{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SWQSPFVDFHLEKJOBRARXCCBAOO","short_pith_number":"pith:SWQSPFVD","schema_version":"1.0","canonical_sha256":"95a12796a329d64525c1882371082073b03c670c2ee21ba9cbe15c7b6e4d6cd7","source":{"kind":"arxiv","id":"2607.19359","version":1},"attestation_state":"computed","paper":{"title":"Profile-Graph Memory for LLM Agents: Implicit Cross-Entity Traversal through Narrative Profiles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Shengtong Zhu","submitted_at":"2026-06-01T09:48:16Z","abstract_excerpt":"Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving multi-hop association largely unmeasured. We make three contributions. First, we introduce MemHop, a multi-hop memory benchmark of 1,000 questions at hop depths 1-5 across 10 social-network scenarios, with per-hop evidence annotations. Second, we present Profile-Graph Memory (ProGraph), a two-layer memory architecture combining (i) profile expansion -- substring-matched traversal of entity names that naturally appear in LLM-written profile narr"},"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":"2607.19359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T09:48:16Z","cross_cats_sorted":[],"title_canon_sha256":"ee57dd308b52226d8cb4099914487356c05533c80df6869f4217703140a6e897","abstract_canon_sha256":"d63e83d312d28a99465119a138853e5283e4c4f942bfd18f70fbbb96b0f4aaf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:44.696170Z","signature_b64":"T3WUdAiqqAXPR5bm/phdXe7+LvgXWwQl1PrSfT2Y1H82e7nfjWfTcCD6mg5BxLn8IyKoN7pruBWlM20MKYjOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a12796a329d64525c1882371082073b03c670c2ee21ba9cbe15c7b6e4d6cd7","last_reissued_at":"2026-07-23T00:23:44.695232Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:44.695232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Profile-Graph Memory for LLM Agents: Implicit Cross-Entity Traversal through Narrative Profiles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Shengtong Zhu","submitted_at":"2026-06-01T09:48:16Z","abstract_excerpt":"Long-term memory is essential for LLM agents that interact across sessions, yet current memory benchmarks primarily evaluate single-hop recall, leaving multi-hop association largely unmeasured. We make three contributions. First, we introduce MemHop, a multi-hop memory benchmark of 1,000 questions at hop depths 1-5 across 10 social-network scenarios, with per-hop evidence annotations. Second, we present Profile-Graph Memory (ProGraph), a two-layer memory architecture combining (i) profile expansion -- substring-matched traversal of entity names that naturally appear in LLM-written profile narr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19359","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/2607.19359/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":"2607.19359","created_at":"2026-07-23T00:23:44.695704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19359v1","created_at":"2026-07-23T00:23:44.695704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19359","created_at":"2026-07-23T00:23:44.695704+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWQSPFVDFHLE","created_at":"2026-07-23T00:23:44.695704+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWQSPFVDFHLEKJOB","created_at":"2026-07-23T00:23:44.695704+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWQSPFVD","created_at":"2026-07-23T00:23:44.695704+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/SWQSPFVDFHLEKJOBRARXCCBAOO","json":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO.json","graph_json":"https://pith.science/api/pith-number/SWQSPFVDFHLEKJOBRARXCCBAOO/graph.json","events_json":"https://pith.science/api/pith-number/SWQSPFVDFHLEKJOBRARXCCBAOO/events.json","paper":"https://pith.science/paper/SWQSPFVD"},"agent_actions":{"view_html":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO","download_json":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO.json","view_paper":"https://pith.science/paper/SWQSPFVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19359&json=true","fetch_graph":"https://pith.science/api/pith-number/SWQSPFVDFHLEKJOBRARXCCBAOO/graph.json","fetch_events":"https://pith.science/api/pith-number/SWQSPFVDFHLEKJOBRARXCCBAOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO/action/storage_attestation","attest_author":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO/action/author_attestation","sign_citation":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO/action/citation_signature","submit_replication":"https://pith.science/pith/SWQSPFVDFHLEKJOBRARXCCBAOO/action/replication_record"}},"created_at":"2026-07-23T00:23:44.695704+00:00","updated_at":"2026-07-23T00:23:44.695704+00:00"}