{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XHQG5722YR4CWXG3JYXEVKIOA2","short_pith_number":"pith:XHQG5722","schema_version":"1.0","canonical_sha256":"b9e06eff5ac4782b5cdb4e2e4aa90e06a3531800c6735ded611e8c582d8290b2","source":{"kind":"arxiv","id":"2605.17058","version":1},"attestation_state":"computed","paper":{"title":"Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joni Pajarinen, Tinghuai Wang, Vivienne Huiling Wang","submitted_at":"2026-05-16T16:04:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-16T16:04:11Z","cross_cats_sorted":[],"title_canon_sha256":"68f5a7268d892dff81f88fecc804f85a704a2a3d3379726cdc8f98442cf17650","abstract_canon_sha256":"984ee08bfee2ab58354c4461b9c9ac4165e21966014c2b235458810ef0c742df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:38.521441Z","signature_b64":"IRW1gWnGpb5q/x8dF4TIeJ6qRWX0XtpRvl95ufrMJkzvxq5DPrjIl0b1eQNV7GjuZK9vpT3MWo7XF+c2yaM5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9e06eff5ac4782b5cdb4e2e4aa90e06a3531800c6735ded611e8c582d8290b2","last_reissued_at":"2026-05-20T00:03:38.520597Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:38.520597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joni Pajarinen, Tinghuai Wang, Vivienne Huiling Wang","submitted_at":"2026-05-16T16:04:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17058","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17058/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"954d22e3a0ce7b1b02786f7aef02475f1bb3fb8ebefde7f44d56f66ace0ea15c"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17058","created_at":"2026-05-20T00:03:38.520741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17058v1","created_at":"2026-05-20T00:03:38.520741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17058","created_at":"2026-05-20T00:03:38.520741+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHQG5722YR4C","created_at":"2026-05-20T00:03:38.520741+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHQG5722YR4CWXG3","created_at":"2026-05-20T00:03:38.520741+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHQG5722","created_at":"2026-05-20T00:03:38.520741+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2","json":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2.json","graph_json":"https://pith.science/api/pith-number/XHQG5722YR4CWXG3JYXEVKIOA2/graph.json","events_json":"https://pith.science/api/pith-number/XHQG5722YR4CWXG3JYXEVKIOA2/events.json","paper":"https://pith.science/paper/XHQG5722"},"agent_actions":{"view_html":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2","download_json":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2.json","view_paper":"https://pith.science/paper/XHQG5722","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17058&json=true","fetch_graph":"https://pith.science/api/pith-number/XHQG5722YR4CWXG3JYXEVKIOA2/graph.json","fetch_events":"https://pith.science/api/pith-number/XHQG5722YR4CWXG3JYXEVKIOA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2/action/storage_attestation","attest_author":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2/action/author_attestation","sign_citation":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2/action/citation_signature","submit_replication":"https://pith.science/pith/XHQG5722YR4CWXG3JYXEVKIOA2/action/replication_record"}},"created_at":"2026-05-20T00:03:38.520741+00:00","updated_at":"2026-05-20T00:03:38.520741+00:00"}