{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5F6Z4IJIHYWHYWOMJUDO32AE5Z","short_pith_number":"pith:5F6Z4IJI","schema_version":"1.0","canonical_sha256":"e97d9e21283e2c7c59cc4d06ede804ee531ee8890412dcc3d3da0a35a045da7f","source":{"kind":"arxiv","id":"2607.12893","version":1},"attestation_state":"computed","paper":{"title":"MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Feiyu Xiong, Xichong Zhang, Xixuan Hao, Yihang Sun, Yuxuan Liang, Zehao Lin, Zeyu Zhang, Zhiyu Li, Ziliang Guo","submitted_at":"2026-07-14T15:33:44Z","abstract_excerpt":"Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through downstream question answering, scoring only the correctness of a final answer. This black-box formulation conflates the heterogeneous causes of memory failure, such as missing the introduction of a relevant fact, binding an operation to the wrong target, or relying on stale values after a correction. As a result, it can credit correct answers despite their reliance on inconsiste"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.12893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T15:33:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d08ffe6eb2cc3d4104bccad5d9e3d9a6e63b5e3c43ad79907505e4ed954f4ad1","abstract_canon_sha256":"b10fa32296c9cb1db35d99b169c596632d8b15d4ed3eb98922241918ebeb0fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:22:23.636637Z","signature_b64":"3Hy/huU4UqQzmpI6st/Udh9mZBgDw8KNlWrHjFNQM+vkEx3wVa8tfefkjkW6khjDVOc4YEAfNQvr7DZHgtjoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e97d9e21283e2c7c59cc4d06ede804ee531ee8890412dcc3d3da0a35a045da7f","last_reissued_at":"2026-07-15T01:22:23.635798Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:22:23.635798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Feiyu Xiong, Xichong Zhang, Xixuan Hao, Yihang Sun, Yuxuan Liang, Zehao Lin, Zeyu Zhang, Zhiyu Li, Ziliang Guo","submitted_at":"2026-07-14T15:33:44Z","abstract_excerpt":"Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through downstream question answering, scoring only the correctness of a final answer. This black-box formulation conflates the heterogeneous causes of memory failure, such as missing the introduction of a relevant fact, binding an operation to the wrong target, or relying on stale values after a correction. As a result, it can credit correct answers despite their reliance on inconsiste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.12893","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.12893/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.12893","created_at":"2026-07-15T01:22:23.636231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.12893v1","created_at":"2026-07-15T01:22:23.636231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.12893","created_at":"2026-07-15T01:22:23.636231+00:00"},{"alias_kind":"pith_short_12","alias_value":"5F6Z4IJIHYWH","created_at":"2026-07-15T01:22:23.636231+00:00"},{"alias_kind":"pith_short_16","alias_value":"5F6Z4IJIHYWHYWOM","created_at":"2026-07-15T01:22:23.636231+00:00"},{"alias_kind":"pith_short_8","alias_value":"5F6Z4IJI","created_at":"2026-07-15T01:22:23.636231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z","json":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z.json","graph_json":"https://pith.science/api/pith-number/5F6Z4IJIHYWHYWOMJUDO32AE5Z/graph.json","events_json":"https://pith.science/api/pith-number/5F6Z4IJIHYWHYWOMJUDO32AE5Z/events.json","paper":"https://pith.science/paper/5F6Z4IJI"},"agent_actions":{"view_html":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z","download_json":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z.json","view_paper":"https://pith.science/paper/5F6Z4IJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.12893&json=true","fetch_graph":"https://pith.science/api/pith-number/5F6Z4IJIHYWHYWOMJUDO32AE5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/5F6Z4IJIHYWHYWOMJUDO32AE5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z/action/storage_attestation","attest_author":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z/action/author_attestation","sign_citation":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z/action/citation_signature","submit_replication":"https://pith.science/pith/5F6Z4IJIHYWHYWOMJUDO32AE5Z/action/replication_record"}},"created_at":"2026-07-15T01:22:23.636231+00:00","updated_at":"2026-07-15T01:22:23.636231+00:00"}