{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7YEVGP254RVYAVFEW7VZ6TDUPK","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":"5be5b0a684555a22c5698768dfad92365670060eb9999c2e437d32ef36df782a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T21:58:10Z","title_canon_sha256":"e993ef2584f4bfccb28d11a693ce26086d02c97fbe05f9360badb03365a08d3a"},"schema_version":"1.0","source":{"id":"2605.23067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23067","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23067v1","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23067","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"pith_short_12","alias_value":"7YEVGP254RVY","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"pith_short_16","alias_value":"7YEVGP254RVYAVFE","created_at":"2026-05-25T02:01:37Z"},{"alias_kind":"pith_short_8","alias_value":"7YEVGP25","created_at":"2026-05-25T02:01:37Z"}],"graph_snapshots":[{"event_id":"sha256:5c2c3da08c56879c02320b6acfb0232ae8f51bd7bd64b843576fa4832f868d8a","target":"graph","created_at":"2026-05-25T02:01:37Z","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/2605.23067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Existing work trains exclusively on a single benchmark, leaving open how the composition of training data shapes the skills a memory agent acquires. We present a controlled empirical study that holds architecture, RL algorithm, and all hyperparameters fixed and varies only the training curriculum across three conditions: in-domain (LoCoMo), mixed-benchmark (LoCoMo + LongMemEval), and out-of-domain (LongMemEval only). Across two benchmarks and ten qu","authors_text":"Jialun Wu, Qiyang Xie, Shuai Xiao, Su Liu, Weikai Zhou, Xinjie He, Zhiyuan Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T21:58:10Z","title":"What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23067","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":"sha256:23a7d7e4e6cf32814642acadd1031fd160d384cb2bd64b98920653e06f076df3","target":"record","created_at":"2026-05-25T02:01:37Z","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":"5be5b0a684555a22c5698768dfad92365670060eb9999c2e437d32ef36df782a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-21T21:58:10Z","title_canon_sha256":"e993ef2584f4bfccb28d11a693ce26086d02c97fbe05f9360badb03365a08d3a"},"schema_version":"1.0","source":{"id":"2605.23067","kind":"arxiv","version":1}},"canonical_sha256":"fe09533f5de46b8054a4b7eb9f4c747a98e3f213b9d7807359fb57c804d6b12b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe09533f5de46b8054a4b7eb9f4c747a98e3f213b9d7807359fb57c804d6b12b","first_computed_at":"2026-05-25T02:01:37.011698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:37.011698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZOBhogOw2xJmxDGurXVx3wQZi1J50oOI/sUmAl2QiGsILah8/s9pMor/fIZJe6daChuY0Vt683JtbGuBj+pBAw==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:37.012294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23a7d7e4e6cf32814642acadd1031fd160d384cb2bd64b98920653e06f076df3","sha256:5c2c3da08c56879c02320b6acfb0232ae8f51bd7bd64b843576fa4832f868d8a"],"state_sha256":"7499faa43e5093cb053d423c64f481b5646a43552e87c12763550a2a6d6906a5"}