{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YAYMTIZYHGP4QL64CVVOH5T3VP","short_pith_number":"pith:YAYMTIZY","schema_version":"1.0","canonical_sha256":"c030c9a338399fc82fdc156ae3f67babd657d8f423a7e857b2dc7aa0fa6862dd","source":{"kind":"arxiv","id":"2412.12653","version":2},"attestation_state":"computed","paper":{"title":"Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jiawei Li, Yiheng Bian, Yunpeng Song, Zhongmin Cai","submitted_at":"2024-12-17T08:20:56Z","abstract_excerpt":"Enhancing the intelligence of smart systems, such as smart home, and smart vehicle, and smart grids, critically depends on developing sophisticated planning capabilities that can anticipate the next desired function based on historical interactions. While existing methods view user behaviors as sequential data and apply models like RNNs and Transformers to predict future actions, they often fail to incorporate domain knowledge and capture personalized user preferences. In this paper, we propose a novel approach that incorporates LLM-enhanced logs and personalized prompts. Our approach first co"},"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":"2412.12653","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-12-17T08:20:56Z","cross_cats_sorted":[],"title_canon_sha256":"1c029b85fe796a088383d98cb3d6abdfaa3a0540a6666f53a1353765121ca067","abstract_canon_sha256":"b0d451ee157094e113174677ce987efff4bcbc5dc1ad95d491e82ef701ca144a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:12.127765Z","signature_b64":"UrrgpiwcglLU8tPoHxVao182J4CoscxHMedwtqFaJEfg+Octi9SVqoZuAyYqrlvCqCWsN3nBhD5WtG9RZnL3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c030c9a338399fc82fdc156ae3f67babd657d8f423a7e857b2dc7aa0fa6862dd","last_reissued_at":"2026-07-05T10:49:12.127304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:12.127304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Jiawei Li, Yiheng Bian, Yunpeng Song, Zhongmin Cai","submitted_at":"2024-12-17T08:20:56Z","abstract_excerpt":"Enhancing the intelligence of smart systems, such as smart home, and smart vehicle, and smart grids, critically depends on developing sophisticated planning capabilities that can anticipate the next desired function based on historical interactions. While existing methods view user behaviors as sequential data and apply models like RNNs and Transformers to predict future actions, they often fail to incorporate domain knowledge and capture personalized user preferences. In this paper, we propose a novel approach that incorporates LLM-enhanced logs and personalized prompts. Our approach first co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12653","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/2412.12653/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":"2412.12653","created_at":"2026-07-05T10:49:12.127369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12653v2","created_at":"2026-07-05T10:49:12.127369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12653","created_at":"2026-07-05T10:49:12.127369+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAYMTIZYHGP4","created_at":"2026-07-05T10:49:12.127369+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAYMTIZYHGP4QL64","created_at":"2026-07-05T10:49:12.127369+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAYMTIZY","created_at":"2026-07-05T10:49:12.127369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.17070","citing_title":"Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-Start Prediction","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP","json":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP.json","graph_json":"https://pith.science/api/pith-number/YAYMTIZYHGP4QL64CVVOH5T3VP/graph.json","events_json":"https://pith.science/api/pith-number/YAYMTIZYHGP4QL64CVVOH5T3VP/events.json","paper":"https://pith.science/paper/YAYMTIZY"},"agent_actions":{"view_html":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP","download_json":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP.json","view_paper":"https://pith.science/paper/YAYMTIZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12653&json=true","fetch_graph":"https://pith.science/api/pith-number/YAYMTIZYHGP4QL64CVVOH5T3VP/graph.json","fetch_events":"https://pith.science/api/pith-number/YAYMTIZYHGP4QL64CVVOH5T3VP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP/action/storage_attestation","attest_author":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP/action/author_attestation","sign_citation":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP/action/citation_signature","submit_replication":"https://pith.science/pith/YAYMTIZYHGP4QL64CVVOH5T3VP/action/replication_record"}},"created_at":"2026-07-05T10:49:12.127369+00:00","updated_at":"2026-07-05T10:49:12.127369+00:00"}