{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YHP33VUF6IDLYFMZILWSSKEXR2","short_pith_number":"pith:YHP33VUF","schema_version":"1.0","canonical_sha256":"c1dfbdd685f206bc159942ed2928978ea9f20fdecc3f51591729157991b8e374","source":{"kind":"arxiv","id":"2503.22496","version":1},"attestation_state":"computed","paper":{"title":"Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Anthony Gosselin, Christopher Pal, Felix Heide, Liam Paull, Luke Rowe, Roger Girgis","submitted_at":"2025-03-28T15:03:41Z","abstract_excerpt":"We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene - comprising a lane graph and agent bounding boxes - and closed-loop agent behaviours. Existing methods for generating driving simulation environments encode the initial traffic scene as a rasterized image and, as such, require parameter-heavy networks that perform unnecessary computation due to many empty pixels in the rasterized scene. Moreover, we find that existing methods that employ rule-based agent behaviours lack diversity and realism. Sc"},"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":"2503.22496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-28T15:03:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5695a6caaf1608db007723bc6c2d306c7c42279dedaee52e2a665aed8bfb5f60","abstract_canon_sha256":"aed4682d45facce1940bb3de569aef503d9d8ab98d638cd1e4e91b6863eb95b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:05.729433Z","signature_b64":"XMr9mQHtx1EtI01DyIhgJhbNpMZ4JzLlow2CBPEbKeUiSkA6q5fiB+s0JabcnWooDrs004B7HcCQHZHAl8nNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1dfbdd685f206bc159942ed2928978ea9f20fdecc3f51591729157991b8e374","last_reissued_at":"2026-07-05T10:41:05.728939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:05.728939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Anthony Gosselin, Christopher Pal, Felix Heide, Liam Paull, Luke Rowe, Roger Girgis","submitted_at":"2025-03-28T15:03:41Z","abstract_excerpt":"We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene - comprising a lane graph and agent bounding boxes - and closed-loop agent behaviours. Existing methods for generating driving simulation environments encode the initial traffic scene as a rasterized image and, as such, require parameter-heavy networks that perform unnecessary computation due to many empty pixels in the rasterized scene. Moreover, we find that existing methods that employ rule-based agent behaviours lack diversity and realism. Sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22496","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/2503.22496/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":"2503.22496","created_at":"2026-07-05T10:41:05.728998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22496v1","created_at":"2026-07-05T10:41:05.728998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22496","created_at":"2026-07-05T10:41:05.728998+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHP33VUF6IDL","created_at":"2026-07-05T10:41:05.728998+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHP33VUF6IDLYFMZ","created_at":"2026-07-05T10:41:05.728998+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHP33VUF","created_at":"2026-07-05T10:41:05.728998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.15422","citing_title":"A Survey on the Applications of Generative Artificial Intelligence in Automated Driving Systems Test Scenario Generation Methods","ref_index":91,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2","json":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2.json","graph_json":"https://pith.science/api/pith-number/YHP33VUF6IDLYFMZILWSSKEXR2/graph.json","events_json":"https://pith.science/api/pith-number/YHP33VUF6IDLYFMZILWSSKEXR2/events.json","paper":"https://pith.science/paper/YHP33VUF"},"agent_actions":{"view_html":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2","download_json":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2.json","view_paper":"https://pith.science/paper/YHP33VUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22496&json=true","fetch_graph":"https://pith.science/api/pith-number/YHP33VUF6IDLYFMZILWSSKEXR2/graph.json","fetch_events":"https://pith.science/api/pith-number/YHP33VUF6IDLYFMZILWSSKEXR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2/action/storage_attestation","attest_author":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2/action/author_attestation","sign_citation":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2/action/citation_signature","submit_replication":"https://pith.science/pith/YHP33VUF6IDLYFMZILWSSKEXR2/action/replication_record"}},"created_at":"2026-07-05T10:41:05.728998+00:00","updated_at":"2026-07-05T10:41:05.728998+00:00"}