{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LFBMMOTFWLIWDST472VOEFCRZY","short_pith_number":"pith:LFBMMOTF","canonical_record":{"source":{"id":"2305.15277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T16:02:51Z","cross_cats_sorted":[],"title_canon_sha256":"c77a0e66034abc32a97e03f7669e113c542b04fc8655c78a7013d33ec2269e86","abstract_canon_sha256":"4ebe4d30707377c92bbc0632d9787b9f6ea9d3e40a595b0fd27356357f32bcff"},"schema_version":"1.0"},"canonical_sha256":"5942c63a65b2d161ca7cfeaae21451ce1a5a0ad150d90a85f15e6ecd5b6a0e54","source":{"kind":"arxiv","id":"2305.15277","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15277","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15277v3","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15277","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"pith_short_12","alias_value":"LFBMMOTFWLIW","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"pith_short_16","alias_value":"LFBMMOTFWLIWDST4","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"pith_short_8","alias_value":"LFBMMOTF","created_at":"2026-07-05T07:37:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LFBMMOTFWLIWDST472VOEFCRZY","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15277","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T16:02:51Z","cross_cats_sorted":[],"title_canon_sha256":"c77a0e66034abc32a97e03f7669e113c542b04fc8655c78a7013d33ec2269e86","abstract_canon_sha256":"4ebe4d30707377c92bbc0632d9787b9f6ea9d3e40a595b0fd27356357f32bcff"},"schema_version":"1.0"},"canonical_sha256":"5942c63a65b2d161ca7cfeaae21451ce1a5a0ad150d90a85f15e6ecd5b6a0e54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:29.045313Z","signature_b64":"pbpUt9U+9lyI0nvg1iazGD6A2vxjfs5mUZRtFBrV6ohM0G3u5wZ0nRFx//kkkzFCM6KDRU3PRoYtKFcTlibTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5942c63a65b2d161ca7cfeaae21451ce1a5a0ad150d90a85f15e6ecd5b6a0e54","last_reissued_at":"2026-07-05T07:37:29.044859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:29.044859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15277","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:37:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6SUT3lcGnM/+JcB68guuB/Vun0MniDG7Vk7DfVHltBgsXcggPiwEpwzudpz35lXuZa/YaGLWmEob5bPyj/p+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:09:44.045880Z"},"content_sha256":"b57f47c569e30ef97e131492b6cf59a3ab089a88199a51bd7f9b083eb050e7bc","schema_version":"1.0","event_id":"sha256:b57f47c569e30ef97e131492b6cf59a3ab089a88199a51bd7f9b083eb050e7bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LFBMMOTFWLIWDST472VOEFCRZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Successor-Predecessor Intrinsic Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changmin Yu, Maneesh Sahani, Neil Burgess, Samuel J. Gershman","submitted_at":"2023-05-24T16:02:51Z","abstract_excerpt":"Exploration is essential in reinforcement learning, particularly in environments where external rewards are sparse. Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with self-generated intrinsic rewards. Although the study of intrinsic rewards has a long history, existing methods focus on composing the intrinsic reward based on measures of future prospects of states, ignoring the information contained in the retrospective structure of transition sequences. Here we argue that the agent can utilise retrospective information to generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15277","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.15277/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T07:37:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+9+/XTP5hSK8zW5IodpyLHbLsp5ilF+vQkaN6ve4ymcoWp+FNoxMW+uq27F4Vv3Gn964p0t3YH7qncAqYsIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T19:09:44.046251Z"},"content_sha256":"5baa181df6cb28f051b465587a8d0be1972da86a0af5e151a52152fb13127a06","schema_version":"1.0","event_id":"sha256:5baa181df6cb28f051b465587a8d0be1972da86a0af5e151a52152fb13127a06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFBMMOTFWLIWDST472VOEFCRZY/bundle.json","state_url":"https://pith.science/pith/LFBMMOTFWLIWDST472VOEFCRZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFBMMOTFWLIWDST472VOEFCRZY/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":"2026-07-14T19:09:44Z","links":{"resolver":"https://pith.science/pith/LFBMMOTFWLIWDST472VOEFCRZY","bundle":"https://pith.science/pith/LFBMMOTFWLIWDST472VOEFCRZY/bundle.json","state":"https://pith.science/pith/LFBMMOTFWLIWDST472VOEFCRZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFBMMOTFWLIWDST472VOEFCRZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LFBMMOTFWLIWDST472VOEFCRZY","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":"4ebe4d30707377c92bbc0632d9787b9f6ea9d3e40a595b0fd27356357f32bcff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T16:02:51Z","title_canon_sha256":"c77a0e66034abc32a97e03f7669e113c542b04fc8655c78a7013d33ec2269e86"},"schema_version":"1.0","source":{"id":"2305.15277","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15277","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15277v3","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15277","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"pith_short_12","alias_value":"LFBMMOTFWLIW","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"pith_short_16","alias_value":"LFBMMOTFWLIWDST4","created_at":"2026-07-05T07:37:29Z"},{"alias_kind":"pith_short_8","alias_value":"LFBMMOTF","created_at":"2026-07-05T07:37:29Z"}],"graph_snapshots":[{"event_id":"sha256:5baa181df6cb28f051b465587a8d0be1972da86a0af5e151a52152fb13127a06","target":"graph","created_at":"2026-07-05T07:37:29Z","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/2305.15277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration is essential in reinforcement learning, particularly in environments where external rewards are sparse. Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with self-generated intrinsic rewards. Although the study of intrinsic rewards has a long history, existing methods focus on composing the intrinsic reward based on measures of future prospects of states, ignoring the information contained in the retrospective structure of transition sequences. Here we argue that the agent can utilise retrospective information to generat","authors_text":"Changmin Yu, Maneesh Sahani, Neil Burgess, Samuel J. Gershman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T16:02:51Z","title":"Successor-Predecessor Intrinsic Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15277","kind":"arxiv","version":3},"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:b57f47c569e30ef97e131492b6cf59a3ab089a88199a51bd7f9b083eb050e7bc","target":"record","created_at":"2026-07-05T07:37:29Z","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":"4ebe4d30707377c92bbc0632d9787b9f6ea9d3e40a595b0fd27356357f32bcff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T16:02:51Z","title_canon_sha256":"c77a0e66034abc32a97e03f7669e113c542b04fc8655c78a7013d33ec2269e86"},"schema_version":"1.0","source":{"id":"2305.15277","kind":"arxiv","version":3}},"canonical_sha256":"5942c63a65b2d161ca7cfeaae21451ce1a5a0ad150d90a85f15e6ecd5b6a0e54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5942c63a65b2d161ca7cfeaae21451ce1a5a0ad150d90a85f15e6ecd5b6a0e54","first_computed_at":"2026-07-05T07:37:29.044859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:29.044859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pbpUt9U+9lyI0nvg1iazGD6A2vxjfs5mUZRtFBrV6ohM0G3u5wZ0nRFx//kkkzFCM6KDRU3PRoYtKFcTlibTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:29.045313Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15277","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b57f47c569e30ef97e131492b6cf59a3ab089a88199a51bd7f9b083eb050e7bc","sha256:5baa181df6cb28f051b465587a8d0be1972da86a0af5e151a52152fb13127a06"],"state_sha256":"7046e8e18604ca0439ae1ff79d59d0331006fa93735a2c5d53089d1414fbe9e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8CFbtEBv1o/W1U5eOcAVjXZt4hvY6zwbpxCiwY4QhG1PD2bGMDsLuNQdDhNCZyMbzLN+59SQjikCMgaTrmzgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T19:09:44.048794Z","bundle_sha256":"366e68f7f97d5aec1f898d14b867b0e2a021bca9c34225585ec8fdce9d2cbe90"}}