{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:AVGVY7LVKVJFNZHLJ7XTXCWDMN","short_pith_number":"pith:AVGVY7LV","canonical_record":{"source":{"id":"1612.06018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-19T01:09:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c2b55d6cedd492c6236c828e257fdea2911247a60882c1f96f510037c251b14","abstract_canon_sha256":"fa2043554b86361086c9ad45ad5b4d5f7e5e1c0b0e514e478f12880af45e2f31"},"schema_version":"1.0"},"canonical_sha256":"054d5c7d75555256e4eb4fef3b8ac36341e5e07073b4482cfa34ba5ece46d3de","source":{"kind":"arxiv","id":"1612.06018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.06018","created_at":"2026-05-18T00:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1612.06018v2","created_at":"2026-05-18T00:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06018","created_at":"2026-05-18T00:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"AVGVY7LVKVJF","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"AVGVY7LVKVJFNZHL","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"AVGVY7LV","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:AVGVY7LVKVJFNZHLJ7XTXCWDMN","target":"record","payload":{"canonical_record":{"source":{"id":"1612.06018","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-19T01:09:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4c2b55d6cedd492c6236c828e257fdea2911247a60882c1f96f510037c251b14","abstract_canon_sha256":"fa2043554b86361086c9ad45ad5b4d5f7e5e1c0b0e514e478f12880af45e2f31"},"schema_version":"1.0"},"canonical_sha256":"054d5c7d75555256e4eb4fef3b8ac36341e5e07073b4482cfa34ba5ece46d3de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:23.776735Z","signature_b64":"XMrCINKJKIhZ6YWDgNgKanR1hSGtDSENx5MhV6h1ALEtwO4LR+WU4BEXGfMkHFVkhgMsVH9rK10j4TaIsLImDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"054d5c7d75555256e4eb4fef3b8ac36341e5e07073b4482cfa34ba5ece46d3de","last_reissued_at":"2026-05-18T00:39:23.776127Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:23.776127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.06018","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFawV0Bho1X+2CRWxMkehV2/Ao4Rw7aSYAgIqWuEQpE261L+BWzyh0qNoIU61A7oNASx0anxc3XTgIQhhoGBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:54:33.415943Z"},"content_sha256":"9fb1b43f61aac0e34b4d0f9adcb59af30a5b7e4cb1e370dc6562b1f43363dddc","schema_version":"1.0","event_id":"sha256:9fb1b43f61aac0e34b4d0f9adcb59af30a5b7e4cb1e370dc6562b1f43363dddc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:AVGVY7LVKVJFNZHLJ7XTXCWDMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Correcting Models for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Erik Talvitie","submitted_at":"2016-12-19T01:09:23Z","abstract_excerpt":"When an agent cannot represent a perfectly accurate model of its environment's dynamics, model-based reinforcement learning (MBRL) can fail catastrophically. Planning involves composing the predictions of the model; when flawed predictions are composed, even minor errors can compound and render the model useless for planning. Hallucinated Replay (Talvitie 2014) trains the model to \"correct\" itself when it produces errors, substantially improving MBRL with flawed models. This paper theoretically analyzes this approach, illuminates settings in which it is likely to be effective or ineffective, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06018","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":""},"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":"2026-05-18T00:39:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBoi7q4tujS2wgM28NqQAXy4VXidYFjzG/Xv7phbBD8/4CXOBiAXLhkJnSUlHRAZwn6Hj+5O1I/8PASu4L4nBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:54:33.416572Z"},"content_sha256":"fdc426fe4ac49c02c75b45ea677895ff955dc42a375a48abf133749c6767338e","schema_version":"1.0","event_id":"sha256:fdc426fe4ac49c02c75b45ea677895ff955dc42a375a48abf133749c6767338e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN/bundle.json","state_url":"https://pith.science/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN/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":"2026-07-07T04:54:33Z","links":{"resolver":"https://pith.science/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN","bundle":"https://pith.science/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN/bundle.json","state":"https://pith.science/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AVGVY7LVKVJFNZHLJ7XTXCWDMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:AVGVY7LVKVJFNZHLJ7XTXCWDMN","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":"fa2043554b86361086c9ad45ad5b4d5f7e5e1c0b0e514e478f12880af45e2f31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-19T01:09:23Z","title_canon_sha256":"4c2b55d6cedd492c6236c828e257fdea2911247a60882c1f96f510037c251b14"},"schema_version":"1.0","source":{"id":"1612.06018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.06018","created_at":"2026-05-18T00:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"1612.06018v2","created_at":"2026-05-18T00:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06018","created_at":"2026-05-18T00:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"AVGVY7LVKVJF","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"AVGVY7LVKVJFNZHL","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"AVGVY7LV","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:fdc426fe4ac49c02c75b45ea677895ff955dc42a375a48abf133749c6767338e","target":"graph","created_at":"2026-05-18T00:39:23Z","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":"When an agent cannot represent a perfectly accurate model of its environment's dynamics, model-based reinforcement learning (MBRL) can fail catastrophically. Planning involves composing the predictions of the model; when flawed predictions are composed, even minor errors can compound and render the model useless for planning. Hallucinated Replay (Talvitie 2014) trains the model to \"correct\" itself when it produces errors, substantially improving MBRL with flawed models. This paper theoretically analyzes this approach, illuminates settings in which it is likely to be effective or ineffective, a","authors_text":"Erik Talvitie","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-19T01:09:23Z","title":"Self-Correcting Models for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06018","kind":"arxiv","version":2},"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":"sha256:9fb1b43f61aac0e34b4d0f9adcb59af30a5b7e4cb1e370dc6562b1f43363dddc","target":"record","created_at":"2026-05-18T00:39:23Z","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":"fa2043554b86361086c9ad45ad5b4d5f7e5e1c0b0e514e478f12880af45e2f31","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-19T01:09:23Z","title_canon_sha256":"4c2b55d6cedd492c6236c828e257fdea2911247a60882c1f96f510037c251b14"},"schema_version":"1.0","source":{"id":"1612.06018","kind":"arxiv","version":2}},"canonical_sha256":"054d5c7d75555256e4eb4fef3b8ac36341e5e07073b4482cfa34ba5ece46d3de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"054d5c7d75555256e4eb4fef3b8ac36341e5e07073b4482cfa34ba5ece46d3de","first_computed_at":"2026-05-18T00:39:23.776127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:23.776127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XMrCINKJKIhZ6YWDgNgKanR1hSGtDSENx5MhV6h1ALEtwO4LR+WU4BEXGfMkHFVkhgMsVH9rK10j4TaIsLImDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:23.776735Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.06018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fb1b43f61aac0e34b4d0f9adcb59af30a5b7e4cb1e370dc6562b1f43363dddc","sha256:fdc426fe4ac49c02c75b45ea677895ff955dc42a375a48abf133749c6767338e"],"state_sha256":"ed0f292f9f5bd3581ea3ae555fc29b40c8c5022d4a40248317fdeab29dc18148"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7tNnFUWsrI/mucjuLTe2xoYPK1ZKqE90zirkh0DsK9CsJCqGUCSIM+xphJ/DkHEpGj7dDpnk7L/SgbqgQAVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:54:33.419671Z","bundle_sha256":"dbede51dca4bedc0af3fe6f9bd1dfa5688624a9f1492e14335154a1e817617ac"}}