{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:5CMLYQDZCWE4KRXTTF3OSKTLCN","short_pith_number":"pith:5CMLYQDZ","canonical_record":{"source":{"id":"1301.2343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T21:54:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff487f7a5c36fa92bb1494e6f0c33996af262dfcfa40ef4595538cfa26d9351f","abstract_canon_sha256":"11378e2b8615b107b6108658c8b3d70761c420c4cb0e62aa331f5d9b8ff49f05"},"schema_version":"1.0"},"canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","source":{"kind":"arxiv","id":"1301.2343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.2343","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"1301.2343v1","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.2343","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"5CMLYQDZCWE4","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"5CMLYQDZCWE4KRXT","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"5CMLYQDZ","created_at":"2026-05-18T12:27:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:5CMLYQDZCWE4KRXTTF3OSKTLCN","target":"record","payload":{"canonical_record":{"source":{"id":"1301.2343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T21:54:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ff487f7a5c36fa92bb1494e6f0c33996af262dfcfa40ef4595538cfa26d9351f","abstract_canon_sha256":"11378e2b8615b107b6108658c8b3d70761c420c4cb0e62aa331f5d9b8ff49f05"},"schema_version":"1.0"},"canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:45.273695Z","signature_b64":"wS+WV1ysH091uStRfa7Kx0ay+p2ApOgsRxnTtylEf0q4WxjlOhPaLzw9Qr8/d5117CVVdY0J1BzH+Fpq8ijQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","last_reissued_at":"2026-05-18T03:36:45.273055Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:45.273055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.2343","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":"2026-05-18T03:36:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQ6XzmnJ4dTOjX/i2nX+s1kfoH718EjGuuZE0YJQ9Br8OQZ2tvY1TVnF8J8fitzVKWD+qAP4iZosI+5J0cQtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:53:39.111068Z"},"content_sha256":"cc2efc84795739a298987b5ca60b7feffba0b546f65df343b3114eb02124312b","schema_version":"1.0","event_id":"sha256:cc2efc84795739a298987b5ca60b7feffba0b546f65df343b3114eb02124312b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:5CMLYQDZCWE4KRXTTF3OSKTLCN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning by Prioritized Sweeping with Small Backups","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Harm van Seijen, Richard S. Sutton","submitted_at":"2013-01-10T21:54:42Z","abstract_excerpt":"Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.2343","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":"2026-05-18T03:36:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"le+klzYv9cgUpf9AsWro7b8MrcYuXV1nfOkyMZwx/CySXlpc02NdXsOOwPQI2dkm1iVDwtbRq6mCqdztotZvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:53:39.111719Z"},"content_sha256":"6344c6b7a9da854125e845b287ed415297b9b366f079626601666d55e0f3a8f5","schema_version":"1.0","event_id":"sha256:6344c6b7a9da854125e845b287ed415297b9b366f079626601666d55e0f3a8f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/bundle.json","state_url":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/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":"2026-05-31T16:53:39Z","links":{"resolver":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN","bundle":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/bundle.json","state":"https://pith.science/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5CMLYQDZCWE4KRXTTF3OSKTLCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:5CMLYQDZCWE4KRXTTF3OSKTLCN","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":"11378e2b8615b107b6108658c8b3d70761c420c4cb0e62aa331f5d9b8ff49f05","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T21:54:42Z","title_canon_sha256":"ff487f7a5c36fa92bb1494e6f0c33996af262dfcfa40ef4595538cfa26d9351f"},"schema_version":"1.0","source":{"id":"1301.2343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.2343","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"1301.2343v1","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.2343","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"5CMLYQDZCWE4","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_16","alias_value":"5CMLYQDZCWE4KRXT","created_at":"2026-05-18T12:27:34Z"},{"alias_kind":"pith_short_8","alias_value":"5CMLYQDZ","created_at":"2026-05-18T12:27:34Z"}],"graph_snapshots":[{"event_id":"sha256:6344c6b7a9da854125e845b287ed415297b9b366f079626601666d55e0f3a8f5","target":"graph","created_at":"2026-05-18T03:36:45Z","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":"Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibi","authors_text":"Harm van Seijen, Richard S. Sutton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T21:54:42Z","title":"Planning by Prioritized Sweeping with Small Backups"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.2343","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:cc2efc84795739a298987b5ca60b7feffba0b546f65df343b3114eb02124312b","target":"record","created_at":"2026-05-18T03:36:45Z","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":"11378e2b8615b107b6108658c8b3d70761c420c4cb0e62aa331f5d9b8ff49f05","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-10T21:54:42Z","title_canon_sha256":"ff487f7a5c36fa92bb1494e6f0c33996af262dfcfa40ef4595538cfa26d9351f"},"schema_version":"1.0","source":{"id":"1301.2343","kind":"arxiv","version":1}},"canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e898bc40791589c546f39976e92a6b136133bbdc9e8fd859f7fce1c08e96f2e1","first_computed_at":"2026-05-18T03:36:45.273055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:36:45.273055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wS+WV1ysH091uStRfa7Kx0ay+p2ApOgsRxnTtylEf0q4WxjlOhPaLzw9Qr8/d5117CVVdY0J1BzH+Fpq8ijQAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:36:45.273695Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.2343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc2efc84795739a298987b5ca60b7feffba0b546f65df343b3114eb02124312b","sha256:6344c6b7a9da854125e845b287ed415297b9b366f079626601666d55e0f3a8f5"],"state_sha256":"ffcf18845b725964eaccbd20774dd65be181cf006e065ae665604eaba026554c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kE1SYNBCcBlxDOETxxBeGhGdvRoBDNibnzSTgxGhLnzCpSDn5O5G3cd4dK6F2Y63vtDj+L9BKzITZV2EIZQuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T16:53:39.115389Z","bundle_sha256":"2809b054fe6f14d820476eb3fdcce6870eb0bb24c6c1759679b8cd5b8d659f38"}}