{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WLPR73BWUCT4IPDZEACCIX5YDL","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":"7a9ca1c3d3f507e5485e77738fc1f06948ffafb93c4fc326dd42ca0ee7fd7050","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T11:11:03Z","title_canon_sha256":"8940530cc7f3398dddcae3fd5917542d73fe8105a4471a8fbe3b7f37fea862f9"},"schema_version":"1.0","source":{"id":"2602.03389","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03389","created_at":"2026-06-23T02:13:58Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03389v2","created_at":"2026-06-23T02:13:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03389","created_at":"2026-06-23T02:13:58Z"},{"alias_kind":"pith_short_12","alias_value":"WLPR73BWUCT4","created_at":"2026-06-23T02:13:58Z"},{"alias_kind":"pith_short_16","alias_value":"WLPR73BWUCT4IPDZ","created_at":"2026-06-23T02:13:58Z"},{"alias_kind":"pith_short_8","alias_value":"WLPR73BW","created_at":"2026-06-23T02:13:58Z"}],"graph_snapshots":[{"event_id":"sha256:5fd06ac7e9f4c82e79a286f8e41aae7f793b131685fb7ab379153584af19cdb4","target":"graph","created_at":"2026-06-23T02:13:58Z","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/2602.03389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by decomposing tasks, most existing methods rely on separate high- and low-level networks and generate only a single intermediate subgoal, leaving several structural limitations in long-horizon decision-making. To address this limitation, we draw inspiration from chain-of-thought reasoning and propose the Chain-of-Goals Hierarchical Policy (CoGHP), a novel framework that reformulates hierarchical decision-making as autoregressive sequence modeling within","authors_text":"Jinwoo Choi, Sang-Hyun Lee, Seung-Woo Seo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T11:11:03Z","title":"Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03389","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:aeb71d1107cc92b57554088cd065fe604256bcb3d60df46e379a392dac233b29","target":"record","created_at":"2026-06-23T02:13:58Z","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":"7a9ca1c3d3f507e5485e77738fc1f06948ffafb93c4fc326dd42ca0ee7fd7050","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T11:11:03Z","title_canon_sha256":"8940530cc7f3398dddcae3fd5917542d73fe8105a4471a8fbe3b7f37fea862f9"},"schema_version":"1.0","source":{"id":"2602.03389","kind":"arxiv","version":2}},"canonical_sha256":"b2df1fec36a0a7c43c792004245fb81ad23e056bb23c8e888d7382a81ca8177e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2df1fec36a0a7c43c792004245fb81ad23e056bb23c8e888d7382a81ca8177e","first_computed_at":"2026-06-23T02:13:58.846839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:58.846839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YTf9PN4/MXdpi6Vbx4eVxqbIoKnyKWGGiNGZnJauxpX24BPApUmVkoBGGZgWKzWUw3ZsODgwnfCcoSD8rVniCQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:58.847430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03389","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aeb71d1107cc92b57554088cd065fe604256bcb3d60df46e379a392dac233b29","sha256:5fd06ac7e9f4c82e79a286f8e41aae7f793b131685fb7ab379153584af19cdb4"],"state_sha256":"0570bf9df2f6afa189de72d3a29604e5703b3d54eb97da146825770b4e8be273"}