{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QG73PAQQNDAGGRAW7OS52PNLUV","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"71deee7e94c3b44f9a41628fcf3195ee82ab50df45ad8d0b5e0272896d7a3fda","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-26T15:41:52Z","title_canon_sha256":"c3c82be95debc9987ca04a7ca744e90e5b00095c0f1d842d83cb1b5a1ff85652"},"schema_version":"1.0","source":{"id":"2607.23726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23726","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23726v1","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23726","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"QG73PAQQNDAG","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"QG73PAQQNDAGGRAW","created_at":"2026-07-28T01:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"QG73PAQQ","created_at":"2026-07-28T01:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:95ebeddd5166a23426e0d5ca9d26cc2a3a442cb725bf4b7ce810b01bb8e19b71","target":"graph","created_at":"2026-07-28T01:23:07Z","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/2607.23726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration in sparse-reward long-horizon tasks poses significant challenges for reinforcement learning. To address these challenges, we propose a two-level Hierarchical Reinforcement Learning (HRL) framework. The first level handles high-level strategic planning, while the low-level uses the continuous-control Soft Actor-Critic (SAC) algorithm, and they utilize entropy-regularized policy optimization. The proposed framework was trained and evaluated using the Search-and-Rescue-2 (SAR-2) dataset. HRL-SAC effectively addresses sparse-reward long-horizon search problems characterized by delayed ","authors_text":"Afef Hfaiedh, Giansalvo Cirrincione, Issmail Ellabib, Nahla Khraief, Zahra Abdalla Elashaal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-26T15:41:52Z","title":"Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23726","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":"sha256:48fa3dda8ff1b0c5488fab1b0897676202f4fe1a9334c41f86905f9192ba00b1","target":"record","created_at":"2026-07-28T01:23:07Z","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":"71deee7e94c3b44f9a41628fcf3195ee82ab50df45ad8d0b5e0272896d7a3fda","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-26T15:41:52Z","title_canon_sha256":"c3c82be95debc9987ca04a7ca744e90e5b00095c0f1d842d83cb1b5a1ff85652"},"schema_version":"1.0","source":{"id":"2607.23726","kind":"arxiv","version":1}},"canonical_sha256":"81bfb7821068c0634416fba5dd3daba559c1df1c02a3a010a884a2baa9afe49e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81bfb7821068c0634416fba5dd3daba559c1df1c02a3a010a884a2baa9afe49e","first_computed_at":"2026-07-28T01:23:07.786884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:07.786884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iom1RnjOUDBl11pOtUh2pHnN84tv1yacufkwGkt4Ex7HVveOPq6pSnzUi+KFsjahLkqVYYQXNNZUQwU55xZ/DA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:07.787735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23726","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:0c21742aec7a0b84c6227a9e0fec1577650d048cfc0a3231aa2c7093f05d8ca1","sha256:61afeeb410d90dfe566d01146d912200861e4e8d4b00a1a56bb126d0ce88066c"]}],"invalid_events":[],"applied_event_ids":["sha256:48fa3dda8ff1b0c5488fab1b0897676202f4fe1a9334c41f86905f9192ba00b1","sha256:95ebeddd5166a23426e0d5ca9d26cc2a3a442cb725bf4b7ce810b01bb8e19b71"],"state_sha256":"cb1556307ca2db331264f8c3bc9be4ae2b134e131d1adb0d756ea71159edc3a4"}