{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XHQG5722YR4CWXG3JYXEVKIOA2","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":"984ee08bfee2ab58354c4461b9c9ac4165e21966014c2b235458810ef0c742df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T16:04:11Z","title_canon_sha256":"68f5a7268d892dff81f88fecc804f85a704a2a3d3379726cdc8f98442cf17650"},"schema_version":"1.0","source":{"id":"2605.17058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17058","created_at":"2026-05-20T00:03:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17058v1","created_at":"2026-05-20T00:03:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17058","created_at":"2026-05-20T00:03:38Z"},{"alias_kind":"pith_short_12","alias_value":"XHQG5722YR4C","created_at":"2026-05-20T00:03:38Z"},{"alias_kind":"pith_short_16","alias_value":"XHQG5722YR4CWXG3","created_at":"2026-05-20T00:03:38Z"},{"alias_kind":"pith_short_8","alias_value":"XHQG5722","created_at":"2026-05-20T00:03:38Z"}],"graph_snapshots":[{"event_id":"sha256:2bf5fb3680b58fdcf42461ee5641596a579a84f457cb7336616f0749eca71128","target":"graph","created_at":"2026-05-20T00:03:38Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.822053Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.763334Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17058/integrity.json","findings":[],"snapshot_sha256":"954d22e3a0ce7b1b02786f7aef02475f1bb3fb8ebefde7f44d56f66ace0ea15c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The combination of exponentially large action spaces, stochastic dynamics, and long-horizon decision-making under limited resources makes Sequential Stochastic Combinatorial Optimization (SSCO) particularly challenging for reinforcement learning. Hierarchical Reinforcement Learning (HRL) offers a natural decomposition, but it places the high-level policy in a Semi-Markov Decision Process (SMDP) where actions have variable durations, making it difficult to learn a world model that is suitable for planning. We introduce a model-based hierarchical framework for sequential stochastic combinatorial","authors_text":"Joni Pajarinen, Tinghuai Wang, Vivienne Huiling Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T16:04:11Z","title":"Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17058","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":"sha256:980761e21231942d2f6c4c2678459a809b1d7ac46dd609912ea4dcd6b9b4d6a6","target":"record","created_at":"2026-05-20T00:03:38Z","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":"984ee08bfee2ab58354c4461b9c9ac4165e21966014c2b235458810ef0c742df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T16:04:11Z","title_canon_sha256":"68f5a7268d892dff81f88fecc804f85a704a2a3d3379726cdc8f98442cf17650"},"schema_version":"1.0","source":{"id":"2605.17058","kind":"arxiv","version":1}},"canonical_sha256":"b9e06eff5ac4782b5cdb4e2e4aa90e06a3531800c6735ded611e8c582d8290b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9e06eff5ac4782b5cdb4e2e4aa90e06a3531800c6735ded611e8c582d8290b2","first_computed_at":"2026-05-20T00:03:38.520597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:38.520597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IRW1gWnGpb5q/x8dF4TIeJ6qRWX0XtpRvl95ufrMJkzvxq5DPrjIl0b1eQNV7GjuZK9vpT3MWo7XF+c2yaM5Ag==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:38.521441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:980761e21231942d2f6c4c2678459a809b1d7ac46dd609912ea4dcd6b9b4d6a6","sha256:2bf5fb3680b58fdcf42461ee5641596a579a84f457cb7336616f0749eca71128"],"state_sha256":"2a85c6307de533bb035c118a723b32923eda2b7b09d424cad87ae134f00958c1"}