{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHZ25LOQRGYHP6V33U7I7ETPDE","short_pith_number":"pith:NHZ25LOQ","schema_version":"1.0","canonical_sha256":"69f3aeadd089b077fabbdd3e8f926f193b16e64912515d1257122a2d58e5a7f5","source":{"kind":"arxiv","id":"2502.05537","version":1},"attestation_state":"computed","paper":{"title":"Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haipeng Chen, Xinsong Feng, Yanhai Xiong, Zihan Yu","submitted_at":"2025-02-08T12:00:30Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a promising tool for combinatorial optimization (CO) problems due to its ability to learn fast, effective, and generalizable solutions. Nonetheless, existing works mostly focus on one-shot deterministic CO, while sequential stochastic CO (SSCO) has rarely been studied despite its broad applications such as adaptive influence maximization (IM) and infectious disease intervention. In this paper, we study the SSCO problem where we first decide the budget (e.g., number of seed nodes in adaptive IM) allocation for all time steps, and then select a set of n"},"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":"2502.05537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-08T12:00:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dc6bc9b35fb603a666079c3add32e73275fbee4782689bcf8bd43af107f1aee9","abstract_canon_sha256":"09c8381f1d63dee1f921cc9f39fdb7b99fbe72a9526eb6e47c3f24a2388eb398"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:39.586624Z","signature_b64":"rhwpLm7ok6N+KzF5cS66M4hyJKHW4TZv/13pbQDpzU4QLbArwuj/SHdfXHGTySKkhpU1PV8ZDAjMaOn+Pzo/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69f3aeadd089b077fabbdd3e8f926f193b16e64912515d1257122a2d58e5a7f5","last_reissued_at":"2026-07-05T10:11:39.586217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:39.586217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haipeng Chen, Xinsong Feng, Yanhai Xiong, Zihan Yu","submitted_at":"2025-02-08T12:00:30Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a promising tool for combinatorial optimization (CO) problems due to its ability to learn fast, effective, and generalizable solutions. Nonetheless, existing works mostly focus on one-shot deterministic CO, while sequential stochastic CO (SSCO) has rarely been studied despite its broad applications such as adaptive influence maximization (IM) and infectious disease intervention. In this paper, we study the SSCO problem where we first decide the budget (e.g., number of seed nodes in adaptive IM) allocation for all time steps, and then select a set of n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05537","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/2502.05537/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":"2502.05537","created_at":"2026-07-05T10:11:39.586266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05537v1","created_at":"2026-07-05T10:11:39.586266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05537","created_at":"2026-07-05T10:11:39.586266+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHZ25LOQRGYH","created_at":"2026-07-05T10:11:39.586266+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHZ25LOQRGYHP6V3","created_at":"2026-07-05T10:11:39.586266+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHZ25LOQ","created_at":"2026-07-05T10:11:39.586266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.19544","citing_title":"Demonstrating Real Advantage of Machine-Learning-Enhanced Monte Carlo for Combinatorial Optimization","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE","json":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE.json","graph_json":"https://pith.science/api/pith-number/NHZ25LOQRGYHP6V33U7I7ETPDE/graph.json","events_json":"https://pith.science/api/pith-number/NHZ25LOQRGYHP6V33U7I7ETPDE/events.json","paper":"https://pith.science/paper/NHZ25LOQ"},"agent_actions":{"view_html":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE","download_json":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE.json","view_paper":"https://pith.science/paper/NHZ25LOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05537&json=true","fetch_graph":"https://pith.science/api/pith-number/NHZ25LOQRGYHP6V33U7I7ETPDE/graph.json","fetch_events":"https://pith.science/api/pith-number/NHZ25LOQRGYHP6V33U7I7ETPDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE/action/storage_attestation","attest_author":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE/action/author_attestation","sign_citation":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE/action/citation_signature","submit_replication":"https://pith.science/pith/NHZ25LOQRGYHP6V33U7I7ETPDE/action/replication_record"}},"created_at":"2026-07-05T10:11:39.586266+00:00","updated_at":"2026-07-05T10:11:39.586266+00:00"}