{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TQGTHGPETTPOW7AGJ25TOY5J2T","short_pith_number":"pith:TQGTHGPE","canonical_record":{"source":{"id":"1905.13320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T21:30:29Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"48cc4b6ef798e6417b1746df296da19d9866df3c0ebb2c1a4337339090ae9274","abstract_canon_sha256":"3c55ddc0c422efabf41c6644df036c052fa7ada4234118d5ddef62c9636f13a7"},"schema_version":"1.0"},"canonical_sha256":"9c0d3399e49cdeeb7c064ebb3763a9d4d93b3929484f083603065b03cd98c640","source":{"kind":"arxiv","id":"1905.13320","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13320","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13320v1","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13320","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"TQGTHGPETTPO","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TQGTHGPETTPOW7AG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TQGTHGPE","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TQGTHGPETTPOW7AGJ25TOY5J2T","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13320","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T21:30:29Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"48cc4b6ef798e6417b1746df296da19d9866df3c0ebb2c1a4337339090ae9274","abstract_canon_sha256":"3c55ddc0c422efabf41c6644df036c052fa7ada4234118d5ddef62c9636f13a7"},"schema_version":"1.0"},"canonical_sha256":"9c0d3399e49cdeeb7c064ebb3763a9d4d93b3929484f083603065b03cd98c640","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.312564Z","signature_b64":"eQlF6cTDS1/yHoR8D+Fpw6zx+aa6ZWAZ9AoOddk7Ygv9ZdWKnSXNj1ypIy61s/HNAPDsxLG896+7YiTjbP+GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c0d3399e49cdeeb7c064ebb3763a9d4d93b3929484f083603065b03cd98c640","last_reissued_at":"2026-05-17T23:44:35.312101Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.312101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13320","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":"2026-05-17T23:44:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WXToxqoyjzFbuf87B7tpvYOeRbTY+5xwJh4XiuKidbZ+3WhCtifkw3YLRzn2rWhZjVfoNwrdMW1F+OG5jtVvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:27:20.092092Z"},"content_sha256":"43eae175cd2e170c52f0bcad729d0d6bdcb8828941307430d5cca2df2d265abf","schema_version":"1.0","event_id":"sha256:43eae175cd2e170c52f0bcad729d0d6bdcb8828941307430d5cca2df2d265abf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TQGTHGPETTPOW7AGJ25TOY5J2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combating the Compounding-Error Problem with a Multi-step Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dipendra Misra, Kavosh Asadi, Michel L. Littman, Seungchan Kim","submitted_at":"2019-05-30T21:30:29Z","abstract_excerpt":"Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and outputs the next state---a one-step model. This model can be composed with itself to enable predicting multiple steps into the future, but one-step prediction errors can get magnified, leading to unacceptable inaccuracy. This compounding-error problem plagues planning and undermines model-based reinforcement learning. In this paper, we address the compoundi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13320","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":"2026-05-17T23:44:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/9FXhl9jLoykcvrr5LolKyKnwXK70+qVMkogv+km57/hTiGLkuZpP2++DpovIygebRCEBvatNyncuXPGCDCVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:27:20.092906Z"},"content_sha256":"52fb4bb91e7bfa6102fe089bec1e2ee548d01df3b6282009ce31ef15c23c8b85","schema_version":"1.0","event_id":"sha256:52fb4bb91e7bfa6102fe089bec1e2ee548d01df3b6282009ce31ef15c23c8b85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQGTHGPETTPOW7AGJ25TOY5J2T/bundle.json","state_url":"https://pith.science/pith/TQGTHGPETTPOW7AGJ25TOY5J2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQGTHGPETTPOW7AGJ25TOY5J2T/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":"2026-06-09T09:27:20Z","links":{"resolver":"https://pith.science/pith/TQGTHGPETTPOW7AGJ25TOY5J2T","bundle":"https://pith.science/pith/TQGTHGPETTPOW7AGJ25TOY5J2T/bundle.json","state":"https://pith.science/pith/TQGTHGPETTPOW7AGJ25TOY5J2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQGTHGPETTPOW7AGJ25TOY5J2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TQGTHGPETTPOW7AGJ25TOY5J2T","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":"3c55ddc0c422efabf41c6644df036c052fa7ada4234118d5ddef62c9636f13a7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T21:30:29Z","title_canon_sha256":"48cc4b6ef798e6417b1746df296da19d9866df3c0ebb2c1a4337339090ae9274"},"schema_version":"1.0","source":{"id":"1905.13320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13320","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13320v1","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13320","created_at":"2026-05-17T23:44:35Z"},{"alias_kind":"pith_short_12","alias_value":"TQGTHGPETTPO","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TQGTHGPETTPOW7AG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TQGTHGPE","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:52fb4bb91e7bfa6102fe089bec1e2ee548d01df3b6282009ce31ef15c23c8b85","target":"graph","created_at":"2026-05-17T23:44:35Z","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":"Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and outputs the next state---a one-step model. This model can be composed with itself to enable predicting multiple steps into the future, but one-step prediction errors can get magnified, leading to unacceptable inaccuracy. This compounding-error problem plagues planning and undermines model-based reinforcement learning. In this paper, we address the compoundi","authors_text":"Dipendra Misra, Kavosh Asadi, Michel L. Littman, Seungchan Kim","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T21:30:29Z","title":"Combating the Compounding-Error Problem with a Multi-step Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13320","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":"sha256:43eae175cd2e170c52f0bcad729d0d6bdcb8828941307430d5cca2df2d265abf","target":"record","created_at":"2026-05-17T23:44:35Z","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":"3c55ddc0c422efabf41c6644df036c052fa7ada4234118d5ddef62c9636f13a7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T21:30:29Z","title_canon_sha256":"48cc4b6ef798e6417b1746df296da19d9866df3c0ebb2c1a4337339090ae9274"},"schema_version":"1.0","source":{"id":"1905.13320","kind":"arxiv","version":1}},"canonical_sha256":"9c0d3399e49cdeeb7c064ebb3763a9d4d93b3929484f083603065b03cd98c640","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c0d3399e49cdeeb7c064ebb3763a9d4d93b3929484f083603065b03cd98c640","first_computed_at":"2026-05-17T23:44:35.312101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:35.312101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eQlF6cTDS1/yHoR8D+Fpw6zx+aa6ZWAZ9AoOddk7Ygv9ZdWKnSXNj1ypIy61s/HNAPDsxLG896+7YiTjbP+GDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:35.312564Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43eae175cd2e170c52f0bcad729d0d6bdcb8828941307430d5cca2df2d265abf","sha256:52fb4bb91e7bfa6102fe089bec1e2ee548d01df3b6282009ce31ef15c23c8b85"],"state_sha256":"7b73fe18bc77e6467e0f3edfd61cd47909daae772a32f86bf7db60e450532754"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3HL564xI2FtUxC4HmQ2itQr+yVIhWavqAsQc6vg9CawrMCW4VIC6I4+O9xsUXVG/OCW+PfLVbbSVapDlm+LCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:27:20.097505Z","bundle_sha256":"0754a4633dede5bedc4b6881f4abad08d095fc3a8297b7e0b53654f6a8219583"}}