{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EHTP2TUTJ45BGLI6SXFWBFHNRM","short_pith_number":"pith:EHTP2TUT","canonical_record":{"source":{"id":"2403.06328","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","cross_cats_sorted":[],"title_canon_sha256":"efb27f3886a1ce3f3c51e7fecfc4dfb5665dc70fa782eb5a7184b331b243b572","abstract_canon_sha256":"4da774a01f4dd6e86b6a6da9fa97be9ab9731223f1202d26e3edd85726740c32"},"schema_version":"1.0"},"canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","source":{"kind":"arxiv","id":"2403.06328","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06328","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06328v4","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06328","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"EHTP2TUTJ45B","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"EHTP2TUTJ45BGLI6","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"EHTP2TUT","created_at":"2026-07-05T10:02:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EHTP2TUTJ45BGLI6SXFWBFHNRM","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06328","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","cross_cats_sorted":[],"title_canon_sha256":"efb27f3886a1ce3f3c51e7fecfc4dfb5665dc70fa782eb5a7184b331b243b572","abstract_canon_sha256":"4da774a01f4dd6e86b6a6da9fa97be9ab9731223f1202d26e3edd85726740c32"},"schema_version":"1.0"},"canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:22.730713Z","signature_b64":"V1ZOlK9doCH16/485wpipqN9oNs+mItwp/olisjCQnhRHtj7RZmZRuK/JXKRPmsvTQfQs+Bgbty7NQZrb4JhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","last_reissued_at":"2026-07-05T10:02:22.730275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:22.730275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06328","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XiKmiJz3Uj1lGS50yiIu9Vl3CjUuIoYCBCJgeNjD+MysZVVbcXXsY5wzbONjrfaoSuI692Hk5b1+66pnlLxABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:01:21.933137Z"},"content_sha256":"276abb4a031e29cc17b3a7cbdec87d833d72ca7914a67b5c41527fdcd5d3aaad","schema_version":"1.0","event_id":"sha256:276abb4a031e29cc17b3a7cbdec87d833d72ca7914a67b5c41527fdcd5d3aaad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EHTP2TUTJ45BGLI6SXFWBFHNRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Chuning Zhu, Simon S. Du, Tyler Han, Xinqi Wang","submitted_at":"2024-03-10T22:27:21Z","abstract_excerpt":"Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through planning. However, autoregressive model rollouts suffer from compounding error, making model-based RL ineffective for long-horizon problems. Successor features offer an alternative by modeling a policy's long-term state occupancy, reducing policy evaluation under new rewards to linear regression. Yet, zero-shot policy optimization for new tasks with successo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06328","kind":"arxiv","version":4},"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/2403.06328/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":"2026-07-05T10:02:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HoBM5w+y0RkAgFhLVqfNssV4T7+OpoEgJKnMxhqeKI7gPNZbjJP8i2P8MLJQ0o4wu7+T35EfTrAJxnfUr9FCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:01:21.934191Z"},"content_sha256":"48e368eb7a9a25dd0b3e5a6f725fe6bbdf0d9d781ae992a374bb7a8a07599dba","schema_version":"1.0","event_id":"sha256:48e368eb7a9a25dd0b3e5a6f725fe6bbdf0d9d781ae992a374bb7a8a07599dba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM/bundle.json","state_url":"https://pith.science/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM/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":"2026-08-21T17:01:21Z","links":{"resolver":"https://pith.science/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM","bundle":"https://pith.science/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM/bundle.json","state":"https://pith.science/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EHTP2TUTJ45BGLI6SXFWBFHNRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EHTP2TUTJ45BGLI6SXFWBFHNRM","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":"4da774a01f4dd6e86b6a6da9fa97be9ab9731223f1202d26e3edd85726740c32","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","title_canon_sha256":"efb27f3886a1ce3f3c51e7fecfc4dfb5665dc70fa782eb5a7184b331b243b572"},"schema_version":"1.0","source":{"id":"2403.06328","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06328","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06328v4","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06328","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"EHTP2TUTJ45B","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"EHTP2TUTJ45BGLI6","created_at":"2026-07-05T10:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"EHTP2TUT","created_at":"2026-07-05T10:02:22Z"}],"graph_snapshots":[{"event_id":"sha256:48e368eb7a9a25dd0b3e5a6f725fe6bbdf0d9d781ae992a374bb7a8a07599dba","target":"graph","created_at":"2026-07-05T10:02:22Z","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/2403.06328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through planning. However, autoregressive model rollouts suffer from compounding error, making model-based RL ineffective for long-horizon problems. Successor features offer an alternative by modeling a policy's long-term state occupancy, reducing policy evaluation under new rewards to linear regression. Yet, zero-shot policy optimization for new tasks with successo","authors_text":"Abhishek Gupta, Chuning Zhu, Simon S. Du, Tyler Han, Xinqi Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06328","kind":"arxiv","version":4},"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":"sha256:276abb4a031e29cc17b3a7cbdec87d833d72ca7914a67b5c41527fdcd5d3aaad","target":"record","created_at":"2026-07-05T10:02:22Z","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":"4da774a01f4dd6e86b6a6da9fa97be9ab9731223f1202d26e3edd85726740c32","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-10T22:27:21Z","title_canon_sha256":"efb27f3886a1ce3f3c51e7fecfc4dfb5665dc70fa782eb5a7184b331b243b572"},"schema_version":"1.0","source":{"id":"2403.06328","kind":"arxiv","version":4}},"canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21e6fd4e934f3a132d1e95cb6094ed8b0fbec879868388e9ed508e7396cf605b","first_computed_at":"2026-07-05T10:02:22.730275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:22.730275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V1ZOlK9doCH16/485wpipqN9oNs+mItwp/olisjCQnhRHtj7RZmZRuK/JXKRPmsvTQfQs+Bgbty7NQZrb4JhDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:22.730713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06328","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:276abb4a031e29cc17b3a7cbdec87d833d72ca7914a67b5c41527fdcd5d3aaad","sha256:48e368eb7a9a25dd0b3e5a6f725fe6bbdf0d9d781ae992a374bb7a8a07599dba"],"state_sha256":"552a1fe9ee709605600417362d84fa6ed70a153a760fbb40cef91d46d2a6b529"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIY81IUrgoIKxOAywTFyZNY2pN+5oKP6blE8GzG1NThNnLZp9j+BPRbBF77GZO4tf1DNZ7zCP+drBLM6V/7SDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:01:21.939573Z","bundle_sha256":"c44be6b2f07c158632664fb1ffb13482bd0ce9e92502b80c5aefd202fdc5b117"}}