{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TG2COKTM4V75C2FW7MBKXHDDKD","short_pith_number":"pith:TG2COKTM","canonical_record":{"source":{"id":"1901.02705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T00:39:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"819e001d7632aa02774606d5da51c8b125fbacc82fa7ac3f33c92023664c1543","abstract_canon_sha256":"bd4c4c7e5594e3c727eb157d4d01eb94885c189ba3185e0dfeeeea867a4e83e8"},"schema_version":"1.0"},"canonical_sha256":"99b4272a6ce57fd168b6fb02ab9c6350d2059f83280a90cbb26ed12e71e96c9f","source":{"kind":"arxiv","id":"1901.02705","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02705","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02705v1","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02705","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"TG2COKTM4V75","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"TG2COKTM4V75C2FW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"TG2COKTM","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TG2COKTM4V75C2FW7MBKXHDDKD","target":"record","payload":{"canonical_record":{"source":{"id":"1901.02705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T00:39:21Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"819e001d7632aa02774606d5da51c8b125fbacc82fa7ac3f33c92023664c1543","abstract_canon_sha256":"bd4c4c7e5594e3c727eb157d4d01eb94885c189ba3185e0dfeeeea867a4e83e8"},"schema_version":"1.0"},"canonical_sha256":"99b4272a6ce57fd168b6fb02ab9c6350d2059f83280a90cbb26ed12e71e96c9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:39.740469Z","signature_b64":"XpvP/ot1Xjs8Krk3DUAsUPL89ZVf+JePgET2CtPMwVVW43VBEh54d/nEKCwR5pCUru/C4uCYyD9yuC116ajxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99b4272a6ce57fd168b6fb02ab9c6350d2059f83280a90cbb26ed12e71e96c9f","last_reissued_at":"2026-05-17T23:56:39.739748Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:39.739748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.02705","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6P7kabmqN7Cwm/etQeDpVcliPDH19B33sMF8fMxmYfee3WZQI4NRgu71rkbu6zy0jm/VNrOEBTp8yR5fd/vhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:10:58.423711Z"},"content_sha256":"8ef8f869735f6a4eb5720a83c3ecd57f160a42a86eec927654be0a7d8fa21413","schema_version":"1.0","event_id":"sha256:8ef8f869735f6a4eb5720a83c3ecd57f160a42a86eec927654be0a7d8fa21413"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TG2COKTM4V75C2FW7MBKXHDDKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alfredo Canziani, Mikael Henaff, Yann LeCun","submitted_at":"2019-01-08T00:39:21Z","abstract_excerpt":"Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the environment dynamics over multiple time steps while explicitly penalizing two costs: the original cost the policy seeks to optimize, and an uncertainty cost which represents its divergence from the states it is trained on. We measure this second cost by using the uncertainty of the dynamics model about its own predictions, using recent ideas from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02705","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxmOHOa+JxJ2W4PtHfqQuukmFlXR2NnJBO9spHcU0PDEfLaOmHq+7A/CjN5dY7sCjx3lswJed641CbiSEABdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:10:58.424076Z"},"content_sha256":"b12b0fcd4952d38414b55b5909da91695e742b7ca3a83df9da347a6b5468dbdc","schema_version":"1.0","event_id":"sha256:b12b0fcd4952d38414b55b5909da91695e742b7ca3a83df9da347a6b5468dbdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TG2COKTM4V75C2FW7MBKXHDDKD/bundle.json","state_url":"https://pith.science/pith/TG2COKTM4V75C2FW7MBKXHDDKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TG2COKTM4V75C2FW7MBKXHDDKD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T08:10:58Z","links":{"resolver":"https://pith.science/pith/TG2COKTM4V75C2FW7MBKXHDDKD","bundle":"https://pith.science/pith/TG2COKTM4V75C2FW7MBKXHDDKD/bundle.json","state":"https://pith.science/pith/TG2COKTM4V75C2FW7MBKXHDDKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TG2COKTM4V75C2FW7MBKXHDDKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TG2COKTM4V75C2FW7MBKXHDDKD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bd4c4c7e5594e3c727eb157d4d01eb94885c189ba3185e0dfeeeea867a4e83e8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T00:39:21Z","title_canon_sha256":"819e001d7632aa02774606d5da51c8b125fbacc82fa7ac3f33c92023664c1543"},"schema_version":"1.0","source":{"id":"1901.02705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.02705","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"arxiv_version","alias_value":"1901.02705v1","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.02705","created_at":"2026-05-17T23:56:39Z"},{"alias_kind":"pith_short_12","alias_value":"TG2COKTM4V75","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"TG2COKTM4V75C2FW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"TG2COKTM","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:b12b0fcd4952d38414b55b5909da91695e742b7ca3a83df9da347a6b5468dbdc","target":"graph","created_at":"2026-05-17T23:56:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the environment dynamics over multiple time steps while explicitly penalizing two costs: the original cost the policy seeks to optimize, and an uncertainty cost which represents its divergence from the states it is trained on. We measure this second cost by using the uncertainty of the dynamics model about its own predictions, using recent ideas from ","authors_text":"Alfredo Canziani, Mikael Henaff, Yann LeCun","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T00:39:21Z","title":"Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.02705","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8ef8f869735f6a4eb5720a83c3ecd57f160a42a86eec927654be0a7d8fa21413","target":"record","created_at":"2026-05-17T23:56:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bd4c4c7e5594e3c727eb157d4d01eb94885c189ba3185e0dfeeeea867a4e83e8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-08T00:39:21Z","title_canon_sha256":"819e001d7632aa02774606d5da51c8b125fbacc82fa7ac3f33c92023664c1543"},"schema_version":"1.0","source":{"id":"1901.02705","kind":"arxiv","version":1}},"canonical_sha256":"99b4272a6ce57fd168b6fb02ab9c6350d2059f83280a90cbb26ed12e71e96c9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99b4272a6ce57fd168b6fb02ab9c6350d2059f83280a90cbb26ed12e71e96c9f","first_computed_at":"2026-05-17T23:56:39.739748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:39.739748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XpvP/ot1Xjs8Krk3DUAsUPL89ZVf+JePgET2CtPMwVVW43VBEh54d/nEKCwR5pCUru/C4uCYyD9yuC116ajxAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:39.740469Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.02705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ef8f869735f6a4eb5720a83c3ecd57f160a42a86eec927654be0a7d8fa21413","sha256:b12b0fcd4952d38414b55b5909da91695e742b7ca3a83df9da347a6b5468dbdc"],"state_sha256":"12eada7d7f7b6c875519fd11e7b5e8999a8297e30d4c519ce9c24e3562bae605"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WrILzFlVpY/zP/YKKmeINs2CeMvgXDAkRAIUTuFXyTzCZzAej9gzw0QfY1U1HOJkJ7wOnICugeSQZHSCd7nuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:10:58.426060Z","bundle_sha256":"55cbea592382bb5370e243572f5fd226f550f85f33cdbc968be027500d1e73da"}}