{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FT4KAS4KAZNZRD4EKBC3ZAV45N","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":"57dd3d8e144bf889cd5b24fdee936bd874b7887cabd8864d236dfe71139c28b6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-02T03:02:33Z","title_canon_sha256":"2e225e4d1e70064820a4cf744612e47e87f1e6cef6d90a5e58c2160ffb23234a"},"schema_version":"1.0","source":{"id":"1804.00379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.00379","created_at":"2026-05-17T23:55:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.00379v2","created_at":"2026-05-17T23:55:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.00379","created_at":"2026-05-17T23:55:21Z"},{"alias_kind":"pith_short_12","alias_value":"FT4KAS4KAZNZ","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"FT4KAS4KAZNZRD4E","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"FT4KAS4K","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:6005d4d7c5d5f51432ec483538ce89267d00efc8a72ed6ed1a466442ab696828","target":"graph","created_at":"2026-05-17T23:55:21Z","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":"In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provide a relevant learning signal. Hence, we may want to preferentially train on those high-reward states and the probable trajectories leading to them. To this end, we advocate for the use of a backtracking model that predicts the preceding states that terminate at a given high-reward state. We can train a model which, starting from a high value state (or one that is estimated to have high value), predicts and sample for which the (state, action)-tuples may ha","authors_text":"Anirudh Goyal, Hugo Larochelle, Philemon Brakel, Sergey Levine, Soumye Singhal, Timothy Lillicrap, William Fedus, Yoshua Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-02T03:02:33Z","title":"Recall Traces: Backtracking Models for Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00379","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":"sha256:0d791a5917cb96830288a0371e4e2fc9f4fbc6d45f74abcfc158257fca608864","target":"record","created_at":"2026-05-17T23:55:21Z","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":"57dd3d8e144bf889cd5b24fdee936bd874b7887cabd8864d236dfe71139c28b6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-02T03:02:33Z","title_canon_sha256":"2e225e4d1e70064820a4cf744612e47e87f1e6cef6d90a5e58c2160ffb23234a"},"schema_version":"1.0","source":{"id":"1804.00379","kind":"arxiv","version":2}},"canonical_sha256":"2cf8a04b8a065b988f845045bc82bceb54f86b9607e07e9b3980724da2b15dd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cf8a04b8a065b988f845045bc82bceb54f86b9607e07e9b3980724da2b15dd6","first_computed_at":"2026-05-17T23:55:21.068515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:21.068515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xa4tbO8NnJFwWDpfYgcIgwOHNmTgte+Ynvj5KuNxk47rBmG9lkSYZtJrJp7COyLzMTbxED5bGMhtYzvWjithCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:21.068950Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.00379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d791a5917cb96830288a0371e4e2fc9f4fbc6d45f74abcfc158257fca608864","sha256:6005d4d7c5d5f51432ec483538ce89267d00efc8a72ed6ed1a466442ab696828"],"state_sha256":"f2320cf47ad114dc80b1dbdc19ebd061f5f8186a1ae36e6127a0735e412a0def"}