{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZJOEMNR2BBE5J43NPEHS4KG3H2","short_pith_number":"pith:ZJOEMNR2","canonical_record":{"source":{"id":"2505.05262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T14:07:20Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"930f339c68e08613836f160b9409cd3fbad76d0eeb473bd668755281d2fac999","abstract_canon_sha256":"5b547c5b9647ea257f8eb69a0e31eb271ecf69a177f9f9f67e9ff8c0aea9b5eb"},"schema_version":"1.0"},"canonical_sha256":"ca5c46363a0849d4f36d790f2e28db3e91e491fb6654a5b7ed46a15bfa5250c5","source":{"kind":"arxiv","id":"2505.05262","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05262","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05262v2","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05262","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZJOEMNR2BBE5","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZJOEMNR2BBE5J43N","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZJOEMNR2","created_at":"2026-07-05T11:20:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZJOEMNR2BBE5J43NPEHS4KG3H2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.05262","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T14:07:20Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"930f339c68e08613836f160b9409cd3fbad76d0eeb473bd668755281d2fac999","abstract_canon_sha256":"5b547c5b9647ea257f8eb69a0e31eb271ecf69a177f9f9f67e9ff8c0aea9b5eb"},"schema_version":"1.0"},"canonical_sha256":"ca5c46363a0849d4f36d790f2e28db3e91e491fb6654a5b7ed46a15bfa5250c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:53.940941Z","signature_b64":"at9rBZOYzc+JsNFk7CSe1nYn0kE1g+oDbI2JqL2c/iKa+OzU9MECz46pxUv5kKij+OBtp67EE5eXZInwzGR2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca5c46363a0849d4f36d790f2e28db3e91e491fb6654a5b7ed46a15bfa5250c5","last_reissued_at":"2026-07-05T11:20:53.940462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:53.940462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.05262","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":"2026-07-05T11:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpg/hhBUFIjSmrCMx3A5JXd/Gd498QuZhLNgCEMHuLaqoO+YKex0z1dts0tT/CaWSo1CXCD1cszDr1Sdqb+pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:11:37.008469Z"},"content_sha256":"c1be67d9e37cc8bf8dc5fab6db0b7839d83f9fcc796c865f70337248d92a223b","schema_version":"1.0","event_id":"sha256:c1be67d9e37cc8bf8dc5fab6db0b7839d83f9fcc796c865f70337248d92a223b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZJOEMNR2BBE5J43NPEHS4KG3H2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Andreas Kontogiannis, George Vouros, Giorgos Stamou, Konstantinos Papathanasiou, Michael M. Zavlanos, Yi Shen","submitted_at":"2025-05-08T14:07:20Z","abstract_excerpt":"Learning to cooperate in distributed partially observable environments with no communication abilities poses significant challenges for multi-agent deep reinforcement learning (MARL). This paper addresses key concerns in this domain, focusing on inferring state representations from individual agent observations and leveraging these representations to enhance agents' exploration and collaborative task execution policies. To this end, we propose a novel state modelling framework for cooperative MARL, where agents infer meaningful belief representations of the non-observable state, with respect t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05262","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/2505.05262/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":"2026-07-05T11:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3G0jpsrh62f/aSNWfahIg3JyavsXsM5Nla7uF7MUMMzgZ9lablQBZzbyzOys6f01ttw8EnR37tqMcZAVenFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:11:37.009093Z"},"content_sha256":"4cbb7b8bdc8ad2412024ed6a635f6fc3d405609c1f5d758f553a471af02948c4","schema_version":"1.0","event_id":"sha256:4cbb7b8bdc8ad2412024ed6a635f6fc3d405609c1f5d758f553a471af02948c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2/bundle.json","state_url":"https://pith.science/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2/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":"2026-08-06T19:11:37Z","links":{"resolver":"https://pith.science/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2","bundle":"https://pith.science/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2/bundle.json","state":"https://pith.science/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJOEMNR2BBE5J43NPEHS4KG3H2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJOEMNR2BBE5J43NPEHS4KG3H2","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":"5b547c5b9647ea257f8eb69a0e31eb271ecf69a177f9f9f67e9ff8c0aea9b5eb","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T14:07:20Z","title_canon_sha256":"930f339c68e08613836f160b9409cd3fbad76d0eeb473bd668755281d2fac999"},"schema_version":"1.0","source":{"id":"2505.05262","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05262","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05262v2","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05262","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZJOEMNR2BBE5","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZJOEMNR2BBE5J43N","created_at":"2026-07-05T11:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZJOEMNR2","created_at":"2026-07-05T11:20:53Z"}],"graph_snapshots":[{"event_id":"sha256:4cbb7b8bdc8ad2412024ed6a635f6fc3d405609c1f5d758f553a471af02948c4","target":"graph","created_at":"2026-07-05T11:20:53Z","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/2505.05262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to cooperate in distributed partially observable environments with no communication abilities poses significant challenges for multi-agent deep reinforcement learning (MARL). This paper addresses key concerns in this domain, focusing on inferring state representations from individual agent observations and leveraging these representations to enhance agents' exploration and collaborative task execution policies. To this end, we propose a novel state modelling framework for cooperative MARL, where agents infer meaningful belief representations of the non-observable state, with respect t","authors_text":"Andreas Kontogiannis, George Vouros, Giorgos Stamou, Konstantinos Papathanasiou, Michael M. Zavlanos, Yi Shen","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T14:07:20Z","title":"Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05262","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:c1be67d9e37cc8bf8dc5fab6db0b7839d83f9fcc796c865f70337248d92a223b","target":"record","created_at":"2026-07-05T11:20:53Z","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":"5b547c5b9647ea257f8eb69a0e31eb271ecf69a177f9f9f67e9ff8c0aea9b5eb","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T14:07:20Z","title_canon_sha256":"930f339c68e08613836f160b9409cd3fbad76d0eeb473bd668755281d2fac999"},"schema_version":"1.0","source":{"id":"2505.05262","kind":"arxiv","version":2}},"canonical_sha256":"ca5c46363a0849d4f36d790f2e28db3e91e491fb6654a5b7ed46a15bfa5250c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca5c46363a0849d4f36d790f2e28db3e91e491fb6654a5b7ed46a15bfa5250c5","first_computed_at":"2026-07-05T11:20:53.940462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:53.940462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"at9rBZOYzc+JsNFk7CSe1nYn0kE1g+oDbI2JqL2c/iKa+OzU9MECz46pxUv5kKij+OBtp67EE5eXZInwzGR2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:53.940941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05262","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1be67d9e37cc8bf8dc5fab6db0b7839d83f9fcc796c865f70337248d92a223b","sha256:4cbb7b8bdc8ad2412024ed6a635f6fc3d405609c1f5d758f553a471af02948c4"],"state_sha256":"822b5966de42fc36280179c45a01ae9bb07ec95b7be8e4333456c447d70dfa7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCXDwAosQnz9bFiOO0Ks+mCegzeE3MjdRclNKUgKFjMgHLsHoCnpVO7ufU/2h9OF4IoUB3zyYnlCxhbGtEtoAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:11:37.015748Z","bundle_sha256":"012ccfb0347969d515a9b84cf55bef21b4a5f420ac1461af1f4b6d39937c1c5d"}}