{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7DDYGFSGOIV4IF5XRSD6QZN7NR","short_pith_number":"pith:7DDYGFSG","canonical_record":{"source":{"id":"2507.18333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T11:59:42Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"11e7685bee43d5eb79ddf756c58d69f5ca714d385559517550eab6466e613af8","abstract_canon_sha256":"ce40f032f49c9937d59ef4ca76739c38119d8e19ee7b3e1aad49d784d93e39b3"},"schema_version":"1.0"},"canonical_sha256":"f8c7831646722bc417b78c87e865bf6c4b0fa04ad17cb33b4118f2e487500ac6","source":{"kind":"arxiv","id":"2507.18333","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18333","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18333v1","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18333","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"7DDYGFSGOIV4","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"7DDYGFSGOIV4IF5X","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"7DDYGFSG","created_at":"2026-07-05T11:42:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7DDYGFSGOIV4IF5XRSD6QZN7NR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18333","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T11:59:42Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"11e7685bee43d5eb79ddf756c58d69f5ca714d385559517550eab6466e613af8","abstract_canon_sha256":"ce40f032f49c9937d59ef4ca76739c38119d8e19ee7b3e1aad49d784d93e39b3"},"schema_version":"1.0"},"canonical_sha256":"f8c7831646722bc417b78c87e865bf6c4b0fa04ad17cb33b4118f2e487500ac6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:46.256858Z","signature_b64":"mkk/o9rx2+pUJTScySvMvZ4h/IF/LbQPKmvqUsBU8gc8p9MckRhBAj8D/JhDf4ifLR6IlDqpk2JL0OBcuZATAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8c7831646722bc417b78c87e865bf6c4b0fa04ad17cb33b4118f2e487500ac6","last_reissued_at":"2026-07-05T11:42:46.256438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:46.256438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18333","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HW1odCxPLydSz9hRQw4nnkSKAC79ZNu/Dm65WjwR0CXs1JQeRMPzSfE/FFw2Al8o5M7rWbvWeTSAGREumGypBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:23:40.720720Z"},"content_sha256":"6078ebacdcb7fe01385670a0df36fa8c508dfec0e17bf836cd459d01a51f459e","schema_version":"1.0","event_id":"sha256:6078ebacdcb7fe01385670a0df36fa8c508dfec0e17bf836cd459d01a51f459e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7DDYGFSGOIV4IF5XRSD6QZN7NR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Remembering the Markov Property in Cooperative MARL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Amos Storkey, David Abel, Kale-ab Abebe Tessera, Leonard Hinckeldey, Riccardo Zamboni","submitted_at":"2025-07-24T11:59:42Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In practice, current model-free MARL algorithms use simple recurrent function approximators to address the challenge of reasoning about others using partial information. In this position paper, we argue that the empirical success of these methods is not due to effective Markov signal recovery, but rather to learning simple conventions that bypass environment observat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18333","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/2507.18333/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":"2026-07-05T11:42:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gKuKb5kYM6NhkVHMIAhMvkLrA6i4jCcIVkx5TY65EihyrJjvZc5YCHESy9rlilCc+fJryXCEYCwCGX8JORTeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:23:40.721172Z"},"content_sha256":"766ea8de9154ac0e9f5907f33b13ffcb8b5550d4c52c159ecebb12326cb757f2","schema_version":"1.0","event_id":"sha256:766ea8de9154ac0e9f5907f33b13ffcb8b5550d4c52c159ecebb12326cb757f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR/bundle.json","state_url":"https://pith.science/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR/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":"2026-08-17T23:23:40Z","links":{"resolver":"https://pith.science/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR","bundle":"https://pith.science/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR/bundle.json","state":"https://pith.science/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DDYGFSGOIV4IF5XRSD6QZN7NR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7DDYGFSGOIV4IF5XRSD6QZN7NR","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":"ce40f032f49c9937d59ef4ca76739c38119d8e19ee7b3e1aad49d784d93e39b3","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T11:59:42Z","title_canon_sha256":"11e7685bee43d5eb79ddf756c58d69f5ca714d385559517550eab6466e613af8"},"schema_version":"1.0","source":{"id":"2507.18333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18333","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18333v1","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18333","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"pith_short_12","alias_value":"7DDYGFSGOIV4","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"pith_short_16","alias_value":"7DDYGFSGOIV4IF5X","created_at":"2026-07-05T11:42:46Z"},{"alias_kind":"pith_short_8","alias_value":"7DDYGFSG","created_at":"2026-07-05T11:42:46Z"}],"graph_snapshots":[{"event_id":"sha256:766ea8de9154ac0e9f5907f33b13ffcb8b5550d4c52c159ecebb12326cb757f2","target":"graph","created_at":"2026-07-05T11:42:46Z","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/2507.18333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In practice, current model-free MARL algorithms use simple recurrent function approximators to address the challenge of reasoning about others using partial information. In this position paper, we argue that the empirical success of these methods is not due to effective Markov signal recovery, but rather to learning simple conventions that bypass environment observat","authors_text":"Amos Storkey, David Abel, Kale-ab Abebe Tessera, Leonard Hinckeldey, Riccardo Zamboni","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T11:59:42Z","title":"Remembering the Markov Property in Cooperative MARL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18333","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":"sha256:6078ebacdcb7fe01385670a0df36fa8c508dfec0e17bf836cd459d01a51f459e","target":"record","created_at":"2026-07-05T11:42:46Z","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":"ce40f032f49c9937d59ef4ca76739c38119d8e19ee7b3e1aad49d784d93e39b3","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-24T11:59:42Z","title_canon_sha256":"11e7685bee43d5eb79ddf756c58d69f5ca714d385559517550eab6466e613af8"},"schema_version":"1.0","source":{"id":"2507.18333","kind":"arxiv","version":1}},"canonical_sha256":"f8c7831646722bc417b78c87e865bf6c4b0fa04ad17cb33b4118f2e487500ac6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8c7831646722bc417b78c87e865bf6c4b0fa04ad17cb33b4118f2e487500ac6","first_computed_at":"2026-07-05T11:42:46.256438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:46.256438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mkk/o9rx2+pUJTScySvMvZ4h/IF/LbQPKmvqUsBU8gc8p9MckRhBAj8D/JhDf4ifLR6IlDqpk2JL0OBcuZATAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:46.256858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6078ebacdcb7fe01385670a0df36fa8c508dfec0e17bf836cd459d01a51f459e","sha256:766ea8de9154ac0e9f5907f33b13ffcb8b5550d4c52c159ecebb12326cb757f2"],"state_sha256":"d94699ae46df4348e6b748d743714987c9616dc1eca3acc87ee6fad5f1297173"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFo53E6SiyjTS3UgmjSdXxfjhBk6EiJX6xBv/Rc+GPJf+I+SBSIJKmbGmJwm9Nkt5kbsSxsEY91PXsCrwcatBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:23:40.723974Z","bundle_sha256":"3ec163618cd9af80b1e5ed8e72a6bf641b78161223b16f705747cac491086d90"}}