","resolution":{"observed_at":"2026-08-10T21:31:12.460534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.445884Z","title":"Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction","venue":null,"work_id":"20ce9759-e75a-4e92-b9ae-52d029133513","year":2020},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.116901Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:96b628face62929c8a96ee29b4b29422d222ff7448806e629bc7a4f2a08f7c8b","observation_id":"8615510f-7d08-4fb6-9059-91f64b40d6be","resolution":{"observed_at":"2026-08-10T21:31:12.449583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.435106Z","title":"Trajectory prediction for autonomous driving based on multi-head attention with joint agent-map representation","venue":null,"work_id":"341217d0-5d34-4f34-b8c0-009579e4fd72","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.120265Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:4a916532f2f0013b6db63fe2e3f542565537db991ea3a9605282d40e4714b3b0","observation_id":"33396a6c-f9c2-4b3a-9439-cd64841cc5f6","resolution":{"observed_at":"2026-08-10T21:31:12.439217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.424196Z","title":"Real-time motion prediction via hetero- geneous polyline transformer with relative pose encoding","venue":null,"work_id":"205e9ea0-5e9d-47d8-81f2-b43e0f1199df","year":null},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.123756Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:46bebd8d7912fa06ef0250c7448e63ba68f650a90b929d47c23ee24de151ea3b","observation_id":"9c552480-2897-415d-b916-166caaa414c1","resolution":{"observed_at":"2026-08-10T21:31:12.428326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.413659Z","title":"Vectornet: Encoding hd maps and agent dynamics from vectorized representation","venue":null,"work_id":"ad58b2c6-977e-435a-af59-900435e08859","year":2020},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.127902Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:1943d494f1572a394cbff862b5e92d6544b007b98ef709679cb4e489cfc04c5b","observation_id":"80ae8451-3e59-4419-8de1-cbfca52b9a77","resolution":{"observed_at":"2026-08-10T21:31:12.417402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.402987Z","title":"Lanercnn: Distributed representations for graph-centric motion forecasting","venue":null,"work_id":"503c7a5e-657c-482b-9db7-3739853dbb34","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.131447Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:efe0163447d94145a05e1e1081c106f9a18d1adda7448c826a186fade74b9e1b","observation_id":"adab9c4c-ce6d-4989-a77b-6a4bc23e3848","resolution":{"observed_at":"2026-08-10T21:31:12.406580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.134960Z","title":"Adaptive trajectory prediction via transferable gnn","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.134960Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:6fb708c0657e25597216b0dec6830684fd01147076f30cae152532cbfdec969a","observation_id":"52b5aab0-1e5f-4135-a6c3-37c5699ab434","resolution":{"observed_at":"2026-08-10T21:31:12.134960Z","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":"2026-08-10T21:31:12.385639Z","title":"Multimodal motion prediction with stacked transformers","venue":null,"work_id":"b7e41dd7-f6b6-453e-8d2d-37424ee0ab82","year":null},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.138508Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:2c20aac626a87f73097aabfc696cb4b9095782e9f036312b77503ec038070f1c","observation_id":"b5da0478-f9f7-4209-af08-6b860273fd08","resolution":{"observed_at":"2026-08-10T21:31:12.389697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.375102Z","title":"Latent variable sequential set transformers for joint multi-agent motion prediction","venue":null,"work_id":"564e3e45-6941-4908-a878-b98f2024b35b","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.142047Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:c1a30199a9bd558001371bc040c6bc96971ebea70c145edb48bf26d1a500f7e6","observation_id":"2be1e56f-438c-46e3-99a4-5e7d352e6458","resolution":{"observed_at":"2026-08-10T21:31:12.378898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.364197Z","title":"Query-centric trajectory prediction","venue":null,"work_id":"8b7cd651-b8a4-4459-bd00-4d46ec23e492","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.145648Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:5234a9fb577a7309133db0ac5fd2c8395a501b720f5038e9065a612612676984","observation_id":"46d3e926-3728-4cff-8a29-0d8ade5b819b","resolution":{"observed_at":"2026-08-10T21:31:12.367950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.353320Z","title":"Learning lane graph representations for motion forecasting","venue":null,"work_id":"d58a848e-2f04-4ade-abf3-c1819db8556d","year":2020},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.148928Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:2de104d46902a1de2de9539d05cf811baba3e2770dcba8359efe44921d371a4b","observation_id":"b8f2df6e-5d75-4670-875e-3aa526f82daf","resolution":{"observed_at":"2026-08-10T21:31:12.356836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.340831Z","title":"Hdgt: Heterogeneous driving graph transformer for multi-agent trajectory prediction via scene