{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JJOSEP2AI6N73KXBTPZOABZS6R","short_pith_number":"pith:JJOSEP2A","schema_version":"1.0","canonical_sha256":"4a5d223f40479bfdaae19bf2e00732f45cb61e31e3ab574aa840305abc1ab2cb","source":{"kind":"arxiv","id":"2607.22690","version":1},"attestation_state":"computed","paper":{"title":"LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaming Zhang, Jing Yu, Xiang Li, Yibo Zhao","submitted_at":"2026-07-17T12:49:57Z","abstract_excerpt":"Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse. Retrieving broadly improves evidence coverage yet overwhelms downstream reasoning with noise; compressing at write time reduces noise but irreversibly discards details the future query may need. We introduce LazyMem, which sidesteps this dilemma by deferring all memory construction to query time. A lightweight 4B model processes the retrieved candidate pool in overlapping parallel windows, selectively retaining and compressing only query-relevant content. The model is traine"},"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":"2607.22690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-17T12:49:57Z","cross_cats_sorted":[],"title_canon_sha256":"1a6ffce73aa31738bb6ec13d08628b3a64a19ff7f5530e640ebd8d02df09b077","abstract_canon_sha256":"1f7858a831aa8713bb6aee85134633a7c2f97717c386156cc165a081905fcfe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:49.274944Z","signature_b64":"l+5f97A0+d3p1Duwg20YaTpr9KruwMnj53L9kOwVG7viL3A6gTv+IDWd4Rux7vXdkGXTOA2SwSJf3DWlGWftCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a5d223f40479bfdaae19bf2e00732f45cb61e31e3ab574aa840305abc1ab2cb","last_reissued_at":"2026-07-28T00:21:49.274100Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:49.274100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiaming Zhang, Jing Yu, Xiang Li, Yibo Zhao","submitted_at":"2026-07-17T12:49:57Z","abstract_excerpt":"Long-term memory lets LLM agents reuse past interactions, but raw dialogue histories are verbose and information-sparse. Retrieving broadly improves evidence coverage yet overwhelms downstream reasoning with noise; compressing at write time reduces noise but irreversibly discards details the future query may need. We introduce LazyMem, which sidesteps this dilemma by deferring all memory construction to query time. A lightweight 4B model processes the retrieved candidate pool in overlapping parallel windows, selectively retaining and compressing only query-relevant content. The model is traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22690","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/2607.22690/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":"2607.22690","created_at":"2026-07-28T00:21:49.274548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22690v1","created_at":"2026-07-28T00:21:49.274548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22690","created_at":"2026-07-28T00:21:49.274548+00:00"},{"alias_kind":"pith_short_12","alias_value":"JJOSEP2AI6N7","created_at":"2026-07-28T00:21:49.274548+00:00"},{"alias_kind":"pith_short_16","alias_value":"JJOSEP2AI6N73KXB","created_at":"2026-07-28T00:21:49.274548+00:00"},{"alias_kind":"pith_short_8","alias_value":"JJOSEP2A","created_at":"2026-07-28T00:21:49.274548+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/JJOSEP2AI6N73KXBTPZOABZS6R","json":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R.json","graph_json":"https://pith.science/api/pith-number/JJOSEP2AI6N73KXBTPZOABZS6R/graph.json","events_json":"https://pith.science/api/pith-number/JJOSEP2AI6N73KXBTPZOABZS6R/events.json","paper":"https://pith.science/paper/JJOSEP2A"},"agent_actions":{"view_html":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R","download_json":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R.json","view_paper":"https://pith.science/paper/JJOSEP2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22690&json=true","fetch_graph":"https://pith.science/api/pith-number/JJOSEP2AI6N73KXBTPZOABZS6R/graph.json","fetch_events":"https://pith.science/api/pith-number/JJOSEP2AI6N73KXBTPZOABZS6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R/action/storage_attestation","attest_author":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R/action/author_attestation","sign_citation":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R/action/citation_signature","submit_replication":"https://pith.science/pith/JJOSEP2AI6N73KXBTPZOABZS6R/action/replication_record"}},"created_at":"2026-07-28T00:21:49.274548+00:00","updated_at":"2026-07-28T00:21:49.274548+00:00"}