{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3JTRABSOYMESZWHL652K55EIZV","short_pith_number":"pith:3JTRABSO","schema_version":"1.0","canonical_sha256":"da6710064ec3092cd8ebf774aef488cd577db8cb2f4666906b94e504d67a8d66","source":{"kind":"arxiv","id":"2404.14285","version":3},"attestation_state":"computed","paper":{"title":"LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Adam Jelley, Amos Storkey, Dongge Han, Peter Bell, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2024-04-22T15:35:33Z","abstract_excerpt":"Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household robotics, a critical gap remains in the personalization of these models to individual user preferences. We introduce LLM-Personalize, a novel framework with an optimization pipeline designed to personalize LLM planners for household robotics. Our LLM-Personalize framework features an LLM planner that performs iterative planning in multi-room, partially-observab"},"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":"2404.14285","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-22T15:35:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35555c935c4db999033d53819a9f5fa0941ad494cf5ea75a2a85a7d6bea0e71f","abstract_canon_sha256":"58e329166fed94846be57ac55e15646ad11edc4c4a7f84b120040dc96fcca8cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:09.101630Z","signature_b64":"7/f8563ZmwSdBM+qiy4lyWB3q0wxBw+A99sb8vKVyr+KHWX5OAa3DNPp07k9LkUT5tUshU4N+p1cD9lXQ2vFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da6710064ec3092cd8ebf774aef488cd577db8cb2f4666906b94e504d67a8d66","last_reissued_at":"2026-07-05T09:55:09.101140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:09.101140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Personalize: Aligning LLM Planners with Human Preferences via Reinforced Self-Training for Housekeeping Robots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Adam Jelley, Amos Storkey, Dongge Han, Peter Bell, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2024-04-22T15:35:33Z","abstract_excerpt":"Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household robotics, a critical gap remains in the personalization of these models to individual user preferences. We introduce LLM-Personalize, a novel framework with an optimization pipeline designed to personalize LLM planners for household robotics. Our LLM-Personalize framework features an LLM planner that performs iterative planning in multi-room, partially-observab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14285","kind":"arxiv","version":3},"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/2404.14285/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":"2404.14285","created_at":"2026-07-05T09:55:09.101199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14285v3","created_at":"2026-07-05T09:55:09.101199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14285","created_at":"2026-07-05T09:55:09.101199+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JTRABSOYMES","created_at":"2026-07-05T09:55:09.101199+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JTRABSOYMESZWHL","created_at":"2026-07-05T09:55:09.101199+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JTRABSO","created_at":"2026-07-05T09:55:09.101199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07663","citing_title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV","json":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV.json","graph_json":"https://pith.science/api/pith-number/3JTRABSOYMESZWHL652K55EIZV/graph.json","events_json":"https://pith.science/api/pith-number/3JTRABSOYMESZWHL652K55EIZV/events.json","paper":"https://pith.science/paper/3JTRABSO"},"agent_actions":{"view_html":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV","download_json":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV.json","view_paper":"https://pith.science/paper/3JTRABSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14285&json=true","fetch_graph":"https://pith.science/api/pith-number/3JTRABSOYMESZWHL652K55EIZV/graph.json","fetch_events":"https://pith.science/api/pith-number/3JTRABSOYMESZWHL652K55EIZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV/action/storage_attestation","attest_author":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV/action/author_attestation","sign_citation":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV/action/citation_signature","submit_replication":"https://pith.science/pith/3JTRABSOYMESZWHL652K55EIZV/action/replication_record"}},"created_at":"2026-07-05T09:55:09.101199+00:00","updated_at":"2026-07-05T09:55:09.101199+00:00"}