encoding","venue":null,"work_id":"471903c6-c503-4d13-8a23-96016893727f","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.152894Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:c82c02f9309633d98fe158050211c706ddc93a104a7f7e4bcfd0af5703fabbf2","observation_id":"5605bdc3-319f-46f6-a3fc-c183e86610f8","resolution":{"observed_at":"2026-08-10T21:31:12.345879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.329053Z","title":"Multipath++: Efficient information fusion and trajectory aggregation for behavior prediction","venue":null,"work_id":"bca5e67d-b269-4752-8006-5d4546977786","year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.156422Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:4a027e219b9e580c839f81350b86b7fc4fa36d53a356059bb351ee64d5af8ce3","observation_id":"8e19599e-990b-40c3-9dc1-cf931eb688c2","resolution":{"observed_at":"2026-08-10T21:31:12.332938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.317672Z","title":"Adapt: Efficient multi-agent trajectory prediction with adaptation","venue":null,"work_id":"a4c2a7f4-6b05-49a8-ad28-b45bc57a05c0","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.159612Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:814a2c409b6fbacff963fc22e4c8253e3a29e6ef9f5cafc90cfd2b2d881939f3","observation_id":"6b17bb02-9cf6-459c-9ff3-95e7048d9d16","resolution":{"observed_at":"2026-08-10T21:31:12.321658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T21:31:12.305689Z","title":"Densetnt: End-to-end trajectory prediction from dense goal sets","venue":null,"work_id":"9510d13a-6315-4f1c-9183-ae1ce68aae1a","year":2021},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.163580Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:4e757863c7005506cb7cf171d54c858678b49de6d066c8391973778b6cc6c0e4","observation_id":"0e13c359-d81e-47ca-b695-29238d57e6e5","resolution":{"observed_at":"2026-08-10T21:31:12.309691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.06697","last_updated":"2023-03-12T16:23:27Z","snapshot_observed_at":"2026-07-06T15:02:04.131913Z","submitted_at":"2023-03-12T16:23:27Z","title":"Traj-MAE: Masked Autoencoders for Trajectory Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.06697","snapshot_observed_at":"2026-08-10T21:31:12.166935Z","title":"Traj- mae: Masked autoencoders for trajectory prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.166935Z"},"links":{"cited_paper":"/paper/2303.06697","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:5dcb24073cd218505d8808742ee4fdef89daa37d9b6f7e2798a5a78455308cad","observation_id":"7175bffd-526f-4d41-b6fe-c11124286b9a","resolution":{"observed_at":"2026-08-10T21:31:12.166935Z","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":"2026-08-10T21:31:12.292990Z","title":"Encoder and decoder, not one less for pre-trained language model sponsored nmt","venue":null,"work_id":"33ccfcc3-7b20-4cdd-bc09-5767cf822e51","year":2023},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.170670Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:4b5bd87daab57f3bbd365ee00a69fdb5faa28b08ca55ebe65cdf64e05a4fbaae","observation_id":"03d1ac7e-df02-4d9a-8e08-625e1e82b0d3","resolution":{"observed_at":"2026-08-10T21:31:12.297851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.19564","last_updated":"2024-07-28T19:18:59Z","snapshot_observed_at":"2026-07-06T18:53:00.965448Z","submitted_at":"2024-07-28T19:18:59Z","title":"Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.19564","snapshot_observed_at":"2026-08-10T21:31:12.174513Z","title":"Forecast-peft: Parameter-efficient fine- tuning for pre-trained motion forecasting models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.174513Z"},"links":{"cited_paper":"/paper/2407.19564","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:48b6d72b016d587a8cd6a126b459b9054b78b9e4ed1b6452888792d24f888825","observation_id":"c52e02e3-d4a9-45cf-aac8-9ddb7d882fbe","resolution":{"observed_at":"2026-08-10T21:31:12.174513Z","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":"2026-08-10T21:31:12.280177Z","title":"Visual prompt tuning","venue":null,"work_id":"8ce3d862-9bbf-4d44-b978-7a55bf8dfac3","year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.178517Z"},"links":{"citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:389bce3ee8631abced5bf2335075f8fe916473ad23207bc232ea2936e7bdc922","observation_id":"32f3d4e1-bb8c-4015-b012-83c4dfc16603","resolution":{"observed_at":"2026-08-10T21:31:12.285094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.08682","last_updated":"2022-12-09T14:53:21Z","snapshot_observed_at":"2026-07-06T14:19:11.158464Z","submitted_at":"2022-11-16T05:31:49Z","title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.08682","snapshot_observed_at":"2026-08-10T21:31:12.182086Z","title":"Parameter-efficient tuning on layer normalization for pre-trained language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:31:12.182086Z"},"links":{"cited_paper":"/paper/2211.08682","citing_paper":"/paper/2501.04815"},"observation_digest":"sha256:fd26c8191aaebdbdd8575c0e0ab749f4555ef1b135ef97bbbdea14d1b62e361c","observation_id":"b3b5c208-fc20-47f6-80aa-9a26313d4274","resolution":{"observed_at":"2026-08-10T21:31:12.182086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.04815","last_updated":"2025-01-08T20:11:09Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T07:38:36.745136Z","submitted_at":"2025-01-08T20:11:09Z","title":"Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":36},"total_outbound_references":44},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2501.04815."}