{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:F6EASRTBLW7PF5UQW64MKNXW45","short_pith_number":"pith:F6EASRTB","schema_version":"1.0","canonical_sha256":"2f880946615dbef2f690b7b8c536f6e777fe64a3c92bdf9810dc75db7b390625","source":{"kind":"arxiv","id":"1805.04829","version":2},"attestation_state":"computed","paper":{"title":"Spatial Uncertainty Sampling for End-to-End Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alexander Amini, Ava Soleimany, Daniela Rus, Sertac Karaman","submitted_at":"2018-05-13T06:19:14Z","abstract_excerpt":"End-to-end trained neural networks (NNs) are a compelling approach to autonomous vehicle control because of their ability to learn complex tasks without manual engineering of rule-based decisions. However, challenging road conditions, ambiguous navigation situations, and safety considerations require reliable uncertainty estimation for the eventual adoption of full-scale autonomous vehicles. Bayesian deep learning approaches provide a way to estimate uncertainty by approximating the posterior distribution of weights given a set of training data. Dropout training in deep NNs approximates Bayesi"},"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":"1805.04829","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-13T06:19:14Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"bfdf7d518ffdd9c3e57940b0cfbe6fa0f819c131215803029bca3ed5df14d8f6","abstract_canon_sha256":"30c76dc1628a2e5d8bb6a50e1c241588e10162b71fd04d4c8faaf0ea4aa31983"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:18.857446Z","signature_b64":"Jrac326tRBDgHSn4Kz9FBAUYSj8oq40XAi8iv1zlzFJ8dJomG1NPW8qxwWfcnwGJe5+CuevHThV6zeY1MugyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f880946615dbef2f690b7b8c536f6e777fe64a3c92bdf9810dc75db7b390625","last_reissued_at":"2026-07-05T03:34:18.856962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:18.856962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial Uncertainty Sampling for End-to-End Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Alexander Amini, Ava Soleimany, Daniela Rus, Sertac Karaman","submitted_at":"2018-05-13T06:19:14Z","abstract_excerpt":"End-to-end trained neural networks (NNs) are a compelling approach to autonomous vehicle control because of their ability to learn complex tasks without manual engineering of rule-based decisions. However, challenging road conditions, ambiguous navigation situations, and safety considerations require reliable uncertainty estimation for the eventual adoption of full-scale autonomous vehicles. Bayesian deep learning approaches provide a way to estimate uncertainty by approximating the posterior distribution of weights given a set of training data. Dropout training in deep NNs approximates Bayesi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04829","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/1805.04829/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":"1805.04829","created_at":"2026-07-05T03:34:18.857019+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04829v2","created_at":"2026-07-05T03:34:18.857019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04829","created_at":"2026-07-05T03:34:18.857019+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6EASRTBLW7P","created_at":"2026-07-05T03:34:18.857019+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6EASRTBLW7PF5UQ","created_at":"2026-07-05T03:34:18.857019+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6EASRTB","created_at":"2026-07-05T03:34:18.857019+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16570","citing_title":"A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45","json":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45.json","graph_json":"https://pith.science/api/pith-number/F6EASRTBLW7PF5UQW64MKNXW45/graph.json","events_json":"https://pith.science/api/pith-number/F6EASRTBLW7PF5UQW64MKNXW45/events.json","paper":"https://pith.science/paper/F6EASRTB"},"agent_actions":{"view_html":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45","download_json":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45.json","view_paper":"https://pith.science/paper/F6EASRTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04829&json=true","fetch_graph":"https://pith.science/api/pith-number/F6EASRTBLW7PF5UQW64MKNXW45/graph.json","fetch_events":"https://pith.science/api/pith-number/F6EASRTBLW7PF5UQW64MKNXW45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45/action/storage_attestation","attest_author":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45/action/author_attestation","sign_citation":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45/action/citation_signature","submit_replication":"https://pith.science/pith/F6EASRTBLW7PF5UQW64MKNXW45/action/replication_record"}},"created_at":"2026-07-05T03:34:18.857019+00:00","updated_at":"2026-07-05T03:34:18.857019+00:00"}