{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XW7O5VTL4U2LSYSMKH3WHV2IVD","short_pith_number":"pith:XW7O5VTL","schema_version":"1.0","canonical_sha256":"bdbeeed66be534b9624c51f763d748a8df82ab77acaf590149d986b1f41bb6a3","source":{"kind":"arxiv","id":"2303.16686","version":1},"attestation_state":"computed","paper":{"title":"Communication Load Balancing via Efficient Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NI","authors_text":"Abhisek Konar, Di Wu, Gregory Dudek, Seowoo Jang, Steve Liu, Yi Tian Xu","submitted_at":"2023-03-22T22:23:23Z","abstract_excerpt":"Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward f"},"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":"2303.16686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2023-03-22T22:23:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e3c6c6940fbc51022289636092e74bd12e6b152baab4ebe5b4e15126a5c3c910","abstract_canon_sha256":"b182ef7ee3c961a4225514c406f6ca574c2b1187d78b13536e16e7148214e61b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:09.270817Z","signature_b64":"xt3DJyv/9YSUq7R8oDPKwey4QNNvT8xBH1o0MNzwAMt/BBbvfU1YpaInAnjn8Zryivp3aCVJVJTMazLWLv7tAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdbeeed66be534b9624c51f763d748a8df82ab77acaf590149d986b1f41bb6a3","last_reissued_at":"2026-07-05T05:56:09.270402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:09.270402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Communication Load Balancing via Efficient Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NI","authors_text":"Abhisek Konar, Di Wu, Gregory Dudek, Seowoo Jang, Steve Liu, Yi Tian Xu","submitted_at":"2023-03-22T22:23:23Z","abstract_excerpt":"Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16686","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/2303.16686/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":"2303.16686","created_at":"2026-07-05T05:56:09.270456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16686v1","created_at":"2026-07-05T05:56:09.270456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16686","created_at":"2026-07-05T05:56:09.270456+00:00"},{"alias_kind":"pith_short_12","alias_value":"XW7O5VTL4U2L","created_at":"2026-07-05T05:56:09.270456+00:00"},{"alias_kind":"pith_short_16","alias_value":"XW7O5VTL4U2LSYSM","created_at":"2026-07-05T05:56:09.270456+00:00"},{"alias_kind":"pith_short_8","alias_value":"XW7O5VTL","created_at":"2026-07-05T05:56:09.270456+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/XW7O5VTL4U2LSYSMKH3WHV2IVD","json":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD.json","graph_json":"https://pith.science/api/pith-number/XW7O5VTL4U2LSYSMKH3WHV2IVD/graph.json","events_json":"https://pith.science/api/pith-number/XW7O5VTL4U2LSYSMKH3WHV2IVD/events.json","paper":"https://pith.science/paper/XW7O5VTL"},"agent_actions":{"view_html":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD","download_json":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD.json","view_paper":"https://pith.science/paper/XW7O5VTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16686&json=true","fetch_graph":"https://pith.science/api/pith-number/XW7O5VTL4U2LSYSMKH3WHV2IVD/graph.json","fetch_events":"https://pith.science/api/pith-number/XW7O5VTL4U2LSYSMKH3WHV2IVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD/action/storage_attestation","attest_author":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD/action/author_attestation","sign_citation":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD/action/citation_signature","submit_replication":"https://pith.science/pith/XW7O5VTL4U2LSYSMKH3WHV2IVD/action/replication_record"}},"created_at":"2026-07-05T05:56:09.270456+00:00","updated_at":"2026-07-05T05:56:09.270456+00:00"}