{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JMJVM5SSPMK7IIAKQDVBQMYCYT","short_pith_number":"pith:JMJVM5SS","schema_version":"1.0","canonical_sha256":"4b135676527b15f4200a80ea183302c4c005d261c9ca539a8b95e04a37e7f284","source":{"kind":"arxiv","id":"2606.30966","version":1},"attestation_state":"computed","paper":{"title":"HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO","cs.MA"],"primary_cat":"cs.AI","authors_text":"Arshia Rafieioskouei, Borzoo Bonakdarpour, Matthew Lucas, Tzu-Han Hsu","submitted_at":"2026-06-29T23:03:05Z","abstract_excerpt":"Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor; (2) expressiveness to specify objectives and constraints, and (3) the ability to define tactics to achieve objectives. However, these benefits remain largely unexplored in the context of Multi-Agent Reinforcement Learning (MARL). This paper introduces HyPOLE, a novel framework for MARL under partial observability, where learning is guided by the expressive power of the so-called hyperproperties and, in particular, the temporal logic HyperLTL. We"},"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":"2606.30966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T23:03:05Z","cross_cats_sorted":["cs.LO","cs.MA"],"title_canon_sha256":"7b5a53a5db87b27b7af083b95cd7fc491756001afd0d5138982731e03c4354d5","abstract_canon_sha256":"10727da90666c17d71a18437c34321122409d2aa16a0ae8740105773020cb63e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:22.954219Z","signature_b64":"vo+Vocfda+3KztPWHeO9Q8kkMoPkjUi+jy67NSIXMf4JvJlU6EEafGP8VkbCC+BgLVYEIABI4uUwrgzMJ2liCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b135676527b15f4200a80ea183302c4c005d261c9ca539a8b95e04a37e7f284","last_reissued_at":"2026-07-01T00:17:22.953817Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:22.953817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO","cs.MA"],"primary_cat":"cs.AI","authors_text":"Arshia Rafieioskouei, Borzoo Bonakdarpour, Matthew Lucas, Tzu-Han Hsu","submitted_at":"2026-06-29T23:03:05Z","abstract_excerpt":"Formal specification is a powerful tool to guide the learning process and provides significant advantages over reward shaping: (1) mathematical rigor; (2) expressiveness to specify objectives and constraints, and (3) the ability to define tactics to achieve objectives. However, these benefits remain largely unexplored in the context of Multi-Agent Reinforcement Learning (MARL). This paper introduces HyPOLE, a novel framework for MARL under partial observability, where learning is guided by the expressive power of the so-called hyperproperties and, in particular, the temporal logic HyperLTL. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30966","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/2606.30966/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":"2606.30966","created_at":"2026-07-01T00:17:22.953870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30966v1","created_at":"2026-07-01T00:17:22.953870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30966","created_at":"2026-07-01T00:17:22.953870+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMJVM5SSPMK7","created_at":"2026-07-01T00:17:22.953870+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMJVM5SSPMK7IIAK","created_at":"2026-07-01T00:17:22.953870+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMJVM5SS","created_at":"2026-07-01T00:17:22.953870+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/JMJVM5SSPMK7IIAKQDVBQMYCYT","json":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT.json","graph_json":"https://pith.science/api/pith-number/JMJVM5SSPMK7IIAKQDVBQMYCYT/graph.json","events_json":"https://pith.science/api/pith-number/JMJVM5SSPMK7IIAKQDVBQMYCYT/events.json","paper":"https://pith.science/paper/JMJVM5SS"},"agent_actions":{"view_html":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT","download_json":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT.json","view_paper":"https://pith.science/paper/JMJVM5SS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30966&json=true","fetch_graph":"https://pith.science/api/pith-number/JMJVM5SSPMK7IIAKQDVBQMYCYT/graph.json","fetch_events":"https://pith.science/api/pith-number/JMJVM5SSPMK7IIAKQDVBQMYCYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT/action/storage_attestation","attest_author":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT/action/author_attestation","sign_citation":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT/action/citation_signature","submit_replication":"https://pith.science/pith/JMJVM5SSPMK7IIAKQDVBQMYCYT/action/replication_record"}},"created_at":"2026-07-01T00:17:22.953870+00:00","updated_at":"2026-07-01T00:17:22.953870+00:00"}