{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CFVMJAGL3RDMMBYJGPHZPOYYHW","short_pith_number":"pith:CFVMJAGL","schema_version":"1.0","canonical_sha256":"116ac480cbdc46c6070933cf97bb183da1653e71d01fb665a2e4348f9ae7e2b4","source":{"kind":"arxiv","id":"2107.04485","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Mixture Density Networks: Learning to Drive Safely from Collision Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Richard Bowden, Saber Fallah, Sampo Kuutti","submitted_at":"2021-07-09T15:16:30Z","abstract_excerpt":"Imitation learning has been widely used to learn control policies for autonomous driving based on pre-recorded data. However, imitation learning based policies have been shown to be susceptible to compounding errors when encountering states outside of the training distribution. Further, these agents have been demonstrated to be easily exploitable by adversarial road users aiming to create collisions. To overcome these shortcomings, we introduce Adversarial Mixture Density Networks (AMDN), which learns two distributions from separate datasets. The first is a distribution of safe actions learned"},"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":"2107.04485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-09T15:16:30Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"63ba3f06ce583d21b057bf2c9e49da7ffac561ec1234b1c5206f61bb43ace8a9","abstract_canon_sha256":"de7db3a758d789bbae044934e56b0a02b66f85b03f959f639f057154c12538fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:33.828935Z","signature_b64":"tV2GahX8+h8vfJM5vIGW2y4nrK3RKcnN4BTTac7R3gP0OIIrEvi+hmt0GP8RQMCqeOoUrEbS6oqMENxbQ/4CDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"116ac480cbdc46c6070933cf97bb183da1653e71d01fb665a2e4348f9ae7e2b4","last_reissued_at":"2026-07-05T02:56:33.828574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:33.828574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Mixture Density Networks: Learning to Drive Safely from Collision Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Richard Bowden, Saber Fallah, Sampo Kuutti","submitted_at":"2021-07-09T15:16:30Z","abstract_excerpt":"Imitation learning has been widely used to learn control policies for autonomous driving based on pre-recorded data. However, imitation learning based policies have been shown to be susceptible to compounding errors when encountering states outside of the training distribution. Further, these agents have been demonstrated to be easily exploitable by adversarial road users aiming to create collisions. To overcome these shortcomings, we introduce Adversarial Mixture Density Networks (AMDN), which learns two distributions from separate datasets. The first is a distribution of safe actions learned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04485","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/2107.04485/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":"2107.04485","created_at":"2026-07-05T02:56:33.828635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.04485v1","created_at":"2026-07-05T02:56:33.828635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04485","created_at":"2026-07-05T02:56:33.828635+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFVMJAGL3RDM","created_at":"2026-07-05T02:56:33.828635+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFVMJAGL3RDMMBYJ","created_at":"2026-07-05T02:56:33.828635+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFVMJAGL","created_at":"2026-07-05T02:56:33.828635+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/CFVMJAGL3RDMMBYJGPHZPOYYHW","json":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW.json","graph_json":"https://pith.science/api/pith-number/CFVMJAGL3RDMMBYJGPHZPOYYHW/graph.json","events_json":"https://pith.science/api/pith-number/CFVMJAGL3RDMMBYJGPHZPOYYHW/events.json","paper":"https://pith.science/paper/CFVMJAGL"},"agent_actions":{"view_html":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW","download_json":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW.json","view_paper":"https://pith.science/paper/CFVMJAGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.04485&json=true","fetch_graph":"https://pith.science/api/pith-number/CFVMJAGL3RDMMBYJGPHZPOYYHW/graph.json","fetch_events":"https://pith.science/api/pith-number/CFVMJAGL3RDMMBYJGPHZPOYYHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW/action/storage_attestation","attest_author":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW/action/author_attestation","sign_citation":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW/action/citation_signature","submit_replication":"https://pith.science/pith/CFVMJAGL3RDMMBYJGPHZPOYYHW/action/replication_record"}},"created_at":"2026-07-05T02:56:33.828635+00:00","updated_at":"2026-07-05T02:56:33.828635+00:00"}