{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FT4KAS4KAZNZRD4EKBC3ZAV45N","short_pith_number":"pith:FT4KAS4K","canonical_record":{"source":{"id":"1804.00379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-02T03:02:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e225e4d1e70064820a4cf744612e47e87f1e6cef6d90a5e58c2160ffb23234a","abstract_canon_sha256":"57dd3d8e144bf889cd5b24fdee936bd874b7887cabd8864d236dfe71139c28b6"},"schema_version":"1.0"},"canonical_sha256":"2cf8a04b8a065b988f845045bc82bceb54f86b9607e07e9b3980724da2b15dd6","source":{"kind":"arxiv","id":"1804.00379","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FT4KAS4KAZNZRD4EKBC3ZAV45N","target":"record","payload":{"canonical_record":{"source":{"id":"1804.00379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-02T03:02:33Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2e225e4d1e70064820a4cf744612e47e87f1e6cef6d90a5e58c2160ffb23234a","abstract_canon_sha256":"57dd3d8e144bf889cd5b24fdee936bd874b7887cabd8864d236dfe71139c28b6"},"schema_version":"1.0"},"canonical_sha256":"2cf8a04b8a065b988f845045bc82bceb54f86b9607e07e9b3980724da2b15dd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:21.068950Z","signature_b64":"Xa4tbO8NnJFwWDpfYgcIgwOHNmTgte+Ynvj5KuNxk47rBmG9lkSYZtJrJp7COyLzMTbxED5bGMhtYzvWjithCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf8a04b8a065b988f845045bc82bceb54f86b9607e07e9b3980724da2b15dd6","last_reissued_at":"2026-05-17T23:55:21.068515Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:21.068515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.00379","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":"2026-05-17T23:55:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IR4Qv0Sn5axwydgRZZ7fc9rPOazMbTQrfZwiI7BITNboN0vRvU87Geeh9pL6ye731w/YxKQbM7ivFQfMXgXcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:03:29.970978Z"},"content_sha256":"0d791a5917cb96830288a0371e4e2fc9f4fbc6d45f74abcfc158257fca608864","schema_version":"1.0","event_id":"sha256:0d791a5917cb96830288a0371e4e2fc9f4fbc6d45f74abcfc158257fca608864"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FT4KAS4KAZNZRD4EKBC3ZAV45N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recall Traces: Backtracking Models for Efficient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Hugo Larochelle, Philemon Brakel, Sergey Levine, Soumye Singhal, Timothy Lillicrap, William Fedus, Yoshua Bengio","submitted_at":"2018-04-02T03:02:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.00379","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":"2026-05-17T23:55:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKBpVeAyNN/NaAqRkRqysqbY84KWtSCahznxcla8TDnCc1ucvZZ7TWiDTGUMdWw9UkSFv6h8sIplpGNy1h0FCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:03:29.971686Z"},"content_sha256":"6005d4d7c5d5f51432ec483538ce89267d00efc8a72ed6ed1a466442ab696828","schema_version":"1.0","event_id":"sha256:6005d4d7c5d5f51432ec483538ce89267d00efc8a72ed6ed1a466442ab696828"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N/bundle.json","state_url":"https://pith.science/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N/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":"2026-05-25T18:03:29Z","links":{"resolver":"https://pith.science/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N","bundle":"https://pith.science/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N/bundle.json","state":"https://pith.science/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FT4KAS4KAZNZRD4EKBC3ZAV45N/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfMsICNkYqV/q3jpQvfQiOlgzKm5pJlOK+e//dxUXh5E0D7MvpUaG5YL3SLLEzikZnRAFoiWYrFx/7rE+JJ0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:03:29.977847Z","bundle_sha256":"1bfa0992e743dcf95d1d462abfd7198a239b9fcda3096b5962145c8e0f388874"}}