{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NAQBB7OTABOL5TEJXXMCELGGHP","short_pith_number":"pith:NAQBB7OT","canonical_record":{"source":{"id":"1902.01240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T15:12:55Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"e379ea181ebeb6870efcce314605fc4110bc33ff04969dcb0650350674336b84","abstract_canon_sha256":"73f1222f92d991b94c7fa57f1eb73b5d9422af25b2d6b3ca1c64f84e58d26914"},"schema_version":"1.0"},"canonical_sha256":"682010fdd3005cbecc89bdd8222cc63bd1a1e3f890dfc6340ea6bebb476dc168","source":{"kind":"arxiv","id":"1902.01240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01240","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01240v1","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01240","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"NAQBB7OTABOL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NAQBB7OTABOL5TEJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NAQBB7OT","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NAQBB7OTABOL5TEJXXMCELGGHP","target":"record","payload":{"canonical_record":{"source":{"id":"1902.01240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T15:12:55Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"e379ea181ebeb6870efcce314605fc4110bc33ff04969dcb0650350674336b84","abstract_canon_sha256":"73f1222f92d991b94c7fa57f1eb73b5d9422af25b2d6b3ca1c64f84e58d26914"},"schema_version":"1.0"},"canonical_sha256":"682010fdd3005cbecc89bdd8222cc63bd1a1e3f890dfc6340ea6bebb476dc168","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:47.771616Z","signature_b64":"1u9rDnFCGEzYwa+3xtY6cMT4O1yLbyuCunw2qCvvb5wROK1dncQewE2DNqsOoULyWbXEX7j8N+GefVioDHTaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"682010fdd3005cbecc89bdd8222cc63bd1a1e3f890dfc6340ea6bebb476dc168","last_reissued_at":"2026-05-17T23:54:47.771047Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:47.771047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.01240","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":"2026-05-17T23:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dg7k8vWfG4ESHkGUiRdcNrgnQKBGE7ZUtF0fMv/bVOGEJvA091EkwhSIpi01LU5LrfpoHWvcPez+6U6F32k5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:13:28.908834Z"},"content_sha256":"fd4f0ec876bf7d38e48f4046f9ef90530800367724f92d45ed9af58d346f2a4b","schema_version":"1.0","event_id":"sha256:fd4f0ec876bf7d38e48f4046f9ef90530800367724f92d45ed9af58d346f2a4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NAQBB7OTABOL5TEJXXMCELGGHP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carl Edward Rasmussen, Jan Peters, Kenji Doya, Paavo Parmas","submitted_at":"2019-02-04T15:12:55Z","abstract_excerpt":"Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization. Our experiments in model-based reinforcement learning imply that the problem is not just a numerical issue, but it may be caused by a fundamental chaos-like nature of long chains of nonlinear computations. Not only do the magnitudes of the gradients become large, the direction of the gradients becomes essentially random. We show that reparameterization gradients suffer from the problem, while lik"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01240","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":"2026-05-17T23:54:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aLTDDgVgmez1iLunVGlFw/rFRGvX9DtFapqGzJsQHc10pawUKd7QBwjlGa4JfDIiePx1KbmtS0vIPBxzboiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:13:28.909192Z"},"content_sha256":"567624d14c23f8ec27cbdbf502aaebea7f90016aa9a301c835d0e86bb475715c","schema_version":"1.0","event_id":"sha256:567624d14c23f8ec27cbdbf502aaebea7f90016aa9a301c835d0e86bb475715c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NAQBB7OTABOL5TEJXXMCELGGHP/bundle.json","state_url":"https://pith.science/pith/NAQBB7OTABOL5TEJXXMCELGGHP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NAQBB7OTABOL5TEJXXMCELGGHP/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":"2026-06-02T02:13:28Z","links":{"resolver":"https://pith.science/pith/NAQBB7OTABOL5TEJXXMCELGGHP","bundle":"https://pith.science/pith/NAQBB7OTABOL5TEJXXMCELGGHP/bundle.json","state":"https://pith.science/pith/NAQBB7OTABOL5TEJXXMCELGGHP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NAQBB7OTABOL5TEJXXMCELGGHP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NAQBB7OTABOL5TEJXXMCELGGHP","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":"73f1222f92d991b94c7fa57f1eb73b5d9422af25b2d6b3ca1c64f84e58d26914","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T15:12:55Z","title_canon_sha256":"e379ea181ebeb6870efcce314605fc4110bc33ff04969dcb0650350674336b84"},"schema_version":"1.0","source":{"id":"1902.01240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01240","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01240v1","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01240","created_at":"2026-05-17T23:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"NAQBB7OTABOL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NAQBB7OTABOL5TEJ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NAQBB7OT","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:567624d14c23f8ec27cbdbf502aaebea7f90016aa9a301c835d0e86bb475715c","target":"graph","created_at":"2026-05-17T23:54:47Z","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":"Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization. Our experiments in model-based reinforcement learning imply that the problem is not just a numerical issue, but it may be caused by a fundamental chaos-like nature of long chains of nonlinear computations. Not only do the magnitudes of the gradients become large, the direction of the gradients becomes essentially random. We show that reparameterization gradients suffer from the problem, while lik","authors_text":"Carl Edward Rasmussen, Jan Peters, Kenji Doya, Paavo Parmas","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T15:12:55Z","title":"PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01240","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:fd4f0ec876bf7d38e48f4046f9ef90530800367724f92d45ed9af58d346f2a4b","target":"record","created_at":"2026-05-17T23:54:47Z","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":"73f1222f92d991b94c7fa57f1eb73b5d9422af25b2d6b3ca1c64f84e58d26914","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-04T15:12:55Z","title_canon_sha256":"e379ea181ebeb6870efcce314605fc4110bc33ff04969dcb0650350674336b84"},"schema_version":"1.0","source":{"id":"1902.01240","kind":"arxiv","version":1}},"canonical_sha256":"682010fdd3005cbecc89bdd8222cc63bd1a1e3f890dfc6340ea6bebb476dc168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"682010fdd3005cbecc89bdd8222cc63bd1a1e3f890dfc6340ea6bebb476dc168","first_computed_at":"2026-05-17T23:54:47.771047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:47.771047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1u9rDnFCGEzYwa+3xtY6cMT4O1yLbyuCunw2qCvvb5wROK1dncQewE2DNqsOoULyWbXEX7j8N+GefVioDHTaDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:47.771616Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.01240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd4f0ec876bf7d38e48f4046f9ef90530800367724f92d45ed9af58d346f2a4b","sha256:567624d14c23f8ec27cbdbf502aaebea7f90016aa9a301c835d0e86bb475715c"],"state_sha256":"6f8fa2019308d8b6316c68103dbee027ff3f07e9bb0e865a04577cc41cfebbd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"94mm39Awb88TqXy4h3A5wjwz9uzaBAAUoL9dfi60e8+7sr09g4ju7Is4eGTV7/jN+jtHzAW+ow5Dxzpm7yxRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T02:13:28.911253Z","bundle_sha256":"8ffb0c1d768f0e8dacc3ff824a2d62aaa0fb6e9f951abec9ec42579a522fbd5e"}}