{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BSDB3ASJ257Q5NBNHRAAE7FTPX","short_pith_number":"pith:BSDB3ASJ","schema_version":"1.0","canonical_sha256":"0c861d8249d77f0eb42d3c40027cb37dc63b1f32a798e0a58f2dc03096d8ad1c","source":{"kind":"arxiv","id":"2003.11919","version":3},"attestation_state":"computed","paper":{"title":"Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alois Knoll, Patrick Hart","submitted_at":"2020-03-20T10:02:30Z","abstract_excerpt":"Learning-based approaches, such as reinforcement and imitation learning are gaining popularity in decision-making for autonomous driving. However, learned policies often fail to generalize and cannot handle novel situations well. Asking and answering questions in the form of \"Would a policy perform well if the other agents had behaved differently?\" can shed light on whether a policy has seen similar situations during training and generalizes well. In this work, a counterfactual policy evaluation is introduced that makes use of counterfactual worlds - worlds in which the behaviors of others are"},"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":"2003.11919","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-20T10:02:30Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"2181bc9fdc6db4a4f11bc3fb6855898dfc31eb18674c32705c45467089c8eb94","abstract_canon_sha256":"e5fc0304df9b5e3190def026145b42a2f79fd2df82ed031e938270168906bc24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:06.488496Z","signature_b64":"pLg4ZlIf0Xt2vwIhMYkUyBVReoBAWbxUIurIaOzd7aJ84XEmRQ0sRem2uo6M4V7YyzTKQ/eOTDnMndGmbZFzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c861d8249d77f0eb42d3c40027cb37dc63b1f32a798e0a58f2dc03096d8ad1c","last_reissued_at":"2026-07-05T01:51:06.487845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:06.487845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alois Knoll, Patrick Hart","submitted_at":"2020-03-20T10:02:30Z","abstract_excerpt":"Learning-based approaches, such as reinforcement and imitation learning are gaining popularity in decision-making for autonomous driving. However, learned policies often fail to generalize and cannot handle novel situations well. Asking and answering questions in the form of \"Would a policy perform well if the other agents had behaved differently?\" can shed light on whether a policy has seen similar situations during training and generalizes well. In this work, a counterfactual policy evaluation is introduced that makes use of counterfactual worlds - worlds in which the behaviors of others are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11919","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/2003.11919/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":"2003.11919","created_at":"2026-07-05T01:51:06.487897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11919v3","created_at":"2026-07-05T01:51:06.487897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11919","created_at":"2026-07-05T01:51:06.487897+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSDB3ASJ257Q","created_at":"2026-07-05T01:51:06.487897+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSDB3ASJ257Q5NBN","created_at":"2026-07-05T01:51:06.487897+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSDB3ASJ","created_at":"2026-07-05T01:51:06.487897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10744","citing_title":"C-CoT: Counterfactual Chain-of-Thought with Vision-Language Models for Safe Autonomous Driving","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX","json":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX.json","graph_json":"https://pith.science/api/pith-number/BSDB3ASJ257Q5NBNHRAAE7FTPX/graph.json","events_json":"https://pith.science/api/pith-number/BSDB3ASJ257Q5NBNHRAAE7FTPX/events.json","paper":"https://pith.science/paper/BSDB3ASJ"},"agent_actions":{"view_html":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX","download_json":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX.json","view_paper":"https://pith.science/paper/BSDB3ASJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11919&json=true","fetch_graph":"https://pith.science/api/pith-number/BSDB3ASJ257Q5NBNHRAAE7FTPX/graph.json","fetch_events":"https://pith.science/api/pith-number/BSDB3ASJ257Q5NBNHRAAE7FTPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX/action/storage_attestation","attest_author":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX/action/author_attestation","sign_citation":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX/action/citation_signature","submit_replication":"https://pith.science/pith/BSDB3ASJ257Q5NBNHRAAE7FTPX/action/replication_record"}},"created_at":"2026-07-05T01:51:06.487897+00:00","updated_at":"2026-07-05T01:51:06.487897+00:00"}