{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UWIMWRUYJHHPR54CUURJP4HCUH","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":"181768bc4754e52b9946c2beca90b69b50786a203169fc3314c80fd32fba2eeb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T08:03:55Z","title_canon_sha256":"3098fd5b5df4212e33ea5a2763300cb20a887e3af857328dd3dfd00a22a5292a"},"schema_version":"1.0","source":{"id":"2605.26667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26667","created_at":"2026-05-27T01:06:04Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26667v1","created_at":"2026-05-27T01:06:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26667","created_at":"2026-05-27T01:06:04Z"},{"alias_kind":"pith_short_12","alias_value":"UWIMWRUYJHHP","created_at":"2026-05-27T01:06:04Z"},{"alias_kind":"pith_short_16","alias_value":"UWIMWRUYJHHPR54C","created_at":"2026-05-27T01:06:04Z"},{"alias_kind":"pith_short_8","alias_value":"UWIMWRUY","created_at":"2026-05-27T01:06:04Z"}],"graph_snapshots":[{"event_id":"sha256:105d3231190940de5b774560102fd7ea0893be46f6b24fd5ee2ee93cf1c752f7","target":"graph","created_at":"2026-05-27T01:06:04Z","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/2605.26667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empirical work has been done to understand the specific failure modes and design choices that these systems present. Existing benchmarks report aggregate question-answering accuracy and treat memory systems as black boxes, making it impossible to attribute an incorrect answer to a particular failure mode of the system. We introduce MemFail, a diagnostic benchmark that isolates the failure modes of modern LLM memory systems. We begin by formalizing mem","authors_text":"Dawn Song, Ishir Garg, Neel Kolhe, Xuandong Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T08:03:55Z","title":"MemFail: Stress-Testing Failure Modes of LLM Memory Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26667","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:ed76dbf94ff80adcf411944824a4729dd74d4378b895392dca1ab6df60620ed2","target":"record","created_at":"2026-05-27T01:06:04Z","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":"181768bc4754e52b9946c2beca90b69b50786a203169fc3314c80fd32fba2eeb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T08:03:55Z","title_canon_sha256":"3098fd5b5df4212e33ea5a2763300cb20a887e3af857328dd3dfd00a22a5292a"},"schema_version":"1.0","source":{"id":"2605.26667","kind":"arxiv","version":1}},"canonical_sha256":"a590cb469849cef8f782a52297f0e2a1ec7445145c80275727444c6a52b4d5b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a590cb469849cef8f782a52297f0e2a1ec7445145c80275727444c6a52b4d5b5","first_computed_at":"2026-05-27T01:06:04.803586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:04.803586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cnzTtv3mUXEy46rRIoDMKbaoLFUyITjKFuYimDPb0mhAQhUn3GF7N+qo6ErSQbJXo2fjtaspzXdN3sDESY92AA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:04.804358Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed76dbf94ff80adcf411944824a4729dd74d4378b895392dca1ab6df60620ed2","sha256:105d3231190940de5b774560102fd7ea0893be46f6b24fd5ee2ee93cf1c752f7"],"state_sha256":"034eeeb33dee380df210daddc43b7cc4132583054ba0e8c3b0ada83eed576d84"}