{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QG44IM4DFBDYMAEW4YSJJ4SJAK","short_pith_number":"pith:QG44IM4D","schema_version":"1.0","canonical_sha256":"81b9c433832847860096e62494f24902a2f0a96d652ed3ff946e30ddc7509e8f","source":{"kind":"arxiv","id":"2104.11212","version":1},"attestation_state":"computed","paper":{"title":"Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam Scibior, Daniele Reda, Frank Wood, Peyman Bateni, Vasileios Lioutas","submitted_at":"2021-04-22T17:48:08Z","abstract_excerpt":"We develop a deep generative model built on a fully differentiable simulator for multi-agent trajectory prediction. Agents are modeled with conditional recurrent variational neural networks (CVRNNs), which take as input an ego-centric birdview image representing the current state of the world and output an action, consisting of steering and acceleration, which is used to derive the subsequent agent state using a kinematic bicycle model. The full simulation state is then differentiably rendered for each agent, initiating the next time step. We achieve state-of-the-art results on the INTERACTION"},"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":"2104.11212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2021-04-22T17:48:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d360ae8e805a78e17735370d25d5390cb0431afea8b365d8c1d12bcac1652a32","abstract_canon_sha256":"86a684cc7db7cbd3bda740c5420c3f3194a01ab87a805bd818ef23f036d7344d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:18.754872Z","signature_b64":"A51kzb/cZJppWXLHALLlKGPz0QiIjA/3JsUodNkAT0zbou5fZEZ6OC7X0oiz3fEivxWA2xocKIUUk/mK+tEXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b9c433832847860096e62494f24902a2f0a96d652ed3ff946e30ddc7509e8f","last_reissued_at":"2026-07-05T02:34:18.754483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:18.754483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam Scibior, Daniele Reda, Frank Wood, Peyman Bateni, Vasileios Lioutas","submitted_at":"2021-04-22T17:48:08Z","abstract_excerpt":"We develop a deep generative model built on a fully differentiable simulator for multi-agent trajectory prediction. Agents are modeled with conditional recurrent variational neural networks (CVRNNs), which take as input an ego-centric birdview image representing the current state of the world and output an action, consisting of steering and acceleration, which is used to derive the subsequent agent state using a kinematic bicycle model. The full simulation state is then differentiably rendered for each agent, initiating the next time step. We achieve state-of-the-art results on the INTERACTION"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11212","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/2104.11212/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":"2104.11212","created_at":"2026-07-05T02:34:18.754544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.11212v1","created_at":"2026-07-05T02:34:18.754544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11212","created_at":"2026-07-05T02:34:18.754544+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG44IM4DFBDY","created_at":"2026-07-05T02:34:18.754544+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG44IM4DFBDYMAEW","created_at":"2026-07-05T02:34:18.754544+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG44IM4D","created_at":"2026-07-05T02:34:18.754544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK","json":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK.json","graph_json":"https://pith.science/api/pith-number/QG44IM4DFBDYMAEW4YSJJ4SJAK/graph.json","events_json":"https://pith.science/api/pith-number/QG44IM4DFBDYMAEW4YSJJ4SJAK/events.json","paper":"https://pith.science/paper/QG44IM4D"},"agent_actions":{"view_html":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK","download_json":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK.json","view_paper":"https://pith.science/paper/QG44IM4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.11212&json=true","fetch_graph":"https://pith.science/api/pith-number/QG44IM4DFBDYMAEW4YSJJ4SJAK/graph.json","fetch_events":"https://pith.science/api/pith-number/QG44IM4DFBDYMAEW4YSJJ4SJAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK/action/storage_attestation","attest_author":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK/action/author_attestation","sign_citation":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK/action/citation_signature","submit_replication":"https://pith.science/pith/QG44IM4DFBDYMAEW4YSJJ4SJAK/action/replication_record"}},"created_at":"2026-07-05T02:34:18.754544+00:00","updated_at":"2026-07-05T02:34:18.754544+00:00"}