{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VPTRJZEPCHFGOWHI2WA2CHPP2U","short_pith_number":"pith:VPTRJZEP","schema_version":"1.0","canonical_sha256":"abe714e48f11ca6758e8d581a11defd529cae11925de41923ed0e3c6ca7c2389","source":{"kind":"arxiv","id":"2602.10715","version":1},"attestation_state":"computed","paper":{"title":"Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents","license":"","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hui Liu, Jun Liu, Lijiao Xu, Lingling Zhang, Muye Huang, Rongman Xu, Weidong Guo, Yifei Li, Yu Xu","submitted_at":"2026-02-11T10:22:35Z","abstract_excerpt":"Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often depend on implicit constraints such as user state, goals, or values that are not explicitly queried later. To evaluate this setting, we introduce \\textbf{LoCoMo-Plus}, a benchmark for assessing cognitive memory under cue--trigger semantic disconnect, where models must retain and apply latent constraints across long conversational contexts. We further show that"},"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":"2602.10715","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"2026-02-11T10:22:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"118f2315137bc46f2cfd77bc248aa65979eb8aa109ee8a687df61e8f380055be","abstract_canon_sha256":"80b714fb85501a1e71b874607b5d3b74a728c618c7d37a1de176a6b5ad8d4846"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T08:42:33.290718Z","signature_b64":"wx4WDSQDLY1uNgPfzZhR/mxu8WJDz5b8XVPKq8dlZ2E6SFqkAeZN9ZC5mBFShV8aSjZKmdb9Z0q6+AHsaRQYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abe714e48f11ca6758e8d581a11defd529cae11925de41923ed0e3c6ca7c2389","last_reissued_at":"2026-07-02T08:42:33.290182Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T08:42:33.290182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents","license":"","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hui Liu, Jun Liu, Lijiao Xu, Lingling Zhang, Muye Huang, Rongman Xu, Weidong Guo, Yifei Li, Yu Xu","submitted_at":"2026-02-11T10:22:35Z","abstract_excerpt":"Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often depend on implicit constraints such as user state, goals, or values that are not explicitly queried later. To evaluate this setting, we introduce \\textbf{LoCoMo-Plus}, a benchmark for assessing cognitive memory under cue--trigger semantic disconnect, where models must retain and apply latent constraints across long conversational contexts. We further show that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10715","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/2602.10715/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":"2602.10715","created_at":"2026-07-02T08:42:33.290247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10715v1","created_at":"2026-07-02T08:42:33.290247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10715","created_at":"2026-07-02T08:42:33.290247+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPTRJZEPCHFG","created_at":"2026-07-02T08:42:33.290247+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPTRJZEPCHFGOWHI","created_at":"2026-07-02T08:42:33.290247+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPTRJZEP","created_at":"2026-07-02T08:42:33.290247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.17328","citing_title":"MemTrace: Probing What Final Accuracy Misses in Long-Term Memory","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04780","citing_title":"PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04315","citing_title":"Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":263,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10870","citing_title":"Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07017","citing_title":"A-MBER: Affective Memory Benchmark for Emotion Recognition","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U","json":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U.json","graph_json":"https://pith.science/api/pith-number/VPTRJZEPCHFGOWHI2WA2CHPP2U/graph.json","events_json":"https://pith.science/api/pith-number/VPTRJZEPCHFGOWHI2WA2CHPP2U/events.json","paper":"https://pith.science/paper/VPTRJZEP"},"agent_actions":{"view_html":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U","download_json":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U.json","view_paper":"https://pith.science/paper/VPTRJZEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10715&json=true","fetch_graph":"https://pith.science/api/pith-number/VPTRJZEPCHFGOWHI2WA2CHPP2U/graph.json","fetch_events":"https://pith.science/api/pith-number/VPTRJZEPCHFGOWHI2WA2CHPP2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U/action/storage_attestation","attest_author":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U/action/author_attestation","sign_citation":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U/action/citation_signature","submit_replication":"https://pith.science/pith/VPTRJZEPCHFGOWHI2WA2CHPP2U/action/replication_record"}},"created_at":"2026-07-02T08:42:33.290247+00:00","updated_at":"2026-07-02T08:42:33.290247+00:00"}