{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SJC6ZTW7KGLPM227Q457FSZTGO","short_pith_number":"pith:SJC6ZTW7","canonical_record":{"source":{"id":"2507.23604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T14:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"e28bf4bc90cca9d826a740a8b26e8e5d40926a5caad3980f50077a10d3c8c9c2","abstract_canon_sha256":"9e2c7b1ccd794a8ba7384b0054a6462369c530a58369fc911b936ed594b2fef8"},"schema_version":"1.0"},"canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","source":{"kind":"arxiv","id":"2507.23604","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23604","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23604v2","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23604","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"SJC6ZTW7KGLP","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"SJC6ZTW7KGLPM227","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"SJC6ZTW7","created_at":"2026-07-01T01:17:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SJC6ZTW7KGLPM227Q457FSZTGO","target":"record","payload":{"canonical_record":{"source":{"id":"2507.23604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T14:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"e28bf4bc90cca9d826a740a8b26e8e5d40926a5caad3980f50077a10d3c8c9c2","abstract_canon_sha256":"9e2c7b1ccd794a8ba7384b0054a6462369c530a58369fc911b936ed594b2fef8"},"schema_version":"1.0"},"canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:40.672663Z","signature_b64":"8fN6HXIk/5owBduyVOI+Tm8pw81aRTwQR/xvNnaBnvr9y4mQCWkgXW962JsRVSRhLN5EYU97MSMz4Q7CtkPBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","last_reissued_at":"2026-07-01T01:17:40.672061Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:40.672061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.23604","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"optL3FCks2n0gwuCHPkK7AQcyZp2ItItyPmR6RnZ0MpujHw9BcwkTdyvkskNItf6zldjP11Kdu1J1U1T0nP5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:41:48.326249Z"},"content_sha256":"ddceb8ec6051b3747a08888918186722e0673a52fa2b957896853e3509a71541","schema_version":"1.0","event_id":"sha256:ddceb8ec6051b3747a08888918186722e0673a52fa2b957896853e3509a71541"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SJC6ZTW7KGLPM227Q457FSZTGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Cini, Cesare Alippi, Tommaso Marzi","submitted_at":"2025-07-31T14:42:12Z","abstract_excerpt":"Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing mechanisms that facilitate coordination and high-level planning. Specifically, coordination and temporal abstraction can be achieved through communication (e.g., message passing) and Hierarchical Reinforcement Learning (HRL) approaches to decision-making. However, optimization issues limit the applicability of hierarchical policies to multi-agent systems. As such, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23604","kind":"arxiv","version":2},"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/2507.23604/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-01T01:17:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XvvybloS0lRFvAchTB/PGBzGUD4MMLUDUFebz1hAPOzTrYTcW5y4tP2QqXKP+jeAxgO1/gxU7mZ34tBqY0POAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:41:48.326650Z"},"content_sha256":"215601b9cd1e844285949b52dae02873b3e3a13471143e48783676ecdf3bc2ee","schema_version":"1.0","event_id":"sha256:215601b9cd1e844285949b52dae02873b3e3a13471143e48783676ecdf3bc2ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/bundle.json","state_url":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJC6ZTW7KGLPM227Q457FSZTGO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T07:41:48Z","links":{"resolver":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO","bundle":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/bundle.json","state":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJC6ZTW7KGLPM227Q457FSZTGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJC6ZTW7KGLPM227Q457FSZTGO","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":"9e2c7b1ccd794a8ba7384b0054a6462369c530a58369fc911b936ed594b2fef8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T14:42:12Z","title_canon_sha256":"e28bf4bc90cca9d826a740a8b26e8e5d40926a5caad3980f50077a10d3c8c9c2"},"schema_version":"1.0","source":{"id":"2507.23604","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23604","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23604v2","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23604","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"pith_short_12","alias_value":"SJC6ZTW7KGLP","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"pith_short_16","alias_value":"SJC6ZTW7KGLPM227","created_at":"2026-07-01T01:17:40Z"},{"alias_kind":"pith_short_8","alias_value":"SJC6ZTW7","created_at":"2026-07-01T01:17:40Z"}],"graph_snapshots":[{"event_id":"sha256:215601b9cd1e844285949b52dae02873b3e3a13471143e48783676ecdf3bc2ee","target":"graph","created_at":"2026-07-01T01:17:40Z","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/2507.23604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing mechanisms that facilitate coordination and high-level planning. Specifically, coordination and temporal abstraction can be achieved through communication (e.g., message passing) and Hierarchical Reinforcement Learning (HRL) approaches to decision-making. However, optimization issues limit the applicability of hierarchical policies to multi-agent systems. As such, th","authors_text":"Andrea Cini, Cesare Alippi, Tommaso Marzi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T14:42:12Z","title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23604","kind":"arxiv","version":2},"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:ddceb8ec6051b3747a08888918186722e0673a52fa2b957896853e3509a71541","target":"record","created_at":"2026-07-01T01:17:40Z","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":"9e2c7b1ccd794a8ba7384b0054a6462369c530a58369fc911b936ed594b2fef8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T14:42:12Z","title_canon_sha256":"e28bf4bc90cca9d826a740a8b26e8e5d40926a5caad3980f50077a10d3c8c9c2"},"schema_version":"1.0","source":{"id":"2507.23604","kind":"arxiv","version":2}},"canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","first_computed_at":"2026-07-01T01:17:40.672061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:40.672061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8fN6HXIk/5owBduyVOI+Tm8pw81aRTwQR/xvNnaBnvr9y4mQCWkgXW962JsRVSRhLN5EYU97MSMz4Q7CtkPBDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:40.672663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23604","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddceb8ec6051b3747a08888918186722e0673a52fa2b957896853e3509a71541","sha256:215601b9cd1e844285949b52dae02873b3e3a13471143e48783676ecdf3bc2ee"],"state_sha256":"2d8d2440c8ef127701ec8e64e43aa0e843758365b0726fcaad315cb6696e5fc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xk7iPGzwkHppf0bux4ZIYDKwC8UK7ggeE0gSxA3L1qAdP3/cCTnW1Jnz3vHFTcYxRwxdWBp0NXEVAHSUPE+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T07:41:48.329121Z","bundle_sha256":"5db30dcb1475c11e7e8f7647d47ca95788c0bb51f27ad2ece4d167a66edd0287"}}