{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z4XHBC6MV64DVJTY3ARM5MU5UA","short_pith_number":"pith:Z4XHBC6M","schema_version":"1.0","canonical_sha256":"cf2e708bccafb83aa678d822ceb29da009baef00a24ca785070d7d0e0e3ce8ab","source":{"kind":"arxiv","id":"2601.01162","version":3},"attestation_state":"computed","paper":{"title":"Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Xin Liao, Yiqun Zhang, Yiu-ming Cheung, Zihua Yang","submitted_at":"2026-01-03T11:37:46Z","abstract_excerpt":"Qualitative data are widespread in domains such as healthcare, marketing, and bioinformatics, where clustering offers a fundamental tool for pattern discovery. A core difficulty of qualitative-data clustering lies in measuring similarity among attribute values that carry no inherent ordering or distance. To recover such relationships, existing studies typically rely on within-dataset co-occurrence statistics. This statistical route, however, becomes unreliable once the sample size is small, and the semantic context of each value is therefore left underexploited. Motivated by this limitation, t"},"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":"2601.01162","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-03T11:37:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6f686b97d2f886e94fc24a8c91bc3d4f95a1849657e1dd435ab6b20bbc83a3d8","abstract_canon_sha256":"49903dc327e67d5c8da8597bfd9a4a11ded5cd5e0024530f2bb8519115d29c73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:01.001641Z","signature_b64":"7vDg5HLghS+K64MxU2ArGRtmFnrXrRyCz9rTMV1J7wKtxT/2PZ3j8d2e0UDIjpnL4HmDUHbFFx609Tb+nTMlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf2e708bccafb83aa678d822ceb29da009baef00a24ca785070d7d0e0e3ce8ab","last_reissued_at":"2026-05-29T01:05:01.000829Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:01.000829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Xin Liao, Yiqun Zhang, Yiu-ming Cheung, Zihua Yang","submitted_at":"2026-01-03T11:37:46Z","abstract_excerpt":"Qualitative data are widespread in domains such as healthcare, marketing, and bioinformatics, where clustering offers a fundamental tool for pattern discovery. A core difficulty of qualitative-data clustering lies in measuring similarity among attribute values that carry no inherent ordering or distance. To recover such relationships, existing studies typically rely on within-dataset co-occurrence statistics. This statistical route, however, becomes unreliable once the sample size is small, and the semantic context of each value is therefore left underexploited. Motivated by this limitation, t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on eight benchmark datasets demonstrate consistent improvements over seven representative counterparts, with gains of 19-27%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-generated descriptions of attribute values provide reliable, unbiased semantic knowledge that meaningfully complements the original categorical metric space without introducing hallucinations or domain mismatches.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ARISE integrates LLM-generated semantic embeddings with categorical data representations to bridge the similarity gap, achieving 19-27% gains over seven baselines on eight benchmark datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ec958ae73bfe1390e2d0422f540ab0139e49963b22e5b176e29ea22b6424bd37"},"source":{"id":"2601.01162","kind":"arxiv","version":3},"verdict":{"id":"52a8420f-9de6-4304-b091-904471b7c303","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T18:02:03.643604Z","strongest_claim":"Experiments on eight benchmark datasets demonstrate consistent improvements over seven representative counterparts, with gains of 19-27%.","one_line_summary":"ARISE integrates LLM-generated semantic embeddings with categorical data representations to bridge the similarity gap, achieving 19-27% gains over seven baselines on eight benchmark datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-generated descriptions of attribute values provide reliable, unbiased semantic knowledge that meaningfully complements the original categorical metric space without introducing hallucinations or domain mismatches.","pith_extraction_headline":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.01162/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":"2601.01162","created_at":"2026-05-29T01:05:01.000910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.01162v3","created_at":"2026-05-29T01:05:01.000910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.01162","created_at":"2026-05-29T01:05:01.000910+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4XHBC6MV64D","created_at":"2026-05-29T01:05:01.000910+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4XHBC6MV64DVJTY","created_at":"2026-05-29T01:05:01.000910+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4XHBC6M","created_at":"2026-05-29T01:05:01.000910+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/Z4XHBC6MV64DVJTY3ARM5MU5UA","json":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA.json","graph_json":"https://pith.science/api/pith-number/Z4XHBC6MV64DVJTY3ARM5MU5UA/graph.json","events_json":"https://pith.science/api/pith-number/Z4XHBC6MV64DVJTY3ARM5MU5UA/events.json","paper":"https://pith.science/paper/Z4XHBC6M"},"agent_actions":{"view_html":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA","download_json":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA.json","view_paper":"https://pith.science/paper/Z4XHBC6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.01162&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4XHBC6MV64DVJTY3ARM5MU5UA/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4XHBC6MV64DVJTY3ARM5MU5UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA/action/storage_attestation","attest_author":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA/action/author_attestation","sign_citation":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA/action/citation_signature","submit_replication":"https://pith.science/pith/Z4XHBC6MV64DVJTY3ARM5MU5UA/action/replication_record"}},"created_at":"2026-05-29T01:05:01.000910+00:00","updated_at":"2026-05-29T01:05:01.000910+00:00"}