{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XB7HOUHHZLU3AAJNTDIH67OM27","short_pith_number":"pith:XB7HOUHH","schema_version":"1.0","canonical_sha256":"b87e7750e7cae9b0012d98d07f7dccd7c47108b4f7fee7685e891fb538b06985","source":{"kind":"arxiv","id":"2601.08160","version":2},"attestation_state":"computed","paper":{"title":"SwiftMem: Fast Agentic Memory via Query-aware Indexing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anxin Tian, Hui-Ling Zhen, Lei Chen, Mingxuan Yuan, Xianzhi Yu, Xing Li, Yiming Li, Zhenhua Dong","submitted_at":"2026-01-13T02:51:04Z","abstract_excerpt":"Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks often perform query-agnostic retrieval over the full memory embedding space even when their storage layer is backed by efficient vector indexes such as HNSW. This full-scope retrieval path creates latency bottlenecks as memory grows, hindering real-time agent interactions. We propose SwiftMem, a query-aware agentic memory system that narrows retrieval to query-relevant memory subsets through specialized indexing ove"},"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":"2601.08160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-13T02:51:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14a3c0db80ae205782e4acf96923dfb2bf791682428e12d386d5fe6835106eaa","abstract_canon_sha256":"a38d26132e22e1982ec627fa3ff0262cda8c6723d9d409d56e2287418fe417ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:19:54.773414Z","signature_b64":"B7oR6eJHrRMFYD9h4guXd/Uj/G5hBXUgiBAQIrCvWzbsODaK5fDvPmVTP5iGqA/GR2R+cHqMhNzW1Q2p0luBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b87e7750e7cae9b0012d98d07f7dccd7c47108b4f7fee7685e891fb538b06985","last_reissued_at":"2026-07-27T01:19:54.772467Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:19:54.772467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SwiftMem: Fast Agentic Memory via Query-aware Indexing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anxin Tian, Hui-Ling Zhen, Lei Chen, Mingxuan Yuan, Xianzhi Yu, Xing Li, Yiming Li, Zhenhua Dong","submitted_at":"2026-01-13T02:51:04Z","abstract_excerpt":"Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks often perform query-agnostic retrieval over the full memory embedding space even when their storage layer is backed by efficient vector indexes such as HNSW. This full-scope retrieval path creates latency bottlenecks as memory grows, hindering real-time agent interactions. We propose SwiftMem, a query-aware agentic memory system that narrows retrieval to query-relevant memory subsets through specialized indexing ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08160","kind":"arxiv","version":2},"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/2601.08160/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":"2601.08160","created_at":"2026-07-27T01:19:54.772910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.08160v2","created_at":"2026-07-27T01:19:54.772910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08160","created_at":"2026-07-27T01:19:54.772910+00:00"},{"alias_kind":"pith_short_12","alias_value":"XB7HOUHHZLU3","created_at":"2026-07-27T01:19:54.772910+00:00"},{"alias_kind":"pith_short_16","alias_value":"XB7HOUHHZLU3AAJN","created_at":"2026-07-27T01:19:54.772910+00:00"},{"alias_kind":"pith_short_8","alias_value":"XB7HOUHH","created_at":"2026-07-27T01:19:54.772910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.04315","citing_title":"Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25869","citing_title":"Mitigating Provenance-Role Collapse in Long-Term Agents via Typed Memory Representation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27","json":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27.json","graph_json":"https://pith.science/api/pith-number/XB7HOUHHZLU3AAJNTDIH67OM27/graph.json","events_json":"https://pith.science/api/pith-number/XB7HOUHHZLU3AAJNTDIH67OM27/events.json","paper":"https://pith.science/paper/XB7HOUHH"},"agent_actions":{"view_html":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27","download_json":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27.json","view_paper":"https://pith.science/paper/XB7HOUHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.08160&json=true","fetch_graph":"https://pith.science/api/pith-number/XB7HOUHHZLU3AAJNTDIH67OM27/graph.json","fetch_events":"https://pith.science/api/pith-number/XB7HOUHHZLU3AAJNTDIH67OM27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27/action/storage_attestation","attest_author":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27/action/author_attestation","sign_citation":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27/action/citation_signature","submit_replication":"https://pith.science/pith/XB7HOUHHZLU3AAJNTDIH67OM27/action/replication_record"}},"created_at":"2026-07-27T01:19:54.772910+00:00","updated_at":"2026-07-27T01:19:54.772910+00:00"}