{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZLMAXRMF7MC7NWCPZAF46UNCMK","short_pith_number":"pith:ZLMAXRMF","canonical_record":{"source":{"id":"2508.01049","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-01T20:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"d160c0cbf665b54b7808ca28da06d3de60ea613d76d38d13c5e7d97ce500f235","abstract_canon_sha256":"bdaaf980e6e5efe9aba0d37a7c6f6e69f471a40d9ca4ba60d186675b6db1f6a6"},"schema_version":"1.0"},"canonical_sha256":"cad80bc585fb05f6d84fc80bcf51a262b0ba49e4afa3398a2f1b1b08b96070d7","source":{"kind":"arxiv","id":"2508.01049","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01049","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01049v2","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01049","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZLMAXRMF7MC7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZLMAXRMF7MC7NWCP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZLMAXRMF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZLMAXRMF7MC7NWCPZAF46UNCMK","target":"record","payload":{"canonical_record":{"source":{"id":"2508.01049","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-01T20:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"d160c0cbf665b54b7808ca28da06d3de60ea613d76d38d13c5e7d97ce500f235","abstract_canon_sha256":"bdaaf980e6e5efe9aba0d37a7c6f6e69f471a40d9ca4ba60d186675b6db1f6a6"},"schema_version":"1.0"},"canonical_sha256":"cad80bc585fb05f6d84fc80bcf51a262b0ba49e4afa3398a2f1b1b08b96070d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:34.945516Z","signature_b64":"MUW7qvC2mi+hDIn8FW7wKB5HBCKi548KvdyR9XjfV1zrpXM1RmneC3WEvMd997SAZHqB7kIwmXYwTXTL0GLtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad80bc585fb05f6d84fc80bcf51a262b0ba49e4afa3398a2f1b1b08b96070d7","last_reissued_at":"2026-05-18T03:09:34.944961Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:34.944961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.01049","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":"2026-05-18T03:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"62Jh3psC/FqBf1DhOUYDpmfMgXTjGftVFgYXvtf3L/OMhSQrDiknvOkV1hVEuAbtses3v4NiKoiwZhqHHSEaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T04:39:26.662665Z"},"content_sha256":"e7326324e215a66311c80e114f43a8a3d276716f9611d5f24d342aea2cb1ecfd","schema_version":"1.0","event_id":"sha256:e7326324e215a66311c80e114f43a8a3d276716f9611d5f24d342aea2cb1ecfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZLMAXRMF7MC7NWCPZAF46UNCMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Josiah P. Hanna, Nicholas E. Corrado","submitted_at":"2025-08-01T20:07:25Z","abstract_excerpt":"Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games, but they are known to converge sub-optimally when each agent's individual policy gradient points away from an optimal joint equilibrium. Going beyond prior work, we observe that sub-optimal convergence can still arise even when the expected individual policy gradients of each agent point toward the optimal joint solution. After collecting a finite set of trajectories, stochasticity in independent action sampling can cause the joint data distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01049","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":""},"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":"2026-05-18T03:09:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqJ+rVYnxLqxBDISDj3aEqaYPlLdurHcBw0ZrgoZYUQG5M3rsFj3SvzMnHm0mUulDr1SJNSphD/qOWgfeKUoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T04:39:26.663270Z"},"content_sha256":"d10228af6bb3b7354a52c74404a6080ab6e3a204abec52c4ecfb842b2b3b2ec9","schema_version":"1.0","event_id":"sha256:d10228af6bb3b7354a52c74404a6080ab6e3a204abec52c4ecfb842b2b3b2ec9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK/bundle.json","state_url":"https://pith.science/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK/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":"2026-05-21T04:39:26Z","links":{"resolver":"https://pith.science/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK","bundle":"https://pith.science/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK/bundle.json","state":"https://pith.science/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLMAXRMF7MC7NWCPZAF46UNCMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZLMAXRMF7MC7NWCPZAF46UNCMK","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":"bdaaf980e6e5efe9aba0d37a7c6f6e69f471a40d9ca4ba60d186675b6db1f6a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-01T20:07:25Z","title_canon_sha256":"d160c0cbf665b54b7808ca28da06d3de60ea613d76d38d13c5e7d97ce500f235"},"schema_version":"1.0","source":{"id":"2508.01049","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01049","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01049v2","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01049","created_at":"2026-05-18T03:09:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZLMAXRMF7MC7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZLMAXRMF7MC7NWCP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZLMAXRMF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d10228af6bb3b7354a52c74404a6080ab6e3a204abec52c4ecfb842b2b3b2ec9","target":"graph","created_at":"2026-05-18T03:09:34Z","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"},"paper":{"abstract_excerpt":"Independent on-policy policy gradient algorithms are widely used for multi-agent reinforcement learning (MARL) in cooperative and no-conflict games, but they are known to converge sub-optimally when each agent's individual policy gradient points away from an optimal joint equilibrium. Going beyond prior work, we observe that sub-optimal convergence can still arise even when the expected individual policy gradients of each agent point toward the optimal joint solution. After collecting a finite set of trajectories, stochasticity in independent action sampling can cause the joint data distributi","authors_text":"Josiah P. Hanna, Nicholas E. Corrado","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-01T20:07:25Z","title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01049","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:e7326324e215a66311c80e114f43a8a3d276716f9611d5f24d342aea2cb1ecfd","target":"record","created_at":"2026-05-18T03:09:34Z","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":"bdaaf980e6e5efe9aba0d37a7c6f6e69f471a40d9ca4ba60d186675b6db1f6a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-01T20:07:25Z","title_canon_sha256":"d160c0cbf665b54b7808ca28da06d3de60ea613d76d38d13c5e7d97ce500f235"},"schema_version":"1.0","source":{"id":"2508.01049","kind":"arxiv","version":2}},"canonical_sha256":"cad80bc585fb05f6d84fc80bcf51a262b0ba49e4afa3398a2f1b1b08b96070d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad80bc585fb05f6d84fc80bcf51a262b0ba49e4afa3398a2f1b1b08b96070d7","first_computed_at":"2026-05-18T03:09:34.944961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:34.944961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MUW7qvC2mi+hDIn8FW7wKB5HBCKi548KvdyR9XjfV1zrpXM1RmneC3WEvMd997SAZHqB7kIwmXYwTXTL0GLtCg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:34.945516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01049","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7326324e215a66311c80e114f43a8a3d276716f9611d5f24d342aea2cb1ecfd","sha256:d10228af6bb3b7354a52c74404a6080ab6e3a204abec52c4ecfb842b2b3b2ec9"],"state_sha256":"33cc9a0666add588bc8cd177d7d87c14b12d65f3888524ae1a953be2bea0c75e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yctFixxknObNfQ/Ys52Mt9NCeEs8fbb6DPo115lmO/y6a0R+QTWss4tKwdXn93DtlWBcBPc+8M7IWbFUXNJ9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T04:39:26.666159Z","bundle_sha256":"9113a506e18c30d77251b4f0d0e9edc2f9eaa2f7e993611e942027a75c2c7a66"}}