{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SOAMMIAIGGSXM342OBNIXG7LQE","short_pith_number":"pith:SOAMMIAI","schema_version":"1.0","canonical_sha256":"9380c6200831a5766f9a705a8b9beb8134b489775dc985578c687a1cd6e94f39","source":{"kind":"arxiv","id":"2605.15701","version":1},"attestation_state":"computed","paper":{"title":"H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawei Yu, Xilin Liu, Yixiang Fang, Yuchi Ma","submitted_at":"2026-05-15T07:46:38Z","abstract_excerpt":"Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack a principled mechanism for effectively modeling how memory data evolves over time and retrieving memory data effectively, leading to poor performance in memory utilization. To fill this gap, we present H-Mem, a novel memory mechanism via a hybrid structure that can not only effectively model the evolution of agent memory over a long period of time, but also "},"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":"2605.15701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T07:46:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2dfc63be70592b4fbf3525206af43d8af93794d5bd723932cbf4243601fec750","abstract_canon_sha256":"37f14f604db7e2b3df7a000c25af72544c72a44b39829cf0138a140a92ceb55e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:13.264454Z","signature_b64":"QoOv1h8NLEWsllDDlQwIvQ2seimFdMleIpc9GZtKro6t4E+RiDRR1BZddNWGC8eKJ1oCZFP7jrGQVSurK3CBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9380c6200831a5766f9a705a8b9beb8134b489775dc985578c687a1cd6e94f39","last_reissued_at":"2026-05-20T00:01:13.263595Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:13.263595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawei Yu, Xilin Liu, Yixiang Fang, Yuchi Ma","submitted_at":"2026-05-15T07:46:38Z","abstract_excerpt":"Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack a principled mechanism for effectively modeling how memory data evolves over time and retrieving memory data effectively, leading to poor performance in memory utilization. To fill this gap, we present H-Mem, a novel memory mechanism via a hybrid structure that can not only effectively model the evolution of agent memory over a long period of time, but also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15701","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/2605.15701/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:27.255511Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.032210Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"61069ac112c0807b05e9d6dae3d1e3740acd815eff4c94465d8112751957eb32"},"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":"2605.15701","created_at":"2026-05-20T00:01:13.263733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15701v1","created_at":"2026-05-20T00:01:13.263733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15701","created_at":"2026-05-20T00:01:13.263733+00:00"},{"alias_kind":"pith_short_12","alias_value":"SOAMMIAIGGSX","created_at":"2026-05-20T00:01:13.263733+00:00"},{"alias_kind":"pith_short_16","alias_value":"SOAMMIAIGGSXM342","created_at":"2026-05-20T00:01:13.263733+00:00"},{"alias_kind":"pith_short_8","alias_value":"SOAMMIAI","created_at":"2026-05-20T00:01:13.263733+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/SOAMMIAIGGSXM342OBNIXG7LQE","json":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE.json","graph_json":"https://pith.science/api/pith-number/SOAMMIAIGGSXM342OBNIXG7LQE/graph.json","events_json":"https://pith.science/api/pith-number/SOAMMIAIGGSXM342OBNIXG7LQE/events.json","paper":"https://pith.science/paper/SOAMMIAI"},"agent_actions":{"view_html":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE","download_json":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE.json","view_paper":"https://pith.science/paper/SOAMMIAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15701&json=true","fetch_graph":"https://pith.science/api/pith-number/SOAMMIAIGGSXM342OBNIXG7LQE/graph.json","fetch_events":"https://pith.science/api/pith-number/SOAMMIAIGGSXM342OBNIXG7LQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE/action/storage_attestation","attest_author":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE/action/author_attestation","sign_citation":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE/action/citation_signature","submit_replication":"https://pith.science/pith/SOAMMIAIGGSXM342OBNIXG7LQE/action/replication_record"}},"created_at":"2026-05-20T00:01:13.263733+00:00","updated_at":"2026-05-20T00:01:13.263733+00:00"}