{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RQZMGAAEAOUIFAHDD6ZI2HT5GT","short_pith_number":"pith:RQZMGAAE","schema_version":"1.0","canonical_sha256":"8c32c3000403a88280e31fb28d1e7d34ee56b4ee5c1e025bef39924cffea2fc6","source":{"kind":"arxiv","id":"2112.03908","version":1},"attestation_state":"computed","paper":{"title":"Causal Imitative Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Alexandre Alahi, Mohammadhossein Bahari, Mohammad Reza Samsami, Saber Salehkaleybar","submitted_at":"2021-12-07T18:59:15Z","abstract_excerpt":"Imitation learning is a powerful approach for learning autonomous driving policy by leveraging data from expert driver demonstrations. However, driving policies trained via imitation learning that neglect the causal structure of expert demonstrations yield two undesirable behaviors: inertia and collision. In this paper, we propose Causal Imitative Model (CIM) to address inertia and collision problems. CIM explicitly discovers the causal model and utilizes it to train the policy. Specifically, CIM disentangles the input to a set of latent variables, selects the causal variables, and determines "},"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":"2112.03908","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-12-07T18:59:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6d8eebc2e0cd433cebf205fa51a243769bc9f03558a148b8f7312b4f40b6cac0","abstract_canon_sha256":"05e25a558a8b7ed54b2827939f3103f845c5c5372bb3295f2de64565145c0d0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:51.054110Z","signature_b64":"NSVrELjytdsEasVIoEGXrerjBt79nuNYTxBaFBDJ3muFGK1OhnnnWVHhrjGhPtWqEJa9/PgqHTwBBQ3AWK5LBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c32c3000403a88280e31fb28d1e7d34ee56b4ee5c1e025bef39924cffea2fc6","last_reissued_at":"2026-07-05T03:38:51.053675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:51.053675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Imitative Model for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Alexandre Alahi, Mohammadhossein Bahari, Mohammad Reza Samsami, Saber Salehkaleybar","submitted_at":"2021-12-07T18:59:15Z","abstract_excerpt":"Imitation learning is a powerful approach for learning autonomous driving policy by leveraging data from expert driver demonstrations. However, driving policies trained via imitation learning that neglect the causal structure of expert demonstrations yield two undesirable behaviors: inertia and collision. In this paper, we propose Causal Imitative Model (CIM) to address inertia and collision problems. CIM explicitly discovers the causal model and utilizes it to train the policy. Specifically, CIM disentangles the input to a set of latent variables, selects the causal variables, and determines "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03908","kind":"arxiv","version":1},"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/2112.03908/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":"2112.03908","created_at":"2026-07-05T03:38:51.053734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03908v1","created_at":"2026-07-05T03:38:51.053734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03908","created_at":"2026-07-05T03:38:51.053734+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQZMGAAEAOUI","created_at":"2026-07-05T03:38:51.053734+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQZMGAAEAOUIFAHD","created_at":"2026-07-05T03:38:51.053734+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQZMGAAE","created_at":"2026-07-05T03:38:51.053734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.07191","citing_title":"Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT","json":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT.json","graph_json":"https://pith.science/api/pith-number/RQZMGAAEAOUIFAHDD6ZI2HT5GT/graph.json","events_json":"https://pith.science/api/pith-number/RQZMGAAEAOUIFAHDD6ZI2HT5GT/events.json","paper":"https://pith.science/paper/RQZMGAAE"},"agent_actions":{"view_html":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT","download_json":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT.json","view_paper":"https://pith.science/paper/RQZMGAAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03908&json=true","fetch_graph":"https://pith.science/api/pith-number/RQZMGAAEAOUIFAHDD6ZI2HT5GT/graph.json","fetch_events":"https://pith.science/api/pith-number/RQZMGAAEAOUIFAHDD6ZI2HT5GT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT/action/storage_attestation","attest_author":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT/action/author_attestation","sign_citation":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT/action/citation_signature","submit_replication":"https://pith.science/pith/RQZMGAAEAOUIFAHDD6ZI2HT5GT/action/replication_record"}},"created_at":"2026-07-05T03:38:51.053734+00:00","updated_at":"2026-07-05T03:38:51.053734+00:00"}