{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZED7WCFX3L25NVNTFINHDBKD52","short_pith_number":"pith:ZED7WCFX","schema_version":"1.0","canonical_sha256":"c907fb08b7daf5d6d5b32a1a718543eeb53d1b4a9a800b7f40eeeec1a2b082c2","source":{"kind":"arxiv","id":"2505.12327","version":1},"attestation_state":"computed","paper":{"title":"Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Albert Zhao, Stefano Soatto","submitted_at":"2025-05-18T09:44:57Z","abstract_excerpt":"We describe a robust planning method for autonomous driving that mixes normal and adversarial agent predictions output by a diffusion model trained for motion prediction. We first train a diffusion model to learn an unbiased distribution of normal agent behaviors. We then generate a distribution of adversarial predictions by biasing the diffusion model at test time to generate predictions that are likely to collide with a candidate plan. We score plans using expected cost with respect to a mixture distribution of normal and adversarial predictions, leading to a planner that is robust against a"},"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":"2505.12327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-18T09:44:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ed0217f4876a7526715428f6801214aca48de6df754723a04f8c86ad75072964","abstract_canon_sha256":"9d5a2348538348f550241ea2f91bf9c342b1f3da9b4bd4c511919e52163c66cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:02.370724Z","signature_b64":"ioLf174U1vM/6GfoWf8R9AF6eaDYTVbak55ziX0EwInK/G6UMNQCAsxC20QGsglEtINipHOiknDpB+9aNT/iAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c907fb08b7daf5d6d5b32a1a718543eeb53d1b4a9a800b7f40eeeec1a2b082c2","last_reissued_at":"2026-07-05T11:05:02.370233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:02.370233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Planning for Autonomous Driving via Mixed Adversarial Diffusion Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Albert Zhao, Stefano Soatto","submitted_at":"2025-05-18T09:44:57Z","abstract_excerpt":"We describe a robust planning method for autonomous driving that mixes normal and adversarial agent predictions output by a diffusion model trained for motion prediction. We first train a diffusion model to learn an unbiased distribution of normal agent behaviors. We then generate a distribution of adversarial predictions by biasing the diffusion model at test time to generate predictions that are likely to collide with a candidate plan. We score plans using expected cost with respect to a mixture distribution of normal and adversarial predictions, leading to a planner that is robust against a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12327","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/2505.12327/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":"2505.12327","created_at":"2026-07-05T11:05:02.370300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12327v1","created_at":"2026-07-05T11:05:02.370300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12327","created_at":"2026-07-05T11:05:02.370300+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZED7WCFX3L25","created_at":"2026-07-05T11:05:02.370300+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZED7WCFX3L25NVNT","created_at":"2026-07-05T11:05:02.370300+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZED7WCFX","created_at":"2026-07-05T11:05:02.370300+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/ZED7WCFX3L25NVNTFINHDBKD52","json":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52.json","graph_json":"https://pith.science/api/pith-number/ZED7WCFX3L25NVNTFINHDBKD52/graph.json","events_json":"https://pith.science/api/pith-number/ZED7WCFX3L25NVNTFINHDBKD52/events.json","paper":"https://pith.science/paper/ZED7WCFX"},"agent_actions":{"view_html":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52","download_json":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52.json","view_paper":"https://pith.science/paper/ZED7WCFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12327&json=true","fetch_graph":"https://pith.science/api/pith-number/ZED7WCFX3L25NVNTFINHDBKD52/graph.json","fetch_events":"https://pith.science/api/pith-number/ZED7WCFX3L25NVNTFINHDBKD52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52/action/storage_attestation","attest_author":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52/action/author_attestation","sign_citation":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52/action/citation_signature","submit_replication":"https://pith.science/pith/ZED7WCFX3L25NVNTFINHDBKD52/action/replication_record"}},"created_at":"2026-07-05T11:05:02.370300+00:00","updated_at":"2026-07-05T11:05:02.370300+00:00"}