{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3GALIFUSMIJWKYF5IUQCYQ3CIF","short_pith_number":"pith:3GALIFUS","schema_version":"1.0","canonical_sha256":"d980b4169262136560bd45202c4362414a7088601b6d4827099458a486507a70","source":{"kind":"arxiv","id":"2405.19686","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingwei Sun, Yiran Chen, Zhixu Du","submitted_at":"2024-05-30T04:57:03Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable proficiency in a range of natural language processing tasks. Once deployed, LLMs encounter users with personalized factual knowledge, and such personalized knowledge is consistently reflected through users' interactions with the LLMs. To enhance user experience, real-time model personalization is essential, allowing LLMs to adapt user-specific knowledge based on user feedback during human-LLM interactions. Existing methods mostly require back-propagation to finetune the model parameters, which incurs high computational and memory costs."},"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":"2405.19686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-30T04:57:03Z","cross_cats_sorted":[],"title_canon_sha256":"4b4b3004533036514026fba2b658b68e1ad6f893a96f9ebdb2146dfef9b7dec0","abstract_canon_sha256":"df25f580ba2d1d84c455dd923237cbbce01d249b3d4399e262691fc2ba66047d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:11.180301Z","signature_b64":"3gBzo2xTRnrw6YFxixF0P0QYfwmm6YVFedJsDI5CyqbQpgPDV8Y2F2YfAtkmnn1ag3cu612CroUPY0YnwESnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d980b4169262136560bd45202c4362414a7088601b6d4827099458a486507a70","last_reissued_at":"2026-07-05T08:25:11.179888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:11.179888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingwei Sun, Yiran Chen, Zhixu Du","submitted_at":"2024-05-30T04:57:03Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable proficiency in a range of natural language processing tasks. Once deployed, LLMs encounter users with personalized factual knowledge, and such personalized knowledge is consistently reflected through users' interactions with the LLMs. To enhance user experience, real-time model personalization is essential, allowing LLMs to adapt user-specific knowledge based on user feedback during human-LLM interactions. Existing methods mostly require back-propagation to finetune the model parameters, which incurs high computational and memory costs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19686","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/2405.19686/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":"2405.19686","created_at":"2026-07-05T08:25:11.179944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19686v1","created_at":"2026-07-05T08:25:11.179944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19686","created_at":"2026-07-05T08:25:11.179944+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GALIFUSMIJW","created_at":"2026-07-05T08:25:11.179944+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GALIFUSMIJWKYF5","created_at":"2026-07-05T08:25:11.179944+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GALIFUS","created_at":"2026-07-05T08:25:11.179944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.15965","citing_title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06845","citing_title":"HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15676","citing_title":"EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF","json":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF.json","graph_json":"https://pith.science/api/pith-number/3GALIFUSMIJWKYF5IUQCYQ3CIF/graph.json","events_json":"https://pith.science/api/pith-number/3GALIFUSMIJWKYF5IUQCYQ3CIF/events.json","paper":"https://pith.science/paper/3GALIFUS"},"agent_actions":{"view_html":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF","download_json":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF.json","view_paper":"https://pith.science/paper/3GALIFUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19686&json=true","fetch_graph":"https://pith.science/api/pith-number/3GALIFUSMIJWKYF5IUQCYQ3CIF/graph.json","fetch_events":"https://pith.science/api/pith-number/3GALIFUSMIJWKYF5IUQCYQ3CIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF/action/storage_attestation","attest_author":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF/action/author_attestation","sign_citation":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF/action/citation_signature","submit_replication":"https://pith.science/pith/3GALIFUSMIJWKYF5IUQCYQ3CIF/action/replication_record"}},"created_at":"2026-07-05T08:25:11.179944+00:00","updated_at":"2026-07-05T08:25:11.179944+00:00"}