{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ZRDKDQRJARDJOHO3AQ56W5VLN","short_pith_number":"pith:7ZRDKDQR","schema_version":"1.0","canonical_sha256":"fe62350e11482234b8eed821df5bb55b4df8b13c273b43cbee3347165c1dc166","source":{"kind":"arxiv","id":"2507.16672","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengrui Zhou, Dannier Li, Huijie Shen, Lu Chang, Yinuo Yang, Yushang Zhao","submitted_at":"2025-07-22T15:07:23Z","abstract_excerpt":"Generative, explainable, and flexible recommender systems, derived using Large Language Models (LLM) are promising and poorly adapted to the cold-start user situation, where there is little to no history of interaction. The current solutions i.e. supervised fine-tuning and collaborative filtering are dense-user-item focused and would be expensive to maintain and update. This paper introduces a meta-learning framework, that can be used to perform parameter-efficient prompt-tuning, to effectively personalize LLM-based recommender systems quickly at cold-start. The model learns soft prompt embedd"},"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":"2507.16672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T15:07:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"03e914cc2449aedea27f79b91f91f76e28b172db3ecc1a9f3ba858cbac599d0b","abstract_canon_sha256":"60299f58c51a721a599a75d65c3536a1ad90562b33a56e7f3a812edc3f88ee5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:28.912244Z","signature_b64":"+Et7vcI99Xv/uZrLLcuAXGPR9xDt+i3HUt+OrAgh2KNULCb+tbeguK4JEA7t9FIziT8ozYNrKJ2eKFCPq9BQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe62350e11482234b8eed821df5bb55b4df8b13c273b43cbee3347165c1dc166","last_reissued_at":"2026-07-05T11:41:28.911758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:28.911758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning for Cold-Start Personalization in Prompt-Tuned LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengrui Zhou, Dannier Li, Huijie Shen, Lu Chang, Yinuo Yang, Yushang Zhao","submitted_at":"2025-07-22T15:07:23Z","abstract_excerpt":"Generative, explainable, and flexible recommender systems, derived using Large Language Models (LLM) are promising and poorly adapted to the cold-start user situation, where there is little to no history of interaction. The current solutions i.e. supervised fine-tuning and collaborative filtering are dense-user-item focused and would be expensive to maintain and update. This paper introduces a meta-learning framework, that can be used to perform parameter-efficient prompt-tuning, to effectively personalize LLM-based recommender systems quickly at cold-start. The model learns soft prompt embedd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16672","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/2507.16672/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":"2507.16672","created_at":"2026-07-05T11:41:28.911815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16672v1","created_at":"2026-07-05T11:41:28.911815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16672","created_at":"2026-07-05T11:41:28.911815+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZRDKDQRJARD","created_at":"2026-07-05T11:41:28.911815+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZRDKDQRJARDJOHO","created_at":"2026-07-05T11:41:28.911815+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZRDKDQR","created_at":"2026-07-05T11:41:28.911815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04751","citing_title":"Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN","json":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN.json","graph_json":"https://pith.science/api/pith-number/7ZRDKDQRJARDJOHO3AQ56W5VLN/graph.json","events_json":"https://pith.science/api/pith-number/7ZRDKDQRJARDJOHO3AQ56W5VLN/events.json","paper":"https://pith.science/paper/7ZRDKDQR"},"agent_actions":{"view_html":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN","download_json":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN.json","view_paper":"https://pith.science/paper/7ZRDKDQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16672&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZRDKDQRJARDJOHO3AQ56W5VLN/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZRDKDQRJARDJOHO3AQ56W5VLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN/action/storage_attestation","attest_author":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN/action/author_attestation","sign_citation":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN/action/citation_signature","submit_replication":"https://pith.science/pith/7ZRDKDQRJARDJOHO3AQ56W5VLN/action/replication_record"}},"created_at":"2026-07-05T11:41:28.911815+00:00","updated_at":"2026-07-05T11:41:28.911815+00:00"}