{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QBW5WMVMGJ7ODSCN3NQS3BTID5","short_pith_number":"pith:QBW5WMVM","schema_version":"1.0","canonical_sha256":"806ddb32ac327ee1c84ddb612d86681f498995ab5493b9dcac5bf4532c39c44f","source":{"kind":"arxiv","id":"2005.04259","version":1},"attestation_state":"computed","paper":{"title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chen Sun, Congcong Li, Cordelia Schmid, Dragomir Anguelov, Hang Zhao, Jiyang Gao, Yi Shen","submitted_at":"2020-05-08T19:07:03Z","abstract_excerpt":"Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights). This paper introduces VectorNet, a hierarchical graph neural network that first exploits the spatial locality of individual road components represented by vectors and then models the high-order interactions among all components. In contrast to most recent approaches, which render trajectories of mov"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2005.04259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-08T19:07:03Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6c4e9bbda2562e53bfb490a297dd694f01094ebae4e3c00d1e86e3fb5249448b","abstract_canon_sha256":"4ebca7d41efa9c0d87d1155480d163bd4693dd32704b83a9bd439ad301074492"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:42.219179Z","signature_b64":"X9XCQ8VYO4NHpOL+Ll4KQ2li4WULJ57JNS2+FrjEvc8iF0FzyAUT4n2ARFO0I9JOcHXkD78sRmwMid2c4ONmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"806ddb32ac327ee1c84ddb612d86681f498995ab5493b9dcac5bf4532c39c44f","last_reissued_at":"2026-07-05T01:01:42.218669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:42.218669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chen Sun, Congcong Li, Cordelia Schmid, Dragomir Anguelov, Hang Zhao, Jiyang Gao, Yi Shen","submitted_at":"2020-05-08T19:07:03Z","abstract_excerpt":"Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights). This paper introduces VectorNet, a hierarchical graph neural network that first exploits the spatial locality of individual road components represented by vectors and then models the high-order interactions among all components. In contrast to most recent approaches, which render trajectories of mov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04259","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.04259/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.04259","created_at":"2026-07-05T01:01:42.218740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04259v1","created_at":"2026-07-05T01:01:42.218740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04259","created_at":"2026-07-05T01:01:42.218740+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBW5WMVMGJ7O","created_at":"2026-07-05T01:01:42.218740+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBW5WMVMGJ7ODSCN","created_at":"2026-07-05T01:01:42.218740+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBW5WMVM","created_at":"2026-07-05T01:01:42.218740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23588","citing_title":"A Generative Model for Closed-Loop Microsimulation of Signalized Intersections","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02930","citing_title":"BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01393","citing_title":"Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11081","citing_title":"MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5","json":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5.json","graph_json":"https://pith.science/api/pith-number/QBW5WMVMGJ7ODSCN3NQS3BTID5/graph.json","events_json":"https://pith.science/api/pith-number/QBW5WMVMGJ7ODSCN3NQS3BTID5/events.json","paper":"https://pith.science/paper/QBW5WMVM"},"agent_actions":{"view_html":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5","download_json":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5.json","view_paper":"https://pith.science/paper/QBW5WMVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04259&json=true","fetch_graph":"https://pith.science/api/pith-number/QBW5WMVMGJ7ODSCN3NQS3BTID5/graph.json","fetch_events":"https://pith.science/api/pith-number/QBW5WMVMGJ7ODSCN3NQS3BTID5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5/action/storage_attestation","attest_author":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5/action/author_attestation","sign_citation":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5/action/citation_signature","submit_replication":"https://pith.science/pith/QBW5WMVMGJ7ODSCN3NQS3BTID5/action/replication_record"}},"created_at":"2026-07-05T01:01:42.218740+00:00","updated_at":"2026-07-05T01:01:42.218740+00:00"}