{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WMP6CAPJD53BBD26OTJT6K3E7R","short_pith_number":"pith:WMP6CAPJ","schema_version":"1.0","canonical_sha256":"b31fe101e91f76108f5e74d33f2b64fc4d2f04b16365f8b433199109b5d2129f","source":{"kind":"arxiv","id":"2406.14761","version":2},"attestation_state":"computed","paper":{"title":"Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Anthony Corso, Harrison Delecki, Mansur Arief, Marcell Vazquez-Chanlatte, Marc R. Schlichting, Mykel J. Kochenderfer","submitted_at":"2024-06-20T22:22:28Z","abstract_excerpt":"Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Monte Carlo may require an enormous number of samples, while methods based on importance sampling often rely on simple parametric families that may struggle to represent the distribution over failures. We propose to sample the distribution over failures using a conditional denoising diffusion model, which has shown success in complex high-dimensional problems such as robotic task planning. We iteratively train a diffusi"},"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":"2406.14761","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-20T22:22:28Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"126bdf6799f5dfbe12b07d7da083c4ed6223cd17a47f2950d9c86abd14b1d6cb","abstract_canon_sha256":"ab5233ad8c37698259ba82a6808237d145d77eaf7bef2c8484d97ec899010b3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:08.232159Z","signature_b64":"HWOOZKSjGSqARypw7TV+UXSl9E4Psa83CM3F9/tMbOH7NRxh+8FTI3wYbkVhM4ei6/nToxxYmFKl1WtM42AcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31fe101e91f76108f5e74d33f2b64fc4d2f04b16365f8b433199109b5d2129f","last_reissued_at":"2026-07-05T11:06:08.231641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:08.231641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Based Failure Sampling for Evaluating Safety-Critical Autonomous Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Anthony Corso, Harrison Delecki, Mansur Arief, Marcell Vazquez-Chanlatte, Marc R. Schlichting, Mykel J. Kochenderfer","submitted_at":"2024-06-20T22:22:28Z","abstract_excerpt":"Validating safety-critical autonomous systems in high-dimensional domains such as robotics presents a significant challenge. Existing black-box approaches based on Markov chain Monte Carlo may require an enormous number of samples, while methods based on importance sampling often rely on simple parametric families that may struggle to represent the distribution over failures. We propose to sample the distribution over failures using a conditional denoising diffusion model, which has shown success in complex high-dimensional problems such as robotic task planning. We iteratively train a diffusi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14761","kind":"arxiv","version":2},"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/2406.14761/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":"2406.14761","created_at":"2026-07-05T11:06:08.231705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14761v2","created_at":"2026-07-05T11:06:08.231705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14761","created_at":"2026-07-05T11:06:08.231705+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMP6CAPJD53B","created_at":"2026-07-05T11:06:08.231705+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMP6CAPJD53BBD26","created_at":"2026-07-05T11:06:08.231705+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMP6CAPJ","created_at":"2026-07-05T11:06:08.231705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08459","citing_title":"Diffusion Models for Safety Validation of Autonomous Driving Systems","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R","json":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R.json","graph_json":"https://pith.science/api/pith-number/WMP6CAPJD53BBD26OTJT6K3E7R/graph.json","events_json":"https://pith.science/api/pith-number/WMP6CAPJD53BBD26OTJT6K3E7R/events.json","paper":"https://pith.science/paper/WMP6CAPJ"},"agent_actions":{"view_html":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R","download_json":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R.json","view_paper":"https://pith.science/paper/WMP6CAPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14761&json=true","fetch_graph":"https://pith.science/api/pith-number/WMP6CAPJD53BBD26OTJT6K3E7R/graph.json","fetch_events":"https://pith.science/api/pith-number/WMP6CAPJD53BBD26OTJT6K3E7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R/action/storage_attestation","attest_author":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R/action/author_attestation","sign_citation":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R/action/citation_signature","submit_replication":"https://pith.science/pith/WMP6CAPJD53BBD26OTJT6K3E7R/action/replication_record"}},"created_at":"2026-07-05T11:06:08.231705+00:00","updated_at":"2026-07-05T11:06:08.231705+00:00"}