{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HXTPRVTEELJW4Y24QQDWSARFX7","short_pith_number":"pith:HXTPRVTE","schema_version":"1.0","canonical_sha256":"3de6f8d66422d36e635c8407690225bff32c84c1ccf0e6791d062702b61c2852","source":{"kind":"arxiv","id":"2506.04015","version":1},"attestation_state":"computed","paper":{"title":"GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Deqing Yang, Hengrui Chen, Jiaqing Liang, Peng Yu, Tiehua Mei","submitted_at":"2025-06-04T14:46:18Z","abstract_excerpt":"Although large language models (LLMs) have shown great potential in recommender systems, the prohibitive computational costs for fine-tuning LLMs on entire datasets hinder their successful deployment in real-world scenarios. To develop affordable and effective LLM-based recommender systems, we focus on the task of coreset selection which identifies a small subset of fine-tuning data to optimize the test loss, thereby facilitating efficient LLMs' fine-tuning. Although there exist some intuitive solutions of subset selection, including distribution-based and importance-based approaches, they oft"},"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":"2506.04015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-04T14:46:18Z","cross_cats_sorted":[],"title_canon_sha256":"30b51d3b969da4ab8d46f019a586ceb974a228bbc52169e41274e451e0e2a501","abstract_canon_sha256":"643ad906ea5b83d13dc25a5110bc1d097d3f2f4b1c3360708b21a2c67794b0ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:18.901020Z","signature_b64":"S33jZv3U0KfFUI0JBul8jev/LxTzYCTSooHyn9okzNdELSb+VXYtRt6F8ujg4uDiJUxS1hNMPzcHgD5REZ8xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3de6f8d66422d36e635c8407690225bff32c84c1ccf0e6791d062702b61c2852","last_reissued_at":"2026-07-05T11:22:18.900500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:18.900500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Deqing Yang, Hengrui Chen, Jiaqing Liang, Peng Yu, Tiehua Mei","submitted_at":"2025-06-04T14:46:18Z","abstract_excerpt":"Although large language models (LLMs) have shown great potential in recommender systems, the prohibitive computational costs for fine-tuning LLMs on entire datasets hinder their successful deployment in real-world scenarios. To develop affordable and effective LLM-based recommender systems, we focus on the task of coreset selection which identifies a small subset of fine-tuning data to optimize the test loss, thereby facilitating efficient LLMs' fine-tuning. Although there exist some intuitive solutions of subset selection, including distribution-based and importance-based approaches, they oft"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04015","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/2506.04015/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":"2506.04015","created_at":"2026-07-05T11:22:18.900563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04015v1","created_at":"2026-07-05T11:22:18.900563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04015","created_at":"2026-07-05T11:22:18.900563+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXTPRVTEELJW","created_at":"2026-07-05T11:22:18.900563+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXTPRVTEELJW4Y24","created_at":"2026-07-05T11:22:18.900563+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXTPRVTE","created_at":"2026-07-05T11:22:18.900563+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7","json":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7.json","graph_json":"https://pith.science/api/pith-number/HXTPRVTEELJW4Y24QQDWSARFX7/graph.json","events_json":"https://pith.science/api/pith-number/HXTPRVTEELJW4Y24QQDWSARFX7/events.json","paper":"https://pith.science/paper/HXTPRVTE"},"agent_actions":{"view_html":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7","download_json":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7.json","view_paper":"https://pith.science/paper/HXTPRVTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04015&json=true","fetch_graph":"https://pith.science/api/pith-number/HXTPRVTEELJW4Y24QQDWSARFX7/graph.json","fetch_events":"https://pith.science/api/pith-number/HXTPRVTEELJW4Y24QQDWSARFX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7/action/storage_attestation","attest_author":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7/action/author_attestation","sign_citation":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7/action/citation_signature","submit_replication":"https://pith.science/pith/HXTPRVTEELJW4Y24QQDWSARFX7/action/replication_record"}},"created_at":"2026-07-05T11:22:18.900563+00:00","updated_at":"2026-07-05T11:22:18.900563+00:00"}