{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NQ7KWI5ISLMSHKUTCWX7QHFXZB","short_pith_number":"pith:NQ7KWI5I","schema_version":"1.0","canonical_sha256":"6c3eab23a892d923aa9315aff81cb7c854bcd8f9492ec9e57ba2aeac46ff3f87","source":{"kind":"arxiv","id":"2501.09645","version":1},"attestation_state":"computed","paper":{"title":"CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Elisabeth Andr\\'e, Florian Matthes, Johannes Kirmayr, Lukas Stappen, Phillip Schneider","submitted_at":"2025-01-16T16:37:33Z","abstract_excerpt":"In today's assistant landscape, personalisation enhances interactions, fosters long-term relationships, and deepens engagement. However, many systems struggle with retaining user preferences, leading to repetitive user requests and disengagement. Furthermore, the unregulated and opaque extraction of user preferences in industry applications raises significant concerns about privacy and trust, especially in regions with stringent regulations like Europe. In response to these challenges, we propose a long-term memory system for voice assistants, structured around predefined categories. This appr"},"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":"2501.09645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-16T16:37:33Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"ff178010f9410cf9e64d7b4a12882147896c4d92c5f3eb4202601dee616dfe49","abstract_canon_sha256":"e8b63f1e67f8b205fdc33452eab555141b17a4f391f8ff3be5eb170250073634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:50.144084Z","signature_b64":"AHAuAH8Ny0gU2t8Uf5XS7w4seRKj7vmhxIovRd5E81uXXXJOEfQoljuGTdWdZyPzdMci7zxgpBpZUytTxCK+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c3eab23a892d923aa9315aff81cb7c854bcd8f9492ec9e57ba2aeac46ff3f87","last_reissued_at":"2026-07-05T10:01:50.143687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:50.143687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CarMem: Enhancing Long-Term Memory in LLM Voice Assistants through Category-Bounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Elisabeth Andr\\'e, Florian Matthes, Johannes Kirmayr, Lukas Stappen, Phillip Schneider","submitted_at":"2025-01-16T16:37:33Z","abstract_excerpt":"In today's assistant landscape, personalisation enhances interactions, fosters long-term relationships, and deepens engagement. However, many systems struggle with retaining user preferences, leading to repetitive user requests and disengagement. Furthermore, the unregulated and opaque extraction of user preferences in industry applications raises significant concerns about privacy and trust, especially in regions with stringent regulations like Europe. In response to these challenges, we propose a long-term memory system for voice assistants, structured around predefined categories. This appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09645","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/2501.09645/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":"2501.09645","created_at":"2026-07-05T10:01:50.143744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09645v1","created_at":"2026-07-05T10:01:50.143744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09645","created_at":"2026-07-05T10:01:50.143744+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQ7KWI5ISLMS","created_at":"2026-07-05T10:01:50.143744+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQ7KWI5ISLMSHKUT","created_at":"2026-07-05T10:01:50.143744+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQ7KWI5I","created_at":"2026-07-05T10:01:50.143744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.13044","citing_title":"CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB","json":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB.json","graph_json":"https://pith.science/api/pith-number/NQ7KWI5ISLMSHKUTCWX7QHFXZB/graph.json","events_json":"https://pith.science/api/pith-number/NQ7KWI5ISLMSHKUTCWX7QHFXZB/events.json","paper":"https://pith.science/paper/NQ7KWI5I"},"agent_actions":{"view_html":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB","download_json":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB.json","view_paper":"https://pith.science/paper/NQ7KWI5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09645&json=true","fetch_graph":"https://pith.science/api/pith-number/NQ7KWI5ISLMSHKUTCWX7QHFXZB/graph.json","fetch_events":"https://pith.science/api/pith-number/NQ7KWI5ISLMSHKUTCWX7QHFXZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB/action/storage_attestation","attest_author":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB/action/author_attestation","sign_citation":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB/action/citation_signature","submit_replication":"https://pith.science/pith/NQ7KWI5ISLMSHKUTCWX7QHFXZB/action/replication_record"}},"created_at":"2026-07-05T10:01:50.143744+00:00","updated_at":"2026-07-05T10:01:50.143744+00:00"}