{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z3RIK27SW2MLQTCGBDUZKQXAFC","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":"90894377721d2fcf89955ccd68e070ac3771e47aead2dc3252eabf431ce4aad0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T10:54:31Z","title_canon_sha256":"445ab08c2d6fa183173f8685730533ffdb27a973292b064b0c8493ca6c230705"},"schema_version":"1.0","source":{"id":"2506.13356","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13356","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13356v1","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13356","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"Z3RIK27SW2ML","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"Z3RIK27SW2MLQTCG","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"Z3RIK27S","created_at":"2026-07-05T11:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:6c76d72ad7e9cd2ecb83dec31742fbae90691ab8b536d777cab49765803fb55b","target":"graph","created_at":"2026-07-05T11:22:09Z","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/2506.13356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-term memory (LTM) is essential for large language models (LLMs) to achieve autonomous intelligence in complex, evolving environments. Despite increasing efforts in memory-augmented and retrieval-based architectures, there remains a lack of standardized benchmarks to systematically evaluate LLMs' long-term memory abilities. Existing benchmarks still face challenges in evaluating knowledge retention and dynamic sequential reasoning, and in their own flexibility, all of which limit their effectiveness in assessing models' LTM capabilities. To address these gaps, we propose a novel benchmark ","authors_text":"Luanbo Wan, Weizhi Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T10:54:31Z","title":"StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13356","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:a05cb67fc8bdfc3046d19b3dca0fbbe1e70cf26e5bf8084ffd325d7433fe57b2","target":"record","created_at":"2026-07-05T11:22:09Z","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":"90894377721d2fcf89955ccd68e070ac3771e47aead2dc3252eabf431ce4aad0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T10:54:31Z","title_canon_sha256":"445ab08c2d6fa183173f8685730533ffdb27a973292b064b0c8493ca6c230705"},"schema_version":"1.0","source":{"id":"2506.13356","kind":"arxiv","version":1}},"canonical_sha256":"cee2856bf2b698b84c4608e99542e0288466590f9360bd3a55826d9766c42182","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cee2856bf2b698b84c4608e99542e0288466590f9360bd3a55826d9766c42182","first_computed_at":"2026-07-05T11:22:09.195450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:09.195450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"puZr4A/VQ1VTtBTVWBzzMiOSW515uJ1m0rI5ibXampLTaSk170qGYIX3irv79lkoAPwSO2m64h0Ua9Ks2LWkAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:09.195945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13356","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a05cb67fc8bdfc3046d19b3dca0fbbe1e70cf26e5bf8084ffd325d7433fe57b2","sha256:6c76d72ad7e9cd2ecb83dec31742fbae90691ab8b536d777cab49765803fb55b"],"state_sha256":"0fe10bd696f42e968784d65dd01f933394e23f0581fe94537ac396d498ea28d8"}