{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DEMORPOHHZXQIOQGCTCKXIS5MR","short_pith_number":"pith:DEMORPOH","schema_version":"1.0","canonical_sha256":"1918e8bdc73e6f043a0614c4aba25d644686e030c86e0da1eedaeef9c84b22a0","source":{"kind":"arxiv","id":"2212.02181","version":1},"attestation_state":"computed","paper":{"title":"Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bencheng Liao, Bo Jiang, Chang Huang, Helong Zhou, Jiajie Chen, Qian Zhang, Shaoyu Chen, Tianheng Cheng, Wenyu Liu, Xinggang Wang","submitted_at":"2022-12-05T11:37:41Z","abstract_excerpt":"Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first end-to-end Transformer-based framework which jointly and interactively performs online mapping, object detection and motion prediction. PIP leverages map queries, agent queries and mode queries to encode the instance-wise information of map elements, agents and motion intentions, respectively. Based on the unified query representation, a differentiable multi-task interaction scheme is proposed to exploit the correlatio"},"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":"2212.02181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-05T11:37:41Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"5591ed47c35ac9932c3709cd6fcbe5b76e0af4bccd8dc712873eef303e690e66","abstract_canon_sha256":"562effb0e8524ca38b2d32b5f63e25a1b535e07a63033baee5d1d6d7818bfe59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:21.490141Z","signature_b64":"2uN46v6Vpq3QiE1KewivAsRu0ODkunxoQ/HKeaMTjCx02hQuW0GXj1NCXe8QfUcsFMBK7GeSVSHyOXkWIroNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1918e8bdc73e6f043a0614c4aba25d644686e030c86e0da1eedaeef9c84b22a0","last_reissued_at":"2026-07-05T05:22:21.489717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:21.489717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Bencheng Liao, Bo Jiang, Chang Huang, Helong Zhou, Jiajie Chen, Qian Zhang, Shaoyu Chen, Tianheng Cheng, Wenyu Liu, Xinggang Wang","submitted_at":"2022-12-05T11:37:41Z","abstract_excerpt":"Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first end-to-end Transformer-based framework which jointly and interactively performs online mapping, object detection and motion prediction. PIP leverages map queries, agent queries and mode queries to encode the instance-wise information of map elements, agents and motion intentions, respectively. Based on the unified query representation, a differentiable multi-task interaction scheme is proposed to exploit the correlatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02181","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/2212.02181/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":"2212.02181","created_at":"2026-07-05T05:22:21.489770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02181v1","created_at":"2026-07-05T05:22:21.489770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02181","created_at":"2026-07-05T05:22:21.489770+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEMORPOHHZXQ","created_at":"2026-07-05T05:22:21.489770+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEMORPOHHZXQIOQG","created_at":"2026-07-05T05:22:21.489770+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEMORPOH","created_at":"2026-07-05T05:22:21.489770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25736","citing_title":"UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13243","citing_title":"VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2410.22313","citing_title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09619","citing_title":"GSMap: 2D Gaussians for Online HD Mapping","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR","json":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR.json","graph_json":"https://pith.science/api/pith-number/DEMORPOHHZXQIOQGCTCKXIS5MR/graph.json","events_json":"https://pith.science/api/pith-number/DEMORPOHHZXQIOQGCTCKXIS5MR/events.json","paper":"https://pith.science/paper/DEMORPOH"},"agent_actions":{"view_html":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR","download_json":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR.json","view_paper":"https://pith.science/paper/DEMORPOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02181&json=true","fetch_graph":"https://pith.science/api/pith-number/DEMORPOHHZXQIOQGCTCKXIS5MR/graph.json","fetch_events":"https://pith.science/api/pith-number/DEMORPOHHZXQIOQGCTCKXIS5MR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR/action/storage_attestation","attest_author":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR/action/author_attestation","sign_citation":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR/action/citation_signature","submit_replication":"https://pith.science/pith/DEMORPOHHZXQIOQGCTCKXIS5MR/action/replication_record"}},"created_at":"2026-07-05T05:22:21.489770+00:00","updated_at":"2026-07-05T05:22:21.489770+00:00"}