{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RRDNU3T677M7O2SN54QE6HOXIG","short_pith_number":"pith:RRDNU3T6","canonical_record":{"source":{"id":"2606.25526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T08:05:11Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"52236da1d79bd8159393218350dcb30c3bdbfa67a74f9d475569104eeb521b3f","abstract_canon_sha256":"4351b043cac520cdb53279ee83157ce3c9c6486e0a2b26feb1017e5ec3651432"},"schema_version":"1.0"},"canonical_sha256":"8c46da6e7effd9f76a4def204f1dd741bcb9529df0e9189ec1a7df5825da8faa","source":{"kind":"arxiv","id":"2606.25526","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25526","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25526v1","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25526","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"pith_short_12","alias_value":"RRDNU3T677M7","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"pith_short_16","alias_value":"RRDNU3T677M7O2SN","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"pith_short_8","alias_value":"RRDNU3T6","created_at":"2026-06-25T01:18:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RRDNU3T677M7O2SN54QE6HOXIG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T08:05:11Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"52236da1d79bd8159393218350dcb30c3bdbfa67a74f9d475569104eeb521b3f","abstract_canon_sha256":"4351b043cac520cdb53279ee83157ce3c9c6486e0a2b26feb1017e5ec3651432"},"schema_version":"1.0"},"canonical_sha256":"8c46da6e7effd9f76a4def204f1dd741bcb9529df0e9189ec1a7df5825da8faa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:07.881198Z","signature_b64":"FXwVbmDtJqzevP6SyCp1qyuJXd6Sa5tOSdrjSxEw/+sGr8ntRX3tnZNYY/cXP/esm8XIMcXYt1kYtHaiBtnyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c46da6e7effd9f76a4def204f1dd741bcb9529df0e9189ec1a7df5825da8faa","last_reissued_at":"2026-06-25T01:18:07.880794Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:07.880794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25526","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":"2026-06-25T01:18:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BVA16VAT1hrwJoaXHhPQQA9RDhS1+dGNNKQrzejwUp3K1kaEEShtNj8MGZlIT0Pao7wycJvHM45voZl7+t1qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T01:57:28.752202Z"},"content_sha256":"628f5f6e6b4f3a4780df5691762ae2d4553b9683f2b69a19255294295ea40a3b","schema_version":"1.0","event_id":"sha256:628f5f6e6b4f3a4780df5691762ae2d4553b9683f2b69a19255294295ea40a3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RRDNU3T677M7O2SN54QE6HOXIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Bang Giang Le, Viet Cuong Ta","submitted_at":"2026-06-24T08:05:11Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent. Instead of relying on other agents' actions, the independent actors setting considers each agent to act based only on its local information, thus having more flexible applications. However, in the sequential update framework, it is required to re-estimate the joint advantage function after each individual agent's policy step. Despite the practical success of importance sampling, the updated advantage function suffers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25526","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/2606.25526/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":"2026-06-25T01:18:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rmNPqKL7vpUoab3j18V4t//xvzDK40iqlIVdjDa9fpVeQhtZrpnmOeJqeP6hMPGWeir6W210Awl+gCEH3LkjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T01:57:28.752591Z"},"content_sha256":"4788b0cb38228aaad04dde6c4b3ea809baf520250781b7e63ea5c9e41f487c0e","schema_version":"1.0","event_id":"sha256:4788b0cb38228aaad04dde6c4b3ea809baf520250781b7e63ea5c9e41f487c0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRDNU3T677M7O2SN54QE6HOXIG/bundle.json","state_url":"https://pith.science/pith/RRDNU3T677M7O2SN54QE6HOXIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRDNU3T677M7O2SN54QE6HOXIG/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":"2026-07-10T01:57:28Z","links":{"resolver":"https://pith.science/pith/RRDNU3T677M7O2SN54QE6HOXIG","bundle":"https://pith.science/pith/RRDNU3T677M7O2SN54QE6HOXIG/bundle.json","state":"https://pith.science/pith/RRDNU3T677M7O2SN54QE6HOXIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRDNU3T677M7O2SN54QE6HOXIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RRDNU3T677M7O2SN54QE6HOXIG","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":"4351b043cac520cdb53279ee83157ce3c9c6486e0a2b26feb1017e5ec3651432","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T08:05:11Z","title_canon_sha256":"52236da1d79bd8159393218350dcb30c3bdbfa67a74f9d475569104eeb521b3f"},"schema_version":"1.0","source":{"id":"2606.25526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25526","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25526v1","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25526","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"pith_short_12","alias_value":"RRDNU3T677M7","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"pith_short_16","alias_value":"RRDNU3T677M7O2SN","created_at":"2026-06-25T01:18:07Z"},{"alias_kind":"pith_short_8","alias_value":"RRDNU3T6","created_at":"2026-06-25T01:18:07Z"}],"graph_snapshots":[{"event_id":"sha256:4788b0cb38228aaad04dde6c4b3ea809baf520250781b7e63ea5c9e41f487c0e","target":"graph","created_at":"2026-06-25T01:18:07Z","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/2606.25526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent. Instead of relying on other agents' actions, the independent actors setting considers each agent to act based only on its local information, thus having more flexible applications. However, in the sequential update framework, it is required to re-estimate the joint advantage function after each individual agent's policy step. Despite the practical success of importance sampling, the updated advantage function suffers ","authors_text":"Bang Giang Le, Viet Cuong Ta","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T08:05:11Z","title":"Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25526","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":"sha256:628f5f6e6b4f3a4780df5691762ae2d4553b9683f2b69a19255294295ea40a3b","target":"record","created_at":"2026-06-25T01:18:07Z","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":"4351b043cac520cdb53279ee83157ce3c9c6486e0a2b26feb1017e5ec3651432","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T08:05:11Z","title_canon_sha256":"52236da1d79bd8159393218350dcb30c3bdbfa67a74f9d475569104eeb521b3f"},"schema_version":"1.0","source":{"id":"2606.25526","kind":"arxiv","version":1}},"canonical_sha256":"8c46da6e7effd9f76a4def204f1dd741bcb9529df0e9189ec1a7df5825da8faa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c46da6e7effd9f76a4def204f1dd741bcb9529df0e9189ec1a7df5825da8faa","first_computed_at":"2026-06-25T01:18:07.880794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:07.880794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FXwVbmDtJqzevP6SyCp1qyuJXd6Sa5tOSdrjSxEw/+sGr8ntRX3tnZNYY/cXP/esm8XIMcXYt1kYtHaiBtnyAw==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:07.881198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:628f5f6e6b4f3a4780df5691762ae2d4553b9683f2b69a19255294295ea40a3b","sha256:4788b0cb38228aaad04dde6c4b3ea809baf520250781b7e63ea5c9e41f487c0e"],"state_sha256":"c6506c8e09570bd7b3158bb79d1138225bdd83d3af1475ed284729513e337458"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1c6sxPE0Y214YFjAO8V9ZqQYmeVMFfjeLoT8O4lVnErIPlFZKFHgB2uGoTLuxYA+U5bAVpjb1tE2Cp1vLv2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T01:57:28.754682Z","bundle_sha256":"2c94d7beb6fb25ed041ceb23870a1c7906c5b32c6f604acbb1ecd7fa0f32c332"}}