{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5BXF7BG3RQGS5F4NWQLF5I7S6Q","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":"aa5ec2deb35ccb001577ebb9113e89c41c4f8133743fd8b6bd916e0c2385182b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-20T13:08:14Z","title_canon_sha256":"4435acd6a04e7e1a8a15e829814f596054409d9e9b7a07332580d492c7246c01"},"schema_version":"1.0","source":{"id":"2307.10846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10846","created_at":"2026-07-05T06:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10846v1","created_at":"2026-07-05T06:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10846","created_at":"2026-07-05T06:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"5BXF7BG3RQGS","created_at":"2026-07-05T06:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"5BXF7BG3RQGS5F4N","created_at":"2026-07-05T06:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"5BXF7BG3","created_at":"2026-07-05T06:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:cf51fa530cfe968f7e0a42b86cdf511531619d570092a96d7fe295a3f476bd6c","target":"graph","created_at":"2026-07-05T06:33:12Z","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/2307.10846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set diverse goals to learn a set of skills. Despite the excellent works proposed in various fields, reaching distant goals in temporally extended tasks remains a challenge for GCRL. Current works tackled this problem by leveraging planning algorithms to plan intermediate subgoals to augment GCRL. Their methods need two crucial requirements: (i) a state representation space to search valid subgoals, and (ii) a distance function to measure the reachability of subgoals. However, they struggle to scale to high-dimens","authors_text":"Bin He, Hongjun Zhou, Mingyu You, Xuanhui Xu, Zhifeng Qian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-20T13:08:14Z","title":"Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10846","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":"sha256:247ffebfae0d9a1610fac110b672c6e4dc001922e4b68f7ee0c04f9228edf45c","target":"record","created_at":"2026-07-05T06:33:12Z","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":"aa5ec2deb35ccb001577ebb9113e89c41c4f8133743fd8b6bd916e0c2385182b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-20T13:08:14Z","title_canon_sha256":"4435acd6a04e7e1a8a15e829814f596054409d9e9b7a07332580d492c7246c01"},"schema_version":"1.0","source":{"id":"2307.10846","kind":"arxiv","version":1}},"canonical_sha256":"e86e5f84db8c0d2e978db4165ea3f2f4393b788488eb255a279a11ed3dccbcf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e86e5f84db8c0d2e978db4165ea3f2f4393b788488eb255a279a11ed3dccbcf7","first_computed_at":"2026-07-05T06:33:12.327667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:12.327667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2lrkl6K8x8E4eBH/Q0Qy9qo6BXkM163fc8nijzh3Q4ELccQPimgb0W8Ui0lfW9RH7b5Znaf6aR/1YK2dLTlbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:12.328053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.10846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:247ffebfae0d9a1610fac110b672c6e4dc001922e4b68f7ee0c04f9228edf45c","sha256:cf51fa530cfe968f7e0a42b86cdf511531619d570092a96d7fe295a3f476bd6c"],"state_sha256":"33107c928817a2163803729bed60842a1b5840797fe84d03feca22c20d8320c9"}