{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5IMNTGCPCOPPMZ36753LOFQIYH","short_pith_number":"pith:5IMNTGCP","canonical_record":{"source":{"id":"2605.13207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"09f2085250a3244c76dfc64a56592c9b2f11523a3a97982b0ab1af7245936e21","abstract_canon_sha256":"eb236112774df187358ca124604368097ee047bca5ed54dd1318152a31c2821a"},"schema_version":"1.0"},"canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","source":{"kind":"arxiv","id":"2605.13207","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13207","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13207v1","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13207","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"5IMNTGCPCOPP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5IMNTGCPCOPPMZ36","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5IMNTGCP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5IMNTGCPCOPPMZ36753LOFQIYH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"09f2085250a3244c76dfc64a56592c9b2f11523a3a97982b0ab1af7245936e21","abstract_canon_sha256":"eb236112774df187358ca124604368097ee047bca5ed54dd1318152a31c2821a"},"schema_version":"1.0"},"canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:48.588045Z","signature_b64":"NutoZgjLl8aGWKcGqRv6UESiHjTjFm3vPJJmF0O7LsOsl2v7j3tkSfK1xdYRBOyVs5xmK0N6aWa0tTFQAjnaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","last_reissued_at":"2026-05-18T03:08:48.587295Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:48.587295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13207","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TKEOHjGNH8xrDhAbUhm/fpH9D8GjukXK4BbfUlbxC/dglnJSLWm0L2WX5+H8tf3Gt2yqQ9Y7sHgcWNlWEDmMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:25:01.490354Z"},"content_sha256":"43c7a5ed659da156bfe606d5d40e4e6ea365212ed366f27caf6abbf62127d994","schema_version":"1.0","event_id":"sha256:43c7a5ed659da156bfe606d5d40e4e6ea365212ed366f27caf6abbf62127d994"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5IMNTGCPCOPPMZ36753LOFQIYH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Proutiere, Stefan Stojanovic","submitted_at":"2026-05-13T08:58:33Z","abstract_excerpt":"Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions or goal-conditioned objectives, which largely confine them to goal-reaching tasks and limit their applicability to general reward functions. In this paper, we introduce switching successor measures, an extension of successor measures that enables hierarchical control in zero-shot reinforcement learning without additional supervision, fixed horizons, or manua"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Switching successor measures arise naturally from classical successor measures while preserving their underlying structure, allowing FB π-Switch to extract both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward representations for hierarchical zero-shot RL without additional supervision, fixed horizons, or manually designed subgoals.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That switching successor measures can be derived from classical ones in a way that preserves structure sufficiently to support emergent hierarchical behavior from a single FB representation across both goal-conditioned and general reward tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0bda80f9832fa6543a6f09680df36d3a17fe87b5ec8a6b1857d6edc24bcc995b"},"source":{"id":"2605.13207","kind":"arxiv","version":1},"verdict":{"id":"f4c4fbb0-0e27-49fc-a8e2-0277f5c3967f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:23:39.992215Z","strongest_claim":"Switching successor measures arise naturally from classical successor measures while preserving their underlying structure, allowing FB π-Switch to extract both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward representations for hierarchical zero-shot RL without additional supervision, fixed horizons, or manually designed subgoals.","one_line_summary":"Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That switching successor measures can be derived from classical ones in a way that preserves structure sufficiently to support emergent hierarchical behavior from a single FB representation across both goal-conditioned and general reward tasks.","pith_extraction_headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL."},"references":{"count":64,"sample":[{"doi":"","year":2021,"title":"Deep reinforcement learning at the edge of the statistical precipice","work_id":"c3d48de0-debb-4594-8d88-4bbd76ba95ee","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"A unified framework for unsupervised reinforcement learning al- gorithms","work_id":"599e9445-4bfe-4ead-9512-2ab76ede8723","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Proto successor measure: Representing the behavior space of an RL agent.arXiv preprint arXiv:2411.19418, 2024","work_id":"e2101019-a668-4daf-be2d-55e515f58012","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Option-aware temporally abstracted value for offline goal-conditioned reinforcement learning","work_id":"178e6002-05c1-4b61-838e-d8e5477a8d7c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"OPAL: Offline primitive discovery for accelerating offline reinforcement learning","work_id":"286b3006-aac9-45e5-bec8-8122a192c114","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":64,"snapshot_sha256":"d827bc72f2d7a74a477eb500d5465e590674be9d1ffa73c3a7267c0f8e18c273","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"461adf71a93f3a186bf64f09d8638da67f16902012ca9553c18b810495f73e45"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f4c4fbb0-0e27-49fc-a8e2-0277f5c3967f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+08Rt1ypiu4rO5Tpt2gfmiBCdnm7Q/w83M7IF14kS9f9pgOsVGUxVxUW6Vs9sV3w2fPng146TX6rLy0DwJK3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:25:01.491163Z"},"content_sha256":"7b9018d920d462826e9e2a963bd871adba45879d542211d570146c703a4d05dc","schema_version":"1.0","event_id":"sha256:7b9018d920d462826e9e2a963bd871adba45879d542211d570146c703a4d05dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/bundle.json","state_url":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5IMNTGCPCOPPMZ36753LOFQIYH/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":"2026-05-27T07:25