{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZWIRCKGBG6NTY4V3PYKS3RKKH6","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":"2af922ba6ad907797b56b9869c5fbe5bd507eabf2403a719609dadca4dc1cd81","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T04:56:52Z","title_canon_sha256":"b78039bb98826321929630f310e8bd840e2d83acd99e6afc82f831a2da1613b0"},"schema_version":"1.0","source":{"id":"2608.11658","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11658","created_at":"2026-08-13T01:27:14Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11658v1","created_at":"2026-08-13T01:27:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11658","created_at":"2026-08-13T01:27:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZWIRCKGBG6NT","created_at":"2026-08-13T01:27:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZWIRCKGBG6NTY4V3","created_at":"2026-08-13T01:27:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZWIRCKGB","created_at":"2026-08-13T01:27:14Z"}],"graph_snapshots":[{"event_id":"sha256:1e9008de38569e2b53a09ee914f2eed2d1448d46fce515e8f4229f6461abae7e","target":"graph","created_at":"2026-08-13T01:27:14Z","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/2608.11658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically after deployment, and retraining a policy for each new objective is prohibitively expensive. For a single agent, this problem is well understood: successor features with generalized policy improvement, together with their universal extension, recombine a library of learned policies into a policy for any new objective, with a guarantee that the result is never worse than any policy in the library. However, multi-agent transfer has received far less attention, an","authors_text":"Sen Li, Zijian Zhao","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T04:56:52Z","title":"Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11658","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:d09a94c13c0f3d92a8312765aa53bdcb30c4b13c5216f3565fadcea3b8fb44a9","target":"record","created_at":"2026-08-13T01:27:14Z","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":"2af922ba6ad907797b56b9869c5fbe5bd507eabf2403a719609dadca4dc1cd81","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T04:56:52Z","title_canon_sha256":"b78039bb98826321929630f310e8bd840e2d83acd99e6afc82f831a2da1613b0"},"schema_version":"1.0","source":{"id":"2608.11658","kind":"arxiv","version":1}},"canonical_sha256":"cd911128c1379b3c72bb7e152dc54a3fbd5ccb05ff6be1d124dd7ccdba8c4a69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd911128c1379b3c72bb7e152dc54a3fbd5ccb05ff6be1d124dd7ccdba8c4a69","first_computed_at":"2026-08-13T01:27:14.438341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:27:14.438341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ajTWRDCQjbh94x/h80TDy4xUkUybzZpZWkB6wSOR+5X/y13DmgwmuFhuyrNMz+6Y144Z/6ijhHoPf2LDDj79Dg==","signature_status":"signed_v1","signed_at":"2026-08-13T01:27:14.440835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11658","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d09a94c13c0f3d92a8312765aa53bdcb30c4b13c5216f3565fadcea3b8fb44a9","sha256:1e9008de38569e2b53a09ee914f2eed2d1448d46fce515e8f4229f6461abae7e"],"state_sha256":"62f2ec7a43218fa0cef8291736626c6eb9125de0669ecf6c01ed98bccd324c05"}