{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T3QDGSFLV63G2LOQXBWKAWCFGD","short_pith_number":"pith:T3QDGSFL","canonical_record":{"source":{"id":"2411.19639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-29T11:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"7fd9d6b906426c39bbb21f7344a74f293d0fc2e92011082f78c6b1f188b4ebb4","abstract_canon_sha256":"3c51e6aa4591517ffb3a871d244ac5a74be6cbec7a7b5d0def7be1a6adeb56da"},"schema_version":"1.0"},"canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","source":{"kind":"arxiv","id":"2411.19639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19639","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19639v1","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19639","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"T3QDGSFLV63G","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"T3QDGSFLV63G2LOQ","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"T3QDGSFL","created_at":"2026-07-05T10:01:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T3QDGSFLV63G2LOQXBWKAWCFGD","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-29T11:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"7fd9d6b906426c39bbb21f7344a74f293d0fc2e92011082f78c6b1f188b4ebb4","abstract_canon_sha256":"3c51e6aa4591517ffb3a871d244ac5a74be6cbec7a7b5d0def7be1a6adeb56da"},"schema_version":"1.0"},"canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:58.263962Z","signature_b64":"jGXHPI71Q68zeaK+PSJdwE5twc1lrDzx0b10ADqwVMy9I3R97xT4h15WZXkXNrCojR6jTTwnw2+7DY4XAUetBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","last_reissued_at":"2026-07-05T10:01:58.263482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:58.263482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19639","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":"2026-07-05T10:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUqQAgAAepobwZqtGm0JbzGSr4n/YcXsUMgzAFTWLPyLMs4DKTHg0O6LkpmqMl6Cp3TMeqHXEc5yPqt7Wi71BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:33:23.791743Z"},"content_sha256":"ce1ac787ee15f726768dc00ce41a922ea98a5c4fb05833d4922b6e21b592f9cc","schema_version":"1.0","event_id":"sha256:ce1ac787ee15f726768dc00ce41a922ea98a5c4fb05833d4922b6e21b592f9cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T3QDGSFLV63G2LOQXBWKAWCFGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RMIO: A Model-Based MARL Framework for Scenarios with Observation Loss in Some Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Meiqin Liu, Ronghao Zheng, Senlin Zhang, Shanling Dong, Zifeng Shi","submitted_at":"2024-11-29T11:45:21Z","abstract_excerpt":"In recent years, model-based reinforcement learning (MBRL) has emerged as a solution to address sample complexity in multi-agent reinforcement learning (MARL) by modeling agent-environment dynamics to improve sample efficiency. However, most MBRL methods assume complete and continuous observations from each agent during the inference stage, which can be overly idealistic in practical applications. A novel model-based MARL approach called RMIO is introduced to address this limitation, specifically designed for scenarios where observation is lost in some agent. RMIO leverages the world model to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19639","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/2411.19639/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":"2026-07-05T10:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3AJYnYPIJeIfXbMkK4joawcttN/Ht3bkVNzdZ4WhMlfs1H5Bp7TX1H+2y9dYqp3GfEy2Vo/DoKrog9hxHAa9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:33:23.792263Z"},"content_sha256":"08697f24d7ae8432c873a2a01256989db213242e38b2e98e9e6a532388d9e87b","schema_version":"1.0","event_id":"sha256:08697f24d7ae8432c873a2a01256989db213242e38b2e98e9e6a532388d9e87b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/bundle.json","state_url":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/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":"2026-08-14T23:33:23Z","links":{"resolver":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD","bundle":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/bundle.json","state":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T3QDGSFLV63G2LOQXBWKAWCFGD","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":"3c51e6aa4591517ffb3a871d244ac5a74be6cbec7a7b5d0def7be1a6adeb56da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-29T11:45:21Z","title_canon_sha256":"7fd9d6b906426c39bbb21f7344a74f293d0fc2e92011082f78c6b1f188b4ebb4"},"schema_version":"1.0","source":{"id":"2411.19639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19639","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19639v1","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19639","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"T3QDGSFLV63G","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"T3QDGSFLV63G2LOQ","created_at":"2026-07-05T10:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"T3QDGSFL","created_at":"2026-07-05T10:01:58Z"}],"graph_snapshots":[{"event_id":"sha256:08697f24d7ae8432c873a2a01256989db213242e38b2e98e9e6a532388d9e87b","target":"graph","created_at":"2026-07-05T10:01:58Z","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/2411.19639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, model-based reinforcement learning (MBRL) has emerged as a solution to address sample complexity in multi-agent reinforcement learning (MARL) by modeling agent-environment dynamics to improve sample efficiency. However, most MBRL methods assume complete and continuous observations from each agent during the inference stage, which can be overly idealistic in practical applications. A novel model-based MARL approach called RMIO is introduced to address this limitation, specifically designed for scenarios where observation is lost in some agent. RMIO leverages the world model to ","authors_text":"Meiqin Liu, Ronghao Zheng, Senlin Zhang, Shanling Dong, Zifeng Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-29T11:45:21Z","title":"RMIO: A Model-Based MARL Framework for Scenarios with Observation Loss in Some Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19639","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:ce1ac787ee15f726768dc00ce41a922ea98a5c4fb05833d4922b6e21b592f9cc","target":"record","created_at":"2026-07-05T10:01:58Z","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":"3c51e6aa4591517ffb3a871d244ac5a74be6cbec7a7b5d0def7be1a6adeb56da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-29T11:45:21Z","title_canon_sha256":"7fd9d6b906426c39bbb21f7344a74f293d0fc2e92011082f78c6b1f188b4ebb4"},"schema_version":"1.0","source":{"id":"2411.19639","kind":"arxiv","version":1}},"canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","first_computed_at":"2026-07-05T10:01:58.263482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:58.263482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jGXHPI71Q68zeaK+PSJdwE5twc1lrDzx0b10ADqwVMy9I3R97xT4h15WZXkXNrCojR6jTTwnw2+7DY4XAUetBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:58.263962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce1ac787ee15f726768dc00ce41a922ea98a5c4fb05833d4922b6e21b592f9cc","sha256:08697f24d7ae8432c873a2a01256989db213242e38b2e98e9e6a532388d9e87b"],"state_sha256":"83db21e9112f4aa3d9abcf377f90893a985196cbfdbfc1469429457f8d453962"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ey/B4IKVvXjf9hWbU8nkqarf3i/8TeUAGj4thvG3HMVSLVf+A2vjDUo5ST42cinRjLvmXZfn06G+8S24I/cCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:33:23.798551Z","bundle_sha256":"d7347e0d872db995882e9ce962f53db543d79f49e261bd693779acc0e2398f3a"}}