{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z4XHBC6MV64DVJTY3ARM5MU5UA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"49903dc327e67d5c8da8597bfd9a4a11ded5cd5e0024530f2bb8519115d29c73","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-03T11:37:46Z","title_canon_sha256":"6f686b97d2f886e94fc24a8c91bc3d4f95a1849657e1dd435ab6b20bbc83a3d8"},"schema_version":"1.0","source":{"id":"2601.01162","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.01162","created_at":"2026-05-29T01:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2601.01162v3","created_at":"2026-05-29T01:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.01162","created_at":"2026-05-29T01:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z4XHBC6MV64D","created_at":"2026-05-29T01:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z4XHBC6MV64DVJTY","created_at":"2026-05-29T01:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z4XHBC6M","created_at":"2026-05-29T01:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:f9532433499fc890fb7b0ad4b12b76f425be093d2ac78e21d391586b05bc8fce","target":"graph","created_at":"2026-05-29T01:05:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on eight benchmark datasets demonstrate consistent improvements over seven representative counterparts, with gains of 19-27%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods."}],"snapshot_sha256":"ec958ae73bfe1390e2d0422f540ab0139e49963b22e5b176e29ea22b6424bd37"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.01162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Xin Liao, Yiqun Zhang, Yiu-ming Cheung, Zihua Yang","cross_cats":["cs.AI","cs.CL"],"headline":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-03T11:37:46Z","title":"Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.01162","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T18:02:03.643604Z","id":"52a8420f-9de6-4304-b091-904471b7c303","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"LLM-generated semantic descriptions of categorical values, when fused into embeddings, measurably improve clustering quality over standard methods.","strongest_claim":"Experiments on eight benchmark datasets demonstrate consistent improvements over seven representative counterparts, with gains of 19-27%.","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."}},"verdict_id":"52a8420f-9de6-4304-b091-904471b7c303"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e632fcdfe272aafa8fa07940607fe0032dfe36c0e41fdf607b1855de5d703792","target":"record","created_at":"2026-05-29T01:05:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"49903dc327e67d5c8da8597bfd9a4a11ded5cd5e0024530f2bb8519115d29c73","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-03T11:37:46Z","title_canon_sha256":"6f686b97d2f886e94fc24a8c91bc3d4f95a1849657e1dd435ab6b20bbc83a3d8"},"schema_version":"1.0","source":{"id":"2601.01162","kind":"arxiv","version":3}},"canonical_sha256":"cf2e708bccafb83aa678d822ceb29da009baef00a24ca785070d7d0e0e3ce8ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf2e708bccafb83aa678d822ceb29da009baef00a24ca785070d7d0e0e3ce8ab","first_computed_at":"2026-05-29T01:05:01.000829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:01.000829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vDg5HLghS+K64MxU2ArGRtmFnrXrRyCz9rTMV1J7wKtxT/2PZ3j8d2e0UDIjpnL4HmDUHbFFx609Tb+nTMlBw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:01.001641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.01162","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e632fcdfe272aafa8fa07940607fe0032dfe36c0e41fdf607b1855de5d703792","sha256:f9532433499fc890fb7b0ad4b12b76f425be093d2ac78e21d391586b05bc8fce"],"state_sha256":"c42efee1caa1d84dafabb9fa5d0794bf0547c47a39ba4c672b00a37157908aa8"}