:01Z","links":{"resolver":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH","bundle":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/bundle.json","state":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5IMNTGCPCOPPMZ36753LOFQIYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5IMNTGCPCOPPMZ36753LOFQIYH","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":"eb236112774df187358ca124604368097ee047bca5ed54dd1318152a31c2821a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:58:33Z","title_canon_sha256":"09f2085250a3244c76dfc64a56592c9b2f11523a3a97982b0ab1af7245936e21"},"schema_version":"1.0","source":{"id":"2605.13207","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13207","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13207v1","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13207","created_at":"2026-05-18T03:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"5IMNTGCPCOPP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"5IMNTGCPCOPPMZ36","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"5IMNTGCP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7b9018d920d462826e9e2a963bd871adba45879d542211d570146c703a4d05dc","target":"graph","created_at":"2026-05-18T03:08:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Switching successor measures arise naturally from classical successor measures while preserving their underlying structure, allowing FB π-Switch to extract both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward representations for hierarchical zero-shot RL without additional supervision, fixed horizons, or manually designed subgoals."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That switching successor measures can be derived from classical ones in a way that preserves structure sufficiently to support emergent hierarchical behavior from a single FB representation across both goal-conditioned and general reward tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL."}],"snapshot_sha256":"0bda80f9832fa6543a6f09680df36d3a17fe87b5ec8a6b1857d6edc24bcc995b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"461adf71a93f3a186bf64f09d8638da67f16902012ca9553c18b810495f73e45"},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions or goal-conditioned objectives, which largely confine them to goal-reaching tasks and limit their applicability to general reward functions. In this paper, we introduce switching successor measures, an extension of successor measures that enables hierarchical control in zero-shot reinforcement learning without additional supervision, fixed horizons, or manua","authors_text":"Alexandre Proutiere, Stefan Stojanovic","cross_cats":[],"headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:58:33Z","title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning"},"references":{"count":64,"internal_anchors":3,"resolved_work":64,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Deep reinforcement learning at the edge of the statistical precipice","work_id":"c3d48de0-debb-4594-8d88-4bbd76ba95ee","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A unified framework for unsupervised reinforcement learning al- gorithms","work_id":"599e9445-4bfe-4ead-9512-2ab76ede8723","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Proto successor measure: Representing the behavior space of an RL agent.arXiv preprint arXiv:2411.19418, 2024","work_id":"e2101019-a668-4daf-be2d-55e515f58012","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Option-aware temporally abstracted value for offline goal-conditioned reinforcement learning","work_id":"178e6002-05c1-4b61-838e-d8e5477a8d7c","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"OPAL: Offline primitive discovery for accelerating offline reinforcement learning","work_id":"286b3006-aac9-45e5-bec8-8122a192c114","year":2021}],"snapshot_sha256":"d827bc72f2d7a74a477eb500d5465e590674be9d1ffa73c3a7267c0f8e18c273"},"source":{"id":"2605.13207","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:23:39.992215Z","id":"f4c4fbb0-0e27-49fc-a8e2-0277f5c3967f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","strongest_claim":"Switching successor measures arise naturally from classical successor measures while preserving their underlying structure, allowing FB π-Switch to extract both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward representations for hierarchical zero-shot RL without additional supervision, fixed horizons, or manually designed subgoals.","weakest_assumption":"That switching successor measures can be derived from classical ones in a way that preserves structure sufficiently to support emergent hierarchical behavior from a single FB representation across both goal-conditioned and general reward tasks."}},"verdict_id":"f4c4fbb0-0e27-49fc-a8e2-0277f5c3967f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:43c7a5ed659da156bfe606d5d40e4e6ea365212ed366f27caf6abbf62127d994","target":"record","created_at":"2026-05-18T03:08:48Z","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":"eb236112774df187358ca124604368097ee047bca5ed54dd1318152a31c2821a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:58:33Z","title_canon_sha256":"09f2085250a3244c76dfc64a56592c9b2f11523a3a97982b0ab1af7245936e21"},"schema_version":"1.0","source":{"id":"2605.13207","kind":"arxiv","version":1}},"canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","first_computed_at":"2026-05-18T03:08:48.587295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:48.587295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NutoZgjLl8aGWKcGqRv6UESiHjTjFm3vPJJmF0O7LsOsl2v7j3tkSfK1xdYRBOyVs5xmK0N6aWa0tTFQAjnaDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:48.588045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13207","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43c7a5ed659da156bfe606d5d40e4e6ea365212ed366f27caf6abbf62127d994","sha256:7b9018d920d462826e9e2a963bd871adba45879d542211d570146c703a4d05dc"],"state_sha256":"0f680c7aaf2637f9729cd423cfca2f293fc454f07b96e39806de6233e3cbcedc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MaqJ72JEyax03vkUDgqfg2pY2cRqqTuuj0CP3gzhnG/RPzhtRf3jyHN4QLWjKjaXsTgPGRuqO86Io40EUES2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:25:01.494822Z","bundle_sha256":"2eef1b629c6abc115876029632e575e13430c0f758892e5b7e072385a297dca1"}}