{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQS2B4XDKQ3X7U4Q5KWZWEGI5Z","short_pith_number":"pith:EQS2B4XD","schema_version":"1.0","canonical_sha256":"2425a0f2e354377fd390eaad9b10c8ee65f8adf0d69ea31df01ca4a840d995c8","source":{"kind":"arxiv","id":"2603.14867","version":4},"attestation_state":"computed","paper":{"title":"Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Mikoto Kudo, Takumi Tanabe, Youhei Akimoto","submitted_at":"2026-03-16T06:11:00Z","abstract_excerpt":"Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's s"},"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":"2603.14867","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-16T06:11:00Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA"],"title_canon_sha256":"a67720820a03539b858310649317539068589d7f68a6a47c41b45ee6f48965e7","abstract_canon_sha256":"37607dc17d94dfa0e69ea1441db8a72d1e3c6e6ddd484f045613a9b515c97014"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:33.256462Z","signature_b64":"urFIndjhWrSDyuQPAKQLryGiTHwnd7g+X5hmUI4oNlaV8QlBRyeTuOanjAkFDffEMVy4bOjCvXxrmY+rDXSsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2425a0f2e354377fd390eaad9b10c8ee65f8adf0d69ea31df01ca4a840d995c8","last_reissued_at":"2026-06-11T01:09:33.255419Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:33.255419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Akifumi Wachi, Mikoto Kudo, Takumi Tanabe, Youhei Akimoto","submitted_at":"2026-03-16T06:11:00Z","abstract_excerpt":"Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14867","kind":"arxiv","version":4},"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/2603.14867/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":"2603.14867","created_at":"2026-06-11T01:09:33.255573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14867v4","created_at":"2026-06-11T01:09:33.255573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14867","created_at":"2026-06-11T01:09:33.255573+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQS2B4XDKQ3X","created_at":"2026-06-11T01:09:33.255573+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQS2B4XDKQ3X7U4Q","created_at":"2026-06-11T01:09:33.255573+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQS2B4XD","created_at":"2026-06-11T01:09:33.255573+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/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z","json":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z.json","graph_json":"https://pith.science/api/pith-number/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/graph.json","events_json":"https://pith.science/api/pith-number/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/events.json","paper":"https://pith.science/paper/EQS2B4XD"},"agent_actions":{"view_html":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z","download_json":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z.json","view_paper":"https://pith.science/paper/EQS2B4XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14867&json=true","fetch_graph":"https://pith.science/api/pith-number/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/action/storage_attestation","attest_author":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/action/author_attestation","sign_citation":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/action/citation_signature","submit_replication":"https://pith.science/pith/EQS2B4XDKQ3X7U4Q5KWZWEGI5Z/action/replication_record"}},"created_at":"2026-06-11T01:09:33.255573+00:00","updated_at":"2026-06-11T01:09:33.255573+00:00"}