{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:G2A6TALSGL3DBPTDSX2QN7BB7E","short_pith_number":"pith:G2A6TALS","canonical_record":{"source":{"id":"2111.03189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131","abstract_canon_sha256":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a"},"schema_version":"1.0"},"canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","source":{"kind":"arxiv","id":"2111.03189","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03189","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03189v2","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03189","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"G2A6TALSGL3D","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"G2A6TALSGL3DBPTD","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"G2A6TALS","created_at":"2026-07-05T04:09:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:G2A6TALSGL3DBPTDSX2QN7BB7E","target":"record","payload":{"canonical_record":{"source":{"id":"2111.03189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131","abstract_canon_sha256":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a"},"schema_version":"1.0"},"canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:59.027487Z","signature_b64":"TmvotIDaKQ0AkblkNwXbRX+9LVMs5OukJVlvFgj1yq/upUMhDRTZDUBMpwIQq23U9Z2LwadGHdlmBlcYqIlhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","last_reissued_at":"2026-07-05T04:09:59.027013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:59.027013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.03189","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":"2026-07-05T04:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dv7+Ey9IMdaI+jTvVH+awrQ7lXCFYBP5bZjEpNbT4f9HEy/HS/fqObG55Zt2NdNevQB3/Lio0xwrsErjzkQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:38.792095Z"},"content_sha256":"61aeb810f18a94b12872e306f85219dd765a59178e8f67d43fa0145e22738904","schema_version":"1.0","event_id":"sha256:61aeb810f18a94b12872e306f85219dd765a59178e8f67d43fa0145e22738904"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:G2A6TALSGL3DBPTDSX2QN7BB7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Toshev, Brian Ichter, Dhruv Shah, Peng Xu, Sergey Levine, Ted Xiao, Yao Lu","submitted_at":"2021-11-04T22:46:16Z","abstract_excerpt":"Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lower-level skills. Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions. Hierarchies can further improve on this by abstracting the space states as well. We posit that a suitable state abstraction should depend on the capabilities of the available lower-level policies. We propose Value Function Spaces: a simple ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03189","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.03189/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":"2026-07-05T04:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BzOZA/h8E7p8sLKpRCv7kF+vWqWVf4Cxk9o6kDKWlAAw5aanFuFVQL+QFzEsyV0yOhg+JLuxpy+P8mxRdGW+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:38.792446Z"},"content_sha256":"6b201eaea50f288dca3c1572348e958c5fa737905a09d63aac05a3da5a5e9aa6","schema_version":"1.0","event_id":"sha256:6b201eaea50f288dca3c1572348e958c5fa737905a09d63aac05a3da5a5e9aa6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/bundle.json","state_url":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/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":"2026-08-11T13:04:38Z","links":{"resolver":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E","bundle":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/bundle.json","state":"https://pith.science/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2A6TALSGL3DBPTDSX2QN7BB7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G2A6TALSGL3DBPTDSX2QN7BB7E","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":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131"},"schema_version":"1.0","source":{"id":"2111.03189","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03189","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03189v2","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03189","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"G2A6TALSGL3D","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_16","alias_value":"G2A6TALSGL3DBPTD","created_at":"2026-07-05T04:09:59Z"},{"alias_kind":"pith_short_8","alias_value":"G2A6TALS","created_at":"2026-07-05T04:09:59Z"}],"graph_snapshots":[{"event_id":"sha256:6b201eaea50f288dca3c1572348e958c5fa737905a09d63aac05a3da5a5e9aa6","target":"graph","created_at":"2026-07-05T04:09:59Z","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/2111.03189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lower-level skills. Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions. Hierarchies can further improve on this by abstracting the space states as well. We posit that a suitable state abstraction should depend on the capabilities of the available lower-level policies. We propose Value Function Spaces: a simple ap","authors_text":"Alexander Toshev, Brian Ichter, Dhruv Shah, Peng Xu, Sergey Levine, Ted Xiao, Yao Lu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03189","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":"sha256:61aeb810f18a94b12872e306f85219dd765a59178e8f67d43fa0145e22738904","target":"record","created_at":"2026-07-05T04:09:59Z","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":"582db74d995dea5cffb0d902127ce69f1cc5abd58f31356d6fd131be5a341b5a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-04T22:46:16Z","title_canon_sha256":"071425454f6090574d5432e742b44f0a3865d497dc46d968364996e323a82131"},"schema_version":"1.0","source":{"id":"2111.03189","kind":"arxiv","version":2}},"canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3681e9817232f630be6395f506fc21f901058e66ef99548e97d8b7b4876cafc0","first_computed_at":"2026-07-05T04:09:59.027013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:59.027013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TmvotIDaKQ0AkblkNwXbRX+9LVMs5OukJVlvFgj1yq/upUMhDRTZDUBMpwIQq23U9Z2LwadGHdlmBlcYqIlhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:59.027487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.03189","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61aeb810f18a94b12872e306f85219dd765a59178e8f67d43fa0145e22738904","sha256:6b201eaea50f288dca3c1572348e958c5fa737905a09d63aac05a3da5a5e9aa6"],"state_sha256":"17718df4e3b7a736253d4c43da4862293311cf27a9fd531ae37ae1be64ba9fee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CLXeyvjqawL6so3hHFNlSXMd+i7wRjbsJP/abEcjqQgsHvsGoBXyA8PlsxyHyPQFRLo29inh0VfsI2+KCnXSDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:04:38.794958Z","bundle_sha256":"6689a921da4f3499aa52fec82b477a23b58bd912edc3f0a076407b773fc3e70e"}}