{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D4I4C3DOAVOWVN5WEQ4PH64BXC","short_pith_number":"pith:D4I4C3DO","schema_version":"1.0","canonical_sha256":"1f11c16c6e055d6ab7b62438f3fb81b897a2547fc20610feb983cbd9d060ca03","source":{"kind":"arxiv","id":"2310.18297","version":4},"attestation_state":"computed","paper":{"title":"Image Clustering Conditioned on Text Criteria","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ernest K. Ryu, Jaeseung Park, Jaewoong Cho, Kangwook Lee, Minkyu Kim, Sehyun Kwon","submitted_at":"2023-10-27T17:35:01Z","abstract_excerpt":"Classical clustering methods do not provide users with direct control of the clustering results, and the clustering results may not be consistent with the relevant criterion that a user has in mind. In this work, we present a new methodology for performing image clustering based on user-specified text criteria by leveraging modern vision-language models and large language models. We call our method Image Clustering Conditioned on Text Criteria (IC|TC), and it represents a different paradigm of image clustering. IC|TC requires a minimal and practical degree of human intervention and grants the "},"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":"2310.18297","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-27T17:35:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f7e7009aee2c47a78aa1c16d4a7909233495b1ce4a2e4d5946b16f3591064f2b","abstract_canon_sha256":"d7b1c41b14527133d53be285279549bdbe13ede6e5a733ca0d5f101bdbb8af02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:00.502851Z","signature_b64":"BHDxIT5r26ZCE+Gp8jnzEQUx6JMu1vE1cL+Ih9wVouWR8Emc8MJdMkw4gh9Miz+2ImhzfyjPhroD17IKN/1WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f11c16c6e055d6ab7b62438f3fb81b897a2547fc20610feb983cbd9d060ca03","last_reissued_at":"2026-07-05T07:48:00.502406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:00.502406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Clustering Conditioned on Text Criteria","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ernest K. Ryu, Jaeseung Park, Jaewoong Cho, Kangwook Lee, Minkyu Kim, Sehyun Kwon","submitted_at":"2023-10-27T17:35:01Z","abstract_excerpt":"Classical clustering methods do not provide users with direct control of the clustering results, and the clustering results may not be consistent with the relevant criterion that a user has in mind. In this work, we present a new methodology for performing image clustering based on user-specified text criteria by leveraging modern vision-language models and large language models. We call our method Image Clustering Conditioned on Text Criteria (IC|TC), and it represents a different paradigm of image clustering. IC|TC requires a minimal and practical degree of human intervention and grants the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18297","kind":"arxiv","version":4},"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/2310.18297/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":"2310.18297","created_at":"2026-07-05T07:48:00.502466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18297v4","created_at":"2026-07-05T07:48:00.502466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18297","created_at":"2026-07-05T07:48:00.502466+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4I4C3DOAVOW","created_at":"2026-07-05T07:48:00.502466+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4I4C3DOAVOWVN5W","created_at":"2026-07-05T07:48:00.502466+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4I4C3DO","created_at":"2026-07-05T07:48:00.502466+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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28517","citing_title":"Drag, Infer, Reproject: Grounding LLMs through Spatial Interaction for Image Clustering","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC","json":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC.json","graph_json":"https://pith.science/api/pith-number/D4I4C3DOAVOWVN5WEQ4PH64BXC/graph.json","events_json":"https://pith.science/api/pith-number/D4I4C3DOAVOWVN5WEQ4PH64BXC/events.json","paper":"https://pith.science/paper/D4I4C3DO"},"agent_actions":{"view_html":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC","download_json":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC.json","view_paper":"https://pith.science/paper/D4I4C3DO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18297&json=true","fetch_graph":"https://pith.science/api/pith-number/D4I4C3DOAVOWVN5WEQ4PH64BXC/graph.json","fetch_events":"https://pith.science/api/pith-number/D4I4C3DOAVOWVN5WEQ4PH64BXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC/action/storage_attestation","attest_author":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC/action/author_attestation","sign_citation":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC/action/citation_signature","submit_replication":"https://pith.science/pith/D4I4C3DOAVOWVN5WEQ4PH64BXC/action/replication_record"}},"created_at":"2026-07-05T07:48:00.502466+00:00","updated_at":"2026-07-05T07:48:00.502466+00:00"}