{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PAWWFTS2Q3IRYVQULVLXPX7QAQ","short_pith_number":"pith:PAWWFTS2","canonical_record":{"source":{"id":"2002.06473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:46:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39f3f8686915ef42a9c6ad8e3d636a5859a20ce67a907757ac85fcdfa319995e","abstract_canon_sha256":"ad7e4db4e93ee0b15b3f9fada873e25650fa88f6262c754d8f4d0e7443730f6d"},"schema_version":"1.0"},"canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","source":{"kind":"arxiv","id":"2002.06473","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06473","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06473v1","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06473","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"PAWWFTS2Q3IR","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"pith_short_16","alias_value":"PAWWFTS2Q3IRYVQU","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"pith_short_8","alias_value":"PAWWFTS2","created_at":"2026-07-05T00:41:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PAWWFTS2Q3IRYVQULVLXPX7QAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:46:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39f3f8686915ef42a9c6ad8e3d636a5859a20ce67a907757ac85fcdfa319995e","abstract_canon_sha256":"ad7e4db4e93ee0b15b3f9fada873e25650fa88f6262c754d8f4d0e7443730f6d"},"schema_version":"1.0"},"canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:06.462485Z","signature_b64":"Mf8swtB6YPzXS4EQfd4qLR1QB00zR7rR+HyK3lSvS0BiKnYDIvolldNTE1U0yzBbHqY/bVjvsSDSIDpKAlJCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","last_reissued_at":"2026-07-05T00:41:06.462021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:06.462021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06473","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":"2026-07-05T00:41:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/ifNR9DnZiEJRSc8yOJ3IZQ8QlUdSFtjI8Jdethrv90L7ADT9f5EgZHKChZnd4zWpo9E2SB7v4xlbXI94XvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:52:23.614214Z"},"content_sha256":"ad967236e52de4386d3d044b5269758eadbbd689144441acd940c2a8bde5195d","schema_version":"1.0","event_id":"sha256:ad967236e52de4386d3d044b5269758eadbbd689144441acd940c2a8bde5195d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PAWWFTS2Q3IRYVQULVLXPX7QAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Isbell, Yannick Schroecker","submitted_at":"2020-02-15T23:46:29Z","abstract_excerpt":"This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a demonstration). Drawing a connection between probabilistic long-term dynamics and the desired value function, this work introduces an approach which utilizes recent advances in density estimation to effectively learn to reach a given state. As our first contribution, we use this approach for goal-conditioned reinforcement learning and show that it is both efficient and d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06473","kind":"arxiv","version":1},"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/2002.06473/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":"2026-07-05T00:41:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W11gtnVJ7S5EC0L15B3y1WjjYf38VkIDwf3eyaNcjJ062cXNGhDhHI1k499CZWQXBg9cDoRuAvB2aiN3h2l1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:52:23.614714Z"},"content_sha256":"16561058fd80a90c22ae702cbc22160b024478626117b1d29b6991c384d82d87","schema_version":"1.0","event_id":"sha256:16561058fd80a90c22ae702cbc22160b024478626117b1d29b6991c384d82d87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/bundle.json","state_url":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/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":"2026-08-08T12:52:23Z","links":{"resolver":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ","bundle":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/bundle.json","state":"https://pith.science/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PAWWFTS2Q3IRYVQULVLXPX7QAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PAWWFTS2Q3IRYVQULVLXPX7QAQ","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":"ad7e4db4e93ee0b15b3f9fada873e25650fa88f6262c754d8f4d0e7443730f6d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:46:29Z","title_canon_sha256":"39f3f8686915ef42a9c6ad8e3d636a5859a20ce67a907757ac85fcdfa319995e"},"schema_version":"1.0","source":{"id":"2002.06473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06473","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06473v1","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06473","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"pith_short_12","alias_value":"PAWWFTS2Q3IR","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"pith_short_16","alias_value":"PAWWFTS2Q3IRYVQU","created_at":"2026-07-05T00:41:06Z"},{"alias_kind":"pith_short_8","alias_value":"PAWWFTS2","created_at":"2026-07-05T00:41:06Z"}],"graph_snapshots":[{"event_id":"sha256:16561058fd80a90c22ae702cbc22160b024478626117b1d29b6991c384d82d87","target":"graph","created_at":"2026-07-05T00:41:06Z","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/2002.06473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a demonstration). Drawing a connection between probabilistic long-term dynamics and the desired value function, this work introduces an approach which utilizes recent advances in density estimation to effectively learn to reach a given state. As our first contribution, we use this approach for goal-conditioned reinforcement learning and show that it is both efficient and d","authors_text":"Charles Isbell, Yannick Schroecker","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:46:29Z","title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06473","kind":"arxiv","version":1},"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:ad967236e52de4386d3d044b5269758eadbbd689144441acd940c2a8bde5195d","target":"record","created_at":"2026-07-05T00:41:06Z","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":"ad7e4db4e93ee0b15b3f9fada873e25650fa88f6262c754d8f4d0e7443730f6d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-15T23:46:29Z","title_canon_sha256":"39f3f8686915ef42a9c6ad8e3d636a5859a20ce67a907757ac85fcdfa319995e"},"schema_version":"1.0","source":{"id":"2002.06473","kind":"arxiv","version":1}},"canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"782d62ce5a86d11c56145d5777dff00428e1e8c156d4ad34e5320886cd85dc3f","first_computed_at":"2026-07-05T00:41:06.462021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:41:06.462021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mf8swtB6YPzXS4EQfd4qLR1QB00zR7rR+HyK3lSvS0BiKnYDIvolldNTE1U0yzBbHqY/bVjvsSDSIDpKAlJCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:41:06.462485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad967236e52de4386d3d044b5269758eadbbd689144441acd940c2a8bde5195d","sha256:16561058fd80a90c22ae702cbc22160b024478626117b1d29b6991c384d82d87"],"state_sha256":"c7de51468d23a649abe2bcac1658497ee880b0934f963aa92fd88e5faaad6b8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/B0I8RFN+BpNlMCAmkkE59qlCr4NfHdLNT7o7alrJa5ar6vEPjAY7msO7DxpRZC/wln5NdGOkmnHYe/ObtDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:52:23.618402Z","bundle_sha256":"04dc420a4d946e75bdda59d2cbcc8f51a2becad0b64ddd63d298d1815287b4ad"}}