{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AF65UX43ANZONLC6HPVCMZ6FAN","short_pith_number":"pith:AF65UX43","schema_version":"1.0","canonical_sha256":"017dda5f9b0372e6ac5e3bea2667c50373a52cf4504d845f27611b73dd417e7f","source":{"kind":"arxiv","id":"2403.05489","version":2},"attestation_state":"computed","paper":{"title":"JointMotion: Joint Self-Supervision for Joint Motion Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Carlos Fernandez, Marvin Klemp, Omer Sahin Tas, Royden Wagner","submitted_at":"2024-03-08T17:54:38Z","abstract_excerpt":"We present JointMotion, a self-supervised pre-training method for joint motion prediction in self-driving vehicles. Our method jointly optimizes a scene-level objective connecting motion and environments, and an instance-level objective to refine learned representations. Scene-level representations are learned via non-contrastive similarity learning of past motion sequences and environment context. At the instance level, we use masked autoencoding to refine multimodal polyline representations. We complement this with an adaptive pre-training decoder that enables JointMotion to generalize acros"},"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":"2403.05489","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-08T17:54:38Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"da3d7e6c1d2f2a986e22f3851faa52d23cc97b47973546ad6eaed1fa0828c98b","abstract_canon_sha256":"a5fdb02f3a656fbf3803406e8afca695c1defbee951d3343b207f25dbf855c62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:33.045651Z","signature_b64":"Ws68WIRwomiJjMMsky7NkaqsnuwzSO6j6TUzFrXH01ezQTpTHB21juGkF262+qjo1fRwp9Gya7G9Udd3Kgd0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"017dda5f9b0372e6ac5e3bea2667c50373a52cf4504d845f27611b73dd417e7f","last_reissued_at":"2026-07-05T09:24:33.045160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:33.045160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JointMotion: Joint Self-Supervision for Joint Motion Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Carlos Fernandez, Marvin Klemp, Omer Sahin Tas, Royden Wagner","submitted_at":"2024-03-08T17:54:38Z","abstract_excerpt":"We present JointMotion, a self-supervised pre-training method for joint motion prediction in self-driving vehicles. Our method jointly optimizes a scene-level objective connecting motion and environments, and an instance-level objective to refine learned representations. Scene-level representations are learned via non-contrastive similarity learning of past motion sequences and environment context. At the instance level, we use masked autoencoding to refine multimodal polyline representations. We complement this with an adaptive pre-training decoder that enables JointMotion to generalize acros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05489","kind":"arxiv","version":2},"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/2403.05489/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":"2403.05489","created_at":"2026-07-05T09:24:33.045212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05489v2","created_at":"2026-07-05T09:24:33.045212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05489","created_at":"2026-07-05T09:24:33.045212+00:00"},{"alias_kind":"pith_short_12","alias_value":"AF65UX43ANZO","created_at":"2026-07-05T09:24:33.045212+00:00"},{"alias_kind":"pith_short_16","alias_value":"AF65UX43ANZONLC6","created_at":"2026-07-05T09:24:33.045212+00:00"},{"alias_kind":"pith_short_8","alias_value":"AF65UX43","created_at":"2026-07-05T09:24:33.045212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13646","citing_title":"Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23262","citing_title":"EMMA: End-to-End Multimodal Model for Autonomous Driving","ref_index":220,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13646","citing_title":"Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN","json":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN.json","graph_json":"https://pith.science/api/pith-number/AF65UX43ANZONLC6HPVCMZ6FAN/graph.json","events_json":"https://pith.science/api/pith-number/AF65UX43ANZONLC6HPVCMZ6FAN/events.json","paper":"https://pith.science/paper/AF65UX43"},"agent_actions":{"view_html":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN","download_json":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN.json","view_paper":"https://pith.science/paper/AF65UX43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05489&json=true","fetch_graph":"https://pith.science/api/pith-number/AF65UX43ANZONLC6HPVCMZ6FAN/graph.json","fetch_events":"https://pith.science/api/pith-number/AF65UX43ANZONLC6HPVCMZ6FAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN/action/storage_attestation","attest_author":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN/action/author_attestation","sign_citation":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN/action/citation_signature","submit_replication":"https://pith.science/pith/AF65UX43ANZONLC6HPVCMZ6FAN/action/replication_record"}},"created_at":"2026-07-05T09:24:33.045212+00:00","updated_at":"2026-07-05T09:24:33.045212+00:00"}