{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:H5SJH2KDI5C7I2RVU7SRCPD4X6","short_pith_number":"pith:H5SJH2KD","canonical_record":{"source":{"id":"2205.15023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T08:35:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"594c97f3a9edfe5dab6c5accdfd54c9754a0b83a3335d506f95711e373ea151d","abstract_canon_sha256":"c5455593293e5f6fa51630f06c24f6557b5c538aa1864ab834b4cf5507a13413"},"schema_version":"1.0"},"canonical_sha256":"3f6493e9434745f46a35a7e5113c7cbfb300f8eb4f73700542a78d44c312e745","source":{"kind":"arxiv","id":"2205.15023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15023","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15023v1","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15023","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"H5SJH2KDI5C7","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"H5SJH2KDI5C7I2RV","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"H5SJH2KD","created_at":"2026-07-05T04:27:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:H5SJH2KDI5C7I2RVU7SRCPD4X6","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T08:35:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"594c97f3a9edfe5dab6c5accdfd54c9754a0b83a3335d506f95711e373ea151d","abstract_canon_sha256":"c5455593293e5f6fa51630f06c24f6557b5c538aa1864ab834b4cf5507a13413"},"schema_version":"1.0"},"canonical_sha256":"3f6493e9434745f46a35a7e5113c7cbfb300f8eb4f73700542a78d44c312e745","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:23.571441Z","signature_b64":"s+edXhY9Khu0W8sWERgD/ri5xDksAGOJlbBUcz+3VYlSWhoGsyFW+MyV4/Z6CgjzQzavKL5LEHlMwFCOyvdEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f6493e9434745f46a35a7e5113c7cbfb300f8eb4f73700542a78d44c312e745","last_reissued_at":"2026-07-05T04:27:23.570969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:23.570969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15023","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":"2026-07-05T04:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ov+IgR/0zXsZ4zwXPxfwbS6RWKbCxYDNbPYUunZKXZuaQ3rlhUjLL/uUApjZTTSrWCPGKeGrBZZM0y+ukhTxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:49:42.242716Z"},"content_sha256":"f4305c134baab9ee5bd6b053b3ad03a711aa24bbd2d4c23b7980cc7b512563a7","schema_version":"1.0","event_id":"sha256:f4305c134baab9ee5bd6b053b3ad03a711aa24bbd2d4c23b7980cc7b512563a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:H5SJH2KDI5C7I2RVU7SRCPD4X6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Multi-Agent Model-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksei Shpilman, Vladimir Egorov","submitted_at":"2022-05-25T08:35:00Z","abstract_excerpt":"Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a dominant approach for both cooperative and mixed environments due to its capability to efficiently train decentralized policies. While in mixed environments full autonomy of the agents can be a desirable outcome, cooperative environments allow agents to share information to facilitate coordination. Approaches that leverage this technique are usually referred as communication methods, as full autonomy of agents is compromised "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15023","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/2205.15023/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":"2026-07-05T04:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IJg6hXe7Gxx0j460GzpfghSpPAFJAaQNwzHZZtv06gHdBJIYgKgyDTMDTNTsKDZE775aE95BiSBYF/E09kzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:49:42.243758Z"},"content_sha256":"4f21a0009c644a03c82faa436b315cb770dfbe08986c3f0db5a560a0b3cdbe30","schema_version":"1.0","event_id":"sha256:4f21a0009c644a03c82faa436b315cb770dfbe08986c3f0db5a560a0b3cdbe30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6/bundle.json","state_url":"https://pith.science/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6/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":"2026-08-12T03:49:42Z","links":{"resolver":"https://pith.science/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6","bundle":"https://pith.science/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6/bundle.json","state":"https://pith.science/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H5SJH2KDI5C7I2RVU7SRCPD4X6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:H5SJH2KDI5C7I2RVU7SRCPD4X6","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":"c5455593293e5f6fa51630f06c24f6557b5c538aa1864ab834b4cf5507a13413","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T08:35:00Z","title_canon_sha256":"594c97f3a9edfe5dab6c5accdfd54c9754a0b83a3335d506f95711e373ea151d"},"schema_version":"1.0","source":{"id":"2205.15023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15023","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15023v1","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15023","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"H5SJH2KDI5C7","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"H5SJH2KDI5C7I2RV","created_at":"2026-07-05T04:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"H5SJH2KD","created_at":"2026-07-05T04:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:4f21a0009c644a03c82faa436b315cb770dfbe08986c3f0db5a560a0b3cdbe30","target":"graph","created_at":"2026-07-05T04:27:23Z","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/2205.15023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a dominant approach for both cooperative and mixed environments due to its capability to efficiently train decentralized policies. While in mixed environments full autonomy of the agents can be a desirable outcome, cooperative environments allow agents to share information to facilitate coordination. Approaches that leverage this technique are usually referred as communication methods, as full autonomy of agents is compromised ","authors_text":"Aleksei Shpilman, Vladimir Egorov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T08:35:00Z","title":"Scalable Multi-Agent Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15023","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:f4305c134baab9ee5bd6b053b3ad03a711aa24bbd2d4c23b7980cc7b512563a7","target":"record","created_at":"2026-07-05T04:27:23Z","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":"c5455593293e5f6fa51630f06c24f6557b5c538aa1864ab834b4cf5507a13413","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-25T08:35:00Z","title_canon_sha256":"594c97f3a9edfe5dab6c5accdfd54c9754a0b83a3335d506f95711e373ea151d"},"schema_version":"1.0","source":{"id":"2205.15023","kind":"arxiv","version":1}},"canonical_sha256":"3f6493e9434745f46a35a7e5113c7cbfb300f8eb4f73700542a78d44c312e745","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f6493e9434745f46a35a7e5113c7cbfb300f8eb4f73700542a78d44c312e745","first_computed_at":"2026-07-05T04:27:23.570969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:23.570969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s+edXhY9Khu0W8sWERgD/ri5xDksAGOJlbBUcz+3VYlSWhoGsyFW+MyV4/Z6CgjzQzavKL5LEHlMwFCOyvdEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:23.571441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4305c134baab9ee5bd6b053b3ad03a711aa24bbd2d4c23b7980cc7b512563a7","sha256:4f21a0009c644a03c82faa436b315cb770dfbe08986c3f0db5a560a0b3cdbe30"],"state_sha256":"26aa4e66d181e89d96396e9be238137fb3921b49e6aef8eac15c1983cce83713"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sVvSLCHLeY/loi2Lq2PnQrIwX2keLafIW/yg50u90xWLo8tMtQkpH3tv8CgG4xh6IcqKWwvBGv8Douo3MptjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T03:49:42.250538Z","bundle_sha256":"1b8f1ccc826c4b6502dfb2d79378966b810e5b1d523c7cc1896edd6fe5324818"}}