{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RVYVKKMDM7CHAAHE3F2YGL2FXG","short_pith_number":"pith:RVYVKKMD","schema_version":"1.0","canonical_sha256":"8d7155298367c47000e4d975832f45b9b7150c7beff8ccd6489f582bcaf4d403","source":{"kind":"arxiv","id":"2606.28764","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingyuan Zhou, Kaidi Yang, Yuexuan Wang","submitted_at":"2026-06-27T06:46:37Z","abstract_excerpt":"Hierarchical decision-making frameworks are pivotal for addressing complex control tasks, enabling agents to decompose intricate problems into manageable subgoals. Despite their promise, existing hierarchical policies face critical limitations: (i) reinforcement learning (RL)-based methods struggle to guarantee strict constraint satisfaction, and (ii) optimal control (OC)-based approaches often rely on myopic and computationally prohibitive formulations. To reconcile these trade-offs, hierarchical RL-OC architectures have emerged as a promising paradigm. However, the formulation of the lower-l"},"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":"2606.28764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T06:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"63edfc88e5f9f0edad3f3cdf6e15594ea25b5bd8ec981773839efc6e8e9d48bd","abstract_canon_sha256":"65add9785677509ac081c7a75e39f29f20c5262c6cf746964f52e02d38bc30d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:51.019680Z","signature_b64":"Rk3COTY0eotBwCd27DURxZDp1x/w4WSdQqM8X7/fCvgKFxH/PM+mChiZjtg9sadfIjncNUNt+PugtrYXol4ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d7155298367c47000e4d975832f45b9b7150c7beff8ccd6489f582bcaf4d403","last_reissued_at":"2026-06-30T01:16:51.019171Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:51.019171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingyuan Zhou, Kaidi Yang, Yuexuan Wang","submitted_at":"2026-06-27T06:46:37Z","abstract_excerpt":"Hierarchical decision-making frameworks are pivotal for addressing complex control tasks, enabling agents to decompose intricate problems into manageable subgoals. Despite their promise, existing hierarchical policies face critical limitations: (i) reinforcement learning (RL)-based methods struggle to guarantee strict constraint satisfaction, and (ii) optimal control (OC)-based approaches often rely on myopic and computationally prohibitive formulations. To reconcile these trade-offs, hierarchical RL-OC architectures have emerged as a promising paradigm. However, the formulation of the lower-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28764","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/2606.28764/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2606.28764","created_at":"2026-06-30T01:16:51.019240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28764v1","created_at":"2026-06-30T01:16:51.019240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28764","created_at":"2026-06-30T01:16:51.019240+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVYVKKMDM7CH","created_at":"2026-06-30T01:16:51.019240+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVYVKKMDM7CHAAHE","created_at":"2026-06-30T01:16:51.019240+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVYVKKMD","created_at":"2026-06-30T01:16:51.019240+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/RVYVKKMDM7CHAAHE3F2YGL2FXG","json":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG.json","graph_json":"https://pith.science/api/pith-number/RVYVKKMDM7CHAAHE3F2YGL2FXG/graph.json","events_json":"https://pith.science/api/pith-number/RVYVKKMDM7CHAAHE3F2YGL2FXG/events.json","paper":"https://pith.science/paper/RVYVKKMD"},"agent_actions":{"view_html":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG","download_json":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG.json","view_paper":"https://pith.science/paper/RVYVKKMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28764&json=true","fetch_graph":"https://pith.science/api/pith-number/RVYVKKMDM7CHAAHE3F2YGL2FXG/graph.json","fetch_events":"https://pith.science/api/pith-number/RVYVKKMDM7CHAAHE3F2YGL2FXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG/action/storage_attestation","attest_author":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG/action/author_attestation","sign_citation":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG/action/citation_signature","submit_replication":"https://pith.science/pith/RVYVKKMDM7CHAAHE3F2YGL2FXG/action/replication_record"}},"created_at":"2026-06-30T01:16:51.019240+00:00","updated_at":"2026-06-30T01:16:51.019240+00:00"}