{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O5LWE76IQOHNZUTKFX3NF22QLI","short_pith_number":"pith:O5LWE76I","canonical_record":{"source":{"id":"2404.03869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T03:02:57Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"ddb41523ce22db14db21838ee82b53e7a5912f3a189eada98c0a3ff3858ff272","abstract_canon_sha256":"c7e422eecc404326337f168bb5f8d6448cf96e0df39b9562b6c5155db1196930"},"schema_version":"1.0"},"canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","source":{"kind":"arxiv","id":"2404.03869","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03869","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03869v2","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03869","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"O5LWE76IQOHN","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"O5LWE76IQOHNZUTK","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"O5LWE76I","created_at":"2026-07-05T09:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O5LWE76IQOHNZUTKFX3NF22QLI","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T03:02:57Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"ddb41523ce22db14db21838ee82b53e7a5912f3a189eada98c0a3ff3858ff272","abstract_canon_sha256":"c7e422eecc404326337f168bb5f8d6448cf96e0df39b9562b6c5155db1196930"},"schema_version":"1.0"},"canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:31.654055Z","signature_b64":"NJIx2Ac4h0ia4uiaBUh9CVYmmynyTx0lXjyikubXzl6uDsy9mxk+adlXgR9CvBCTre8czAZTFxzrp1B3ApKJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","last_reissued_at":"2026-07-05T09:14:31.653521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:31.653521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03869","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":"2026-07-05T09:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yK9mRFfC8l6wAichOHS60GxpcOA3VET/tjdo4O/Oyeuk4qtJIKQcsQbmGU3D2ktWBmf3vBYgAbVkPl2yvGKuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:08:54.119595Z"},"content_sha256":"632a1b0f462c3cf5627fe5a7f2fdd00bb6720dbe5e0fbf4d393abd9fe208c51b","schema_version":"1.0","event_id":"sha256:632a1b0f462c3cf5627fe5a7f2fdd00bb6720dbe5e0fbf4d393abd9fe208c51b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O5LWE76IQOHNZUTKFX3NF22QLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Daming Shi, Junjie Yu, Wenhui Fan, Xudong Guo","submitted_at":"2024-04-05T03:02:57Z","abstract_excerpt":"The emergence of multi-agent reinforcement learning (MARL) is significantly transforming various fields like autonomous vehicle networks. However, real-world multi-agent systems typically contain multiple roles, and the scale of these systems dynamically fluctuates. Consequently, in order to achieve zero-shot scalable collaboration, it is essential that strategies for different roles can be updated flexibly according to the scales, which is still a challenge for current MARL frameworks. To address this, we propose a novel MARL framework named Scalable and Heterogeneous Proximal Policy Optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03869","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/2404.03869/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":"2026-07-05T09:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jBjaGUqktk55K/1ACVp3nMl5NJneG2tzF6hSOyEMhy7wUdXDlhiZcMnxN5n5XECFRKlVRN0JQU5RaXskoSJ5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:08:54.119995Z"},"content_sha256":"0c93455f6300ab017d4f28744790348f7b911771701378b31a52090a21e2fa5f","schema_version":"1.0","event_id":"sha256:0c93455f6300ab017d4f28744790348f7b911771701378b31a52090a21e2fa5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/bundle.json","state_url":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5LWE76IQOHNZUTKFX3NF22QLI/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":"2026-08-07T10:08:54Z","links":{"resolver":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI","bundle":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/bundle.json","state":"https://pith.science/pith/O5LWE76IQOHNZUTKFX3NF22QLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5LWE76IQOHNZUTKFX3NF22QLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O5LWE76IQOHNZUTKFX3NF22QLI","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":"c7e422eecc404326337f168bb5f8d6448cf96e0df39b9562b6c5155db1196930","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T03:02:57Z","title_canon_sha256":"ddb41523ce22db14db21838ee82b53e7a5912f3a189eada98c0a3ff3858ff272"},"schema_version":"1.0","source":{"id":"2404.03869","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03869","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03869v2","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03869","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"O5LWE76IQOHN","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"O5LWE76IQOHNZUTK","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"O5LWE76I","created_at":"2026-07-05T09:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:0c93455f6300ab017d4f28744790348f7b911771701378b31a52090a21e2fa5f","target":"graph","created_at":"2026-07-05T09:14:31Z","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/2404.03869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of multi-agent reinforcement learning (MARL) is significantly transforming various fields like autonomous vehicle networks. However, real-world multi-agent systems typically contain multiple roles, and the scale of these systems dynamically fluctuates. Consequently, in order to achieve zero-shot scalable collaboration, it is essential that strategies for different roles can be updated flexibly according to the scales, which is still a challenge for current MARL frameworks. To address this, we propose a novel MARL framework named Scalable and Heterogeneous Proximal Policy Optimiza","authors_text":"Daming Shi, Junjie Yu, Wenhui Fan, Xudong Guo","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T03:02:57Z","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03869","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":"sha256:632a1b0f462c3cf5627fe5a7f2fdd00bb6720dbe5e0fbf4d393abd9fe208c51b","target":"record","created_at":"2026-07-05T09:14:31Z","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":"c7e422eecc404326337f168bb5f8d6448cf96e0df39b9562b6c5155db1196930","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T03:02:57Z","title_canon_sha256":"ddb41523ce22db14db21838ee82b53e7a5912f3a189eada98c0a3ff3858ff272"},"schema_version":"1.0","source":{"id":"2404.03869","kind":"arxiv","version":2}},"canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7757627fc8838edcd26a2df6d2eb505a175d22d2d313c7052d1d06b4a9400ee9","first_computed_at":"2026-07-05T09:14:31.653521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:31.653521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NJIx2Ac4h0ia4uiaBUh9CVYmmynyTx0lXjyikubXzl6uDsy9mxk+adlXgR9CvBCTre8czAZTFxzrp1B3ApKJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:31.654055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03869","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:632a1b0f462c3cf5627fe5a7f2fdd00bb6720dbe5e0fbf4d393abd9fe208c51b","sha256:0c93455f6300ab017d4f28744790348f7b911771701378b31a52090a21e2fa5f"],"state_sha256":"6e362f421b82ad6ee3220f3ab2660885ba54518f0c57cc739b8f250fd679e6ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"243b0OQKAT1hcXD7+9+CVP5xsd6Ga/jWXYY2X0MHYw6W+5LXfsnbgXLsIE0g2ytI1b1X8BSoBww1uuIUQGdCCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:08:54.122838Z","bundle_sha256":"cff3be75537584db490d33ecb97a794f7bb8df65df64659427eda1d68c340bb8"}}