{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ARVVR7Z37FUZ7W4YSKXRXWUPNG","short_pith_number":"pith:ARVVR7Z3","canonical_record":{"source":{"id":"2501.11818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T01:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"1dedfedba28d340ade2dec8e1b16d87831a7a07223ba37f6a8072fd3d00f5599","abstract_canon_sha256":"7e08799c2911291b2bcc30d43fd01d022de577116b4a0003c1510d207992c79f"},"schema_version":"1.0"},"canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","source":{"kind":"arxiv","id":"2501.11818","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11818","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11818v2","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11818","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"ARVVR7Z37FUZ","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"ARVVR7Z37FUZ7W4Y","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"ARVVR7Z3","created_at":"2026-07-05T10:14:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ARVVR7Z37FUZ7W4YSKXRXWUPNG","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T01:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"1dedfedba28d340ade2dec8e1b16d87831a7a07223ba37f6a8072fd3d00f5599","abstract_canon_sha256":"7e08799c2911291b2bcc30d43fd01d022de577116b4a0003c1510d207992c79f"},"schema_version":"1.0"},"canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:49.977937Z","signature_b64":"I2fqx8keaExpEl6rHDk6md9QgM75TYlEQm+9E85KOniYZFNbJX9h021le3qYSRtRrZScIBHcn3jYhN5M6uv0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","last_reissued_at":"2026-07-05T10:14:49.977385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:49.977385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11818","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":"2026-07-05T10:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsv5cQa6UOQQul8h9TZMl5IGdDHPqMFq3buC5JnOMaKfHeJ5bfVlmBbrRFeoJB6MINjyhmeQaOGX5qoIVeWsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:30:03.710500Z"},"content_sha256":"bb2856f51be58311a5246f614a3bee1e419789bb474cf475a77dc6dc9b221f5f","schema_version":"1.0","event_id":"sha256:bb2856f51be58311a5246f614a3bee1e419789bb474cf475a77dc6dc9b221f5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ARVVR7Z37FUZ7W4YSKXRXWUPNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Group-Agent Reinforcement Learning with Heterogeneous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiyue Wu, Tingting Mu, Xiao-Jun Zeng","submitted_at":"2025-01-21T01:56:33Z","abstract_excerpt":"Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11818","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/2501.11818/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":"2026-07-05T10:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwSNfQTiecF8ifUp5eqCD00fvpIoCZtMXt1VvPXz6o7Cy2k1Euoo+HSEZaUIVSqh2zgcpyE7Bi0057Rk1PWeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T23:30:03.711007Z"},"content_sha256":"76f91070aa824744fcb6568f4f67810301e1b6052b4c64300cdb1ab92f9ff4ff","schema_version":"1.0","event_id":"sha256:76f91070aa824744fcb6568f4f67810301e1b6052b4c64300cdb1ab92f9ff4ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/bundle.json","state_url":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/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":"2026-08-12T23:30:03Z","links":{"resolver":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG","bundle":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/bundle.json","state":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ARVVR7Z37FUZ7W4YSKXRXWUPNG","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":"7e08799c2911291b2bcc30d43fd01d022de577116b4a0003c1510d207992c79f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T01:56:33Z","title_canon_sha256":"1dedfedba28d340ade2dec8e1b16d87831a7a07223ba37f6a8072fd3d00f5599"},"schema_version":"1.0","source":{"id":"2501.11818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11818","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11818v2","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11818","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"ARVVR7Z37FUZ","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"ARVVR7Z37FUZ7W4Y","created_at":"2026-07-05T10:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"ARVVR7Z3","created_at":"2026-07-05T10:14:49Z"}],"graph_snapshots":[{"event_id":"sha256:76f91070aa824744fcb6568f4f67810301e1b6052b4c64300cdb1ab92f9ff4ff","target":"graph","created_at":"2026-07-05T10:14:49Z","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/2501.11818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function","authors_text":"Kaiyue Wu, Tingting Mu, Xiao-Jun Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T01:56:33Z","title":"Group-Agent Reinforcement Learning with Heterogeneous Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11818","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:bb2856f51be58311a5246f614a3bee1e419789bb474cf475a77dc6dc9b221f5f","target":"record","created_at":"2026-07-05T10:14:49Z","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":"7e08799c2911291b2bcc30d43fd01d022de577116b4a0003c1510d207992c79f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T01:56:33Z","title_canon_sha256":"1dedfedba28d340ade2dec8e1b16d87831a7a07223ba37f6a8072fd3d00f5599"},"schema_version":"1.0","source":{"id":"2501.11818","kind":"arxiv","version":2}},"canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","first_computed_at":"2026-07-05T10:14:49.977385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:49.977385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I2fqx8keaExpEl6rHDk6md9QgM75TYlEQm+9E85KOniYZFNbJX9h021le3qYSRtRrZScIBHcn3jYhN5M6uv0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:49.977937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb2856f51be58311a5246f614a3bee1e419789bb474cf475a77dc6dc9b221f5f","sha256:76f91070aa824744fcb6568f4f67810301e1b6052b4c64300cdb1ab92f9ff4ff"],"state_sha256":"40f48fc552a7ab2579f502857f10fe0e992b0d524630677dfe2b30931482b8e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGM7/9i78uRfQl9ow9yPYtrKDyi9mfyj8NwcM1W3YmbUojmeElgzysycZ+/nJrNgAoewfy58fkXZ9/KJV3baBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T23:30:03.715290Z","bundle_sha256":"fe3dd80403caf06e902d6f6fa657f72d02d3ef8c671241e1dbe5c3c737f28fa9"}}