{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VAF2JTV2XZ56CYYFT5ZHC4YOPJ","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":"fd6811b269eab6789ac12d79bd553ee6a199dc495f34e82a075cd660b9adc665","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T21:21:52Z","title_canon_sha256":"fe81af9897485e04ddc406293082784e4e70585c7b3efe81f89869f2bc3b44bb"},"schema_version":"1.0","source":{"id":"2607.28849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28849","created_at":"2026-08-03T01:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28849v1","created_at":"2026-08-03T01:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28849","created_at":"2026-08-03T01:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"VAF2JTV2XZ56","created_at":"2026-08-03T01:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"VAF2JTV2XZ56CYYF","created_at":"2026-08-03T01:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"VAF2JTV2","created_at":"2026-08-03T01:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:730aabfff49625e06a4f1ceb66b9b6fe15a39669cbcc498dbc3d61fc939c165e","target":"graph","created_at":"2026-08-03T01:17:12Z","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":[],"endpoint":"/pith/2607.28849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hierarchical task decomposition, and reinforcement learning from human feedback (RL-HF). Most of the bilevel RL algorithms are either not scalable because of using hypergradient with Hessian, or they suffer from high sample complexity because of using penalty-based approximation methods. In this work, we propose a hypergradient-based bilevel RL algorithm using the optimality of the Boltzmann policy for the entropy regular","authors_text":"Mudit Gaur, Naman Saxena, Vaneet Aggarwal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T21:21:52Z","title":"Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28849","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:b405d72b8d07b582e806c60ae8e322131963aba9b8641cf917de9512e255193c","target":"record","created_at":"2026-08-03T01:17:12Z","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":"fd6811b269eab6789ac12d79bd553ee6a199dc495f34e82a075cd660b9adc665","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T21:21:52Z","title_canon_sha256":"fe81af9897485e04ddc406293082784e4e70585c7b3efe81f89869f2bc3b44bb"},"schema_version":"1.0","source":{"id":"2607.28849","kind":"arxiv","version":1}},"canonical_sha256":"a80ba4cebabe7be163059f7271730e7a782668568bdd30ac91405ad970d76826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a80ba4cebabe7be163059f7271730e7a782668568bdd30ac91405ad970d76826","first_computed_at":"2026-08-03T01:17:12.368674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:17:12.368674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BKbtNxYFolkwny2WclQ8qUjigMebSx4WCh8TgG5c0nFIVqgFndvG/Vk6YXa1nhHRZISAkW6sGGugVgHMyYE1Bg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:17:12.370260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b405d72b8d07b582e806c60ae8e322131963aba9b8641cf917de9512e255193c","sha256:730aabfff49625e06a4f1ceb66b9b6fe15a39669cbcc498dbc3d61fc939c165e"],"state_sha256":"ef2645a54350e052fad17012ddf30502560d0e71163c580efb9b816e88036e34"}