{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KT4LHULRRSVHMGIUCCEZBUGX2M","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":"1b9379a41dcac3bb4774a777d3d3238920b7616082f2e0774db2502262660f23","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T21:19:52Z","title_canon_sha256":"1989cd2741588be20b2a05d234124350009190ab27de49648f11e0ceee3c04be"},"schema_version":"1.0","source":{"id":"2310.20025","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20025","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20025v3","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20025","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"KT4LHULRRSVH","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"pith_short_16","alias_value":"KT4LHULRRSVHMGIU","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"pith_short_8","alias_value":"KT4LHULR","created_at":"2026-07-05T08:19:37Z"}],"graph_snapshots":[{"event_id":"sha256:6fbccbc1650a9ae50c2740b56e7a9b9bf75a3b46a246a73ba28f98e739f7002b","target":"graph","created_at":"2026-07-05T08:19:37Z","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/2310.20025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face constraints in handling limited data and generalizing to unseen goals. In this work, we propose Goal-conditioned Offline Planning (GOPlan), a novel model-based framework that contains two key phases: (1) pretraining a prior policy capable of capturing multi-modal action distribution within the multi-goal dataset; (2) employing the reanalysis method with pla","authors_text":"Giovanni Montana, Hao Sun, Meng Fang, Mianchu Wang, Rui Yang, Xi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T21:19:52Z","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20025","kind":"arxiv","version":3},"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":"sha256:069357053a2d8eaf6cab4063aa89f5bb1cde2fb676c98bd82598564836f8869b","target":"record","created_at":"2026-07-05T08:19:37Z","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":"1b9379a41dcac3bb4774a777d3d3238920b7616082f2e0774db2502262660f23","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T21:19:52Z","title_canon_sha256":"1989cd2741588be20b2a05d234124350009190ab27de49648f11e0ceee3c04be"},"schema_version":"1.0","source":{"id":"2310.20025","kind":"arxiv","version":3}},"canonical_sha256":"54f8b3d1718caa761914108990d0d7d33ca68a9edf7b59a0b70ecd3b6044c868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54f8b3d1718caa761914108990d0d7d33ca68a9edf7b59a0b70ecd3b6044c868","first_computed_at":"2026-07-05T08:19:37.867436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:37.867436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bdl0LYz6dnZZRgURdewU1oRlDE2O+PZy3h3JySLBPXJKeSmNKj4Lom/t0mEp96tUl/7dRFNgpWixTG4TctDxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:37.867967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20025","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:069357053a2d8eaf6cab4063aa89f5bb1cde2fb676c98bd82598564836f8869b","sha256:6fbccbc1650a9ae50c2740b56e7a9b9bf75a3b46a246a73ba28f98e739f7002b"],"state_sha256":"9a0d54f7f0b19a3393252593980ce6378493d09e917e22833e45e9ae56f1577e"}