{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3GGWUG6SJE3XFJYW4OVZCFDBVQ","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":"a183cc21cde01315228da3106cc601bdf21ab8bfacda1a9b2b3068d9ed5b89b8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T16:00:47Z","title_canon_sha256":"ce2a75d486e799982859db83b44279f87b019ca5cbf7fd72e5c3289dc38b9b0a"},"schema_version":"1.0","source":{"id":"2010.13685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13685","created_at":"2026-07-05T01:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13685v1","created_at":"2026-07-05T01:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13685","created_at":"2026-07-05T01:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"3GGWUG6SJE3X","created_at":"2026-07-05T01:46:08Z"},{"alias_kind":"pith_short_16","alias_value":"3GGWUG6SJE3XFJYW","created_at":"2026-07-05T01:46:08Z"},{"alias_kind":"pith_short_8","alias_value":"3GGWUG6S","created_at":"2026-07-05T01:46:08Z"}],"graph_snapshots":[{"event_id":"sha256:b7e7b8e8824059080275e39278cbd6778d6ec9f3aff83f9a1bb79bb79aef25be","target":"graph","created_at":"2026-07-05T01:46:08Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.13685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of credit assignment in reinforcement learning and explore fundamental questions regarding the way in which an agent can best use additional computation to propagate new information, by planning with internal models of the world to improve its predictions. Particularly, we work to understand the gains and peculiarities of planning employed as forethought via forward models or as hindsight operating with backward models. We establish the relative merits, limitations and complementary properties of both planning mechanisms in carefully constructed scenarios. Further, we in","authors_text":"Doina Precup, Hado van Hasselt, Veronica Chelu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T16:00:47Z","title":"Forethought and Hindsight in Credit Assignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13685","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":"sha256:62174448bdb0402add3924d680c76c9123508d6ef3252d8fddfdd5ff62ffc676","target":"record","created_at":"2026-07-05T01:46:08Z","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":"a183cc21cde01315228da3106cc601bdf21ab8bfacda1a9b2b3068d9ed5b89b8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T16:00:47Z","title_canon_sha256":"ce2a75d486e799982859db83b44279f87b019ca5cbf7fd72e5c3289dc38b9b0a"},"schema_version":"1.0","source":{"id":"2010.13685","kind":"arxiv","version":1}},"canonical_sha256":"d98d6a1bd2493772a716e3ab911461ac047ca0d5145ef45a3d49e16e76e66baf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d98d6a1bd2493772a716e3ab911461ac047ca0d5145ef45a3d49e16e76e66baf","first_computed_at":"2026-07-05T01:46:08.591253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:46:08.591253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yyZPT8q8ZULB5e5cOKbXL9N+uW+I3osH60FKj52PGujQUYp+VhqUjyrRTBEuTGDha5owVBtwNlgHo9GdFCFsCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:46:08.591676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.13685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62174448bdb0402add3924d680c76c9123508d6ef3252d8fddfdd5ff62ffc676","sha256:b7e7b8e8824059080275e39278cbd6778d6ec9f3aff83f9a1bb79bb79aef25be"],"state_sha256":"5fcd8fcb643b51bde8dbdcfbb32cba01390c46eaad04bacb173e8bf767b475e3"}