{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ABW67QLAEV7JCWZDLLLGVW5YRV","short_pith_number":"pith:ABW67QLA","schema_version":"1.0","canonical_sha256":"006defc160257e915b235ad66adbb88d64cdd489e23bfc72e115e7cf5b5e5d7c","source":{"kind":"arxiv","id":"2503.22241","version":3},"attestation_state":"computed","paper":{"title":"Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mingming Gong, Riheng Zhu, Yiqun Duan, Zhenbang Sun, Ziye Chen","submitted_at":"2025-03-28T08:45:15Z","abstract_excerpt":"Personalized multiple clustering aims to generate diverse partitions of a dataset based on different user-specific aspects, rather than a single clustering. It has recently drawn research interest for accommodating varying user preferences. Recent approaches primarily use CLIP embeddings with proxy learning to extract representations biased toward user clustering preferences. However, CLIP primarily focuses on coarse image-text alignment, lacking a deep contextual understanding of user interests. To overcome these limitations, we propose an agent-centric personalized clustering framework that "},"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":"2503.22241","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-28T08:45:15Z","cross_cats_sorted":[],"title_canon_sha256":"69f8ae882864c51211330699dd4f69f225161c40761c4f02894055adbfad4273","abstract_canon_sha256":"4d1c25563d3b1d57ea5eab22793c8b7c30b21ef7070d5051fe134917f24c4d49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:55.002380Z","signature_b64":"EcE4pV0KY3PQEhGTzoDCclA8gR3pvb/dAGeW6jeFJ+4tNHY0TCl+O8CdhDHdY1jZiddFXhuSpmd3OFXMpfR7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"006defc160257e915b235ad66adbb88d64cdd489e23bfc72e115e7cf5b5e5d7c","last_reissued_at":"2026-07-05T11:10:55.001826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:55.001826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mingming Gong, Riheng Zhu, Yiqun Duan, Zhenbang Sun, Ziye Chen","submitted_at":"2025-03-28T08:45:15Z","abstract_excerpt":"Personalized multiple clustering aims to generate diverse partitions of a dataset based on different user-specific aspects, rather than a single clustering. It has recently drawn research interest for accommodating varying user preferences. Recent approaches primarily use CLIP embeddings with proxy learning to extract representations biased toward user clustering preferences. However, CLIP primarily focuses on coarse image-text alignment, lacking a deep contextual understanding of user interests. To overcome these limitations, we propose an agent-centric personalized clustering framework that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22241","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/2503.22241/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":"2503.22241","created_at":"2026-07-05T11:10:55.001884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22241v3","created_at":"2026-07-05T11:10:55.001884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22241","created_at":"2026-07-05T11:10:55.001884+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABW67QLAEV7J","created_at":"2026-07-05T11:10:55.001884+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABW67QLAEV7JCWZD","created_at":"2026-07-05T11:10:55.001884+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABW67QLA","created_at":"2026-07-05T11:10:55.001884+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24094","citing_title":"Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01255","citing_title":"Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinement","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV","json":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV.json","graph_json":"https://pith.science/api/pith-number/ABW67QLAEV7JCWZDLLLGVW5YRV/graph.json","events_json":"https://pith.science/api/pith-number/ABW67QLAEV7JCWZDLLLGVW5YRV/events.json","paper":"https://pith.science/paper/ABW67QLA"},"agent_actions":{"view_html":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV","download_json":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV.json","view_paper":"https://pith.science/paper/ABW67QLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22241&json=true","fetch_graph":"https://pith.science/api/pith-number/ABW67QLAEV7JCWZDLLLGVW5YRV/graph.json","fetch_events":"https://pith.science/api/pith-number/ABW67QLAEV7JCWZDLLLGVW5YRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV/action/storage_attestation","attest_author":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV/action/author_attestation","sign_citation":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV/action/citation_signature","submit_replication":"https://pith.science/pith/ABW67QLAEV7JCWZDLLLGVW5YRV/action/replication_record"}},"created_at":"2026-07-05T11:10:55.001884+00:00","updated_at":"2026-07-05T11:10:55.001884+00:00"}