{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:62FV7ZIAVLDPB74WZGZTNPUC42","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":"aa97e977f9a11067bd69f43c67885f0972f0faff40eb517c65fdaf4709a1e0c7","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:02:00Z","title_canon_sha256":"563cbd3ba0a3eaa94be10f0e3717dd446bc7e5d329bbd6280fac20619054931f"},"schema_version":"1.0","source":{"id":"2605.21768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21768","created_at":"2026-05-22T01:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21768v1","created_at":"2026-05-22T01:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21768","created_at":"2026-05-22T01:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"62FV7ZIAVLDP","created_at":"2026-05-22T01:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"62FV7ZIAVLDPB74W","created_at":"2026-05-22T01:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"62FV7ZIA","created_at":"2026-05-22T01:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:12e858ae4b2562530ed62c0e640a072ffb68677f97d14d96073ebd84db48e8a5","target":"graph","created_at":"2026-05-22T01:03:31Z","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/2605.21768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments is challenging because memory turns the agent's past actions into part of its future environment. Once different rollouts write, update, or delete different memories, they no longer share the same intermediate memory state, making trajectory-level comparisons fundamentally unfair. This violates a key assumption behind group-relative methods such as GRPO, wh","authors_text":"Ahmed Bahloul, Ercong Nie, Riccardo Trivisonno, Sikuan Yan, Susanna Schwarzmann, Volker Tresp, Yunpu Ma","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:02:00Z","title":"Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21768","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":"sha256:8e098ca5b66e8bf5e43918799f61341c1c4a9efae422c91e20522552b2ecda2e","target":"record","created_at":"2026-05-22T01:03:31Z","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":"aa97e977f9a11067bd69f43c67885f0972f0faff40eb517c65fdaf4709a1e0c7","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T22:02:00Z","title_canon_sha256":"563cbd3ba0a3eaa94be10f0e3717dd446bc7e5d329bbd6280fac20619054931f"},"schema_version":"1.0","source":{"id":"2605.21768","kind":"arxiv","version":1}},"canonical_sha256":"f68b5fe500aac6f0ff96c9b336be82e6af60a3e79a6c4499b20f24c1c0652f2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f68b5fe500aac6f0ff96c9b336be82e6af60a3e79a6c4499b20f24c1c0652f2e","first_computed_at":"2026-05-22T01:03:31.093366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:31.093366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ER6EevgSDHI6KYdByP4dxJ8YsPD8qzwNlhyoBQcLnsiRXCV9E5xMu5eERYk6QPy12VoThl0RXO8Aghvdiz1kCg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:31.093897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e098ca5b66e8bf5e43918799f61341c1c4a9efae422c91e20522552b2ecda2e","sha256:12e858ae4b2562530ed62c0e640a072ffb68677f97d14d96073ebd84db48e8a5"],"state_sha256":"973802dbbd08ff2577850177c7aeecdbea42d0014c3accfcf127b8e53dd8abd1"}