{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DBN6PDFNQVFXCTOIIGZMYGHZQJ","short_pith_number":"pith:DBN6PDFN","schema_version":"1.0","canonical_sha256":"185be78cad854b714dc841b2cc18f982468cb19c1e4de5ca3e1fce73355fa294","source":{"kind":"arxiv","id":"2605.12710","version":1},"attestation_state":"computed","paper":{"title":"Belief-Space Residual Risk for Automated Driving under Localization Uncertainty","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Residual risk assessment for automated driving is extended into belief space by modeling ego pose uncertainty as a Gaussian distribution and reformulating risk as an expectation over that belief.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Frank Diermeyer, Nijinshan Karunainayagam, Nils Gehrke","submitted_at":"2026-05-12T20:16:52Z","abstract_excerpt":"Residual risk metrics have recently been introduced to assess the safety implications of automated driving systems. Existing approaches typically assume a deterministic ego pose and concentrate mainly on perception errors related to surrounding objects and latency effects. In practice, however, automated vehicles operate under considerable localization uncertainty, especially in complex urban settings and in adverse weather conditions. This work extends the spatial residual risk formulation to the belief space by explicitly modeling ego pose uncertainty as a Gaussian distribution. Residual ris"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-12T20:16:52Z","cross_cats_sorted":[],"title_canon_sha256":"8ab931a7397046fda9bcc4c4fd1711fb1d48416d5eb6a8c83dd596068d558b79","abstract_canon_sha256":"4b6d0769b15a9ec1059311e845496a57ee7f72b4f823d3946b8c9b2239e45957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:49.557732Z","signature_b64":"i9mum4ud0PX6mI7ns68+fe0EjEawqXsKJvNOoADkSa1DQ8lz1dh94PGvgrBWQ4q+dbEu7HEylg7ZMyo3vpLbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"185be78cad854b714dc841b2cc18f982468cb19c1e4de5ca3e1fce73355fa294","last_reissued_at":"2026-05-18T03:09:49.556707Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:49.556707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Belief-Space Residual Risk for Automated Driving under Localization Uncertainty","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Residual risk assessment for automated driving is extended into belief space by modeling ego pose uncertainty as a Gaussian distribution and reformulating risk as an expectation over that belief.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Frank Diermeyer, Nijinshan Karunainayagam, Nils Gehrke","submitted_at":"2026-05-12T20:16:52Z","abstract_excerpt":"Residual risk metrics have recently been introduced to assess the safety implications of automated driving systems. Existing approaches typically assume a deterministic ego pose and concentrate mainly on perception errors related to surrounding objects and latency effects. In practice, however, automated vehicles operate under considerable localization uncertainty, especially in complex urban settings and in adverse weather conditions. This work extends the spatial residual risk formulation to the belief space by explicitly modeling ego pose uncertainty as a Gaussian distribution. Residual ris"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This work extends the spatial residual risk formulation to the belief space by explicitly modeling ego pose uncertainty as a Gaussian distribution. Residual risk is reformulated as the expected degradation-induced risk over the ego pose belief distribution.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That ego pose uncertainty is adequately captured by a single Gaussian and that covariance fusion of ego and object uncertainties produces accurate collision probabilities within the particle-based framework.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reformulates residual risk as the expected value over a Gaussian ego-pose belief distribution and incorporates it into particle-based collision probabilities via covariance fusion.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Residual risk assessment for automated driving is extended into belief space by modeling ego pose uncertainty as a Gaussian distribution and reformulating risk as an expectation over that belief.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fa484db985113bfd96119109236c5fa8a3e390db0207d651ff6023482f63b8f1"},"source":{"id":"2605.12710","kind":"arxiv","version":1},"verdict":{"id":"e9eb5afc-af80-4098-a056-0a3b645ac755","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:00:51.804121Z","strongest_claim":"This work extends the spatial residual risk formulation to the belief space by explicitly modeling ego pose uncertainty as a Gaussian distribution. Residual risk is reformulated as the expected degradation-induced risk over the ego pose belief distribution.","one_line_summary":"Reformulates residual risk as the expected value over a Gaussian ego-pose belief distribution and incorporates it into particle-based collision probabilities via covariance fusion.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That ego pose uncertainty is adequately captured by a single Gaussian and that covariance fusion of ego and object uncertainties produces accurate collision probabilities within the particle-based framework.","pith_extraction_headline":"Residual risk assessment for automated driving is extended into belief space by modeling ego pose uncertainty as a Gaussian distribution and reformulating risk as an expectation over that belief."},"references":{"count":23,"sample":[{"doi":"","year":2011,"title":"Road vehicles – Functional safety,","work_id":"77e4b8f4-2270-4f46-a1e4-c1e8ef597128","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Is it safe to drive? an overview of factors, metrics, and datasets for driveability assessment in au- tonomous driving,","work_id":"899f069d-1c93-4c37-a4a3-11af30b83a40","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"State Estimation Based on Generalized Gaussian Distributions,","work_id":"dfbcad48-0bba-4195-bab2-535bfa3aa938","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Tumdot–muc: Data collection and processing of multimodal trajectories collected by aerial drones,","work_id":"451e528e-17db-408c-9146-e477f12b2160","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Introducing spatial residual risk for information degradation in automated driving,","work_id":"f837ad67-dcb3-4e64-83c2-d2ead492cb64","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"ba7787e979998344df2a0af9886c9d03d49efab4a1ddc2c2d9433b33133c9209","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bfaad18fcb07e9275e3baddf07f358d23c887ad30ee3454bf9f771db8c6b3d72"},"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":"2605.12710","created_at":"2026-05-18T03:09:49.556907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12710v1","created_at":"2026-05-18T03:09:49.556907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12710","created_at":"2026-05-18T03:09:49.556907+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBN6PDFNQVFX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBN6PDFNQVFXCTOI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBN6PDFN","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ","json":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ.json","graph_json":"https://pith.science/api/pith-number/DBN6PDFNQVFXCTOIIGZMYGHZQJ/graph.json","events_json":"https://pith.science/api/pith-number/DBN6PDFNQVFXCTOIIGZMYGHZQJ/events.json","paper":"https://pith.science/paper/DBN6PDFN"},"agent_actions":{"view_html":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ","download_json":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ.json","view_paper":"https://pith.science/paper/DBN6PDFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12710&json=true","fetch_graph":"https://pith.science/api/pith-number/DBN6PDFNQVFXCTOIIGZMYGHZQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DBN6PDFNQVFXCTOIIGZMYGHZQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ/action/storage_attestation","attest_author":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ/action/author_attestation","sign_citation":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ/action/citation_signature","submit_replication":"https://pith.science/pith/DBN6PDFNQVFXCTOIIGZMYGHZQJ/action/replication_record"}},"created_at":"2026-05-18T03:09:49.556907+00:00","updated_at":"2026-05-18T03:09:49.556907+00:00"}