{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N2IFUTZFNGVQ7QLL2UPHGY4YUB","short_pith_number":"pith:N2IFUTZF","schema_version":"1.0","canonical_sha256":"6e905a4f2569ab0fc16bd51e736398a06314391e5ff9d6eef4dd5d329f8a9b2f","source":{"kind":"arxiv","id":"2003.01197","version":3},"attestation_state":"computed","paper":{"title":"Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Baiming Chen, Ding Zhao, Minjun Xu, Wenhao Ding","submitted_at":"2020-03-02T21:26:03Z","abstract_excerpt":"Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safety-critical scenarios for evaluating specific task algorithms. We first represent the traffic scenarios with a series of autoregressive building blocks and generate diverse scenarios by sampling from the joint distribution of these blocks. We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving 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":"2003.01197","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-03-02T21:26:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d3d8fa958d91d95b0ffc220bacd3a15a5ae8186d383105f073dd8f33094e0677","abstract_canon_sha256":"42d30423267466f9508d4adaee5a46973ee2bb2290799ce1e1b7f560dd4f950c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:36.406467Z","signature_b64":"3tBEfP86E6yWGsi0117TVL6TGnc8tXJSU/nhTJbSrUvvmkVP4VaS3G0PpFnS0aSPoSgDbpOZI0yAildazcmbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e905a4f2569ab0fc16bd51e736398a06314391e5ff9d6eef4dd5d329f8a9b2f","last_reissued_at":"2026-07-05T01:21:36.405984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:36.405984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Baiming Chen, Ding Zhao, Minjun Xu, Wenhao Ding","submitted_at":"2020-03-02T21:26:03Z","abstract_excerpt":"Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safety-critical scenarios for evaluating specific task algorithms. We first represent the traffic scenarios with a series of autoregressive building blocks and generate diverse scenarios by sampling from the joint distribution of these blocks. We then train the generative model as an agent (or a generator) to investigate the risky distribution parameters for a given driving a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01197","kind":"arxiv","version":3},"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/2003.01197/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":"2003.01197","created_at":"2026-07-05T01:21:36.406057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.01197v3","created_at":"2026-07-05T01:21:36.406057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01197","created_at":"2026-07-05T01:21:36.406057+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2IFUTZFNGVQ","created_at":"2026-07-05T01:21:36.406057+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2IFUTZFNGVQ7QLL","created_at":"2026-07-05T01:21:36.406057+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2IFUTZF","created_at":"2026-07-05T01:21:36.406057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15587","citing_title":"Red-Team Multi-Agent Reinforcement Learning for Emergency Braking Scenario","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB","json":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB.json","graph_json":"https://pith.science/api/pith-number/N2IFUTZFNGVQ7QLL2UPHGY4YUB/graph.json","events_json":"https://pith.science/api/pith-number/N2IFUTZFNGVQ7QLL2UPHGY4YUB/events.json","paper":"https://pith.science/paper/N2IFUTZF"},"agent_actions":{"view_html":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB","download_json":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB.json","view_paper":"https://pith.science/paper/N2IFUTZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.01197&json=true","fetch_graph":"https://pith.science/api/pith-number/N2IFUTZFNGVQ7QLL2UPHGY4YUB/graph.json","fetch_events":"https://pith.science/api/pith-number/N2IFUTZFNGVQ7QLL2UPHGY4YUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB/action/storage_attestation","attest_author":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB/action/author_attestation","sign_citation":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB/action/citation_signature","submit_replication":"https://pith.science/pith/N2IFUTZFNGVQ7QLL2UPHGY4YUB/action/replication_record"}},"created_at":"2026-07-05T01:21:36.406057+00:00","updated_at":"2026-07-05T01:21:36.406057+00:00"}