{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E4JOD2HC6EX3YDZGWL6MEN42SP","short_pith_number":"pith:E4JOD2HC","schema_version":"1.0","canonical_sha256":"2712e1e8e2f12fbc0f26b2fcc2379a93dc6ac2034e0f8e067f2ff8f753a9e233","source":{"kind":"arxiv","id":"2505.05583","version":1},"attestation_state":"computed","paper":{"title":"KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afshin Khadangi, Christophe Zgrzendek, Igor Tchappi, Johannes Sedlmeir, Qianbo Zang","submitted_at":"2025-05-08T18:27:27Z","abstract_excerpt":"Hierarchical Text Classification (HTC) involves assigning documents to labels organized within a taxonomy. Most previous research on HTC has focused on supervised methods. However, in real-world scenarios, employing supervised HTC can be challenging due to a lack of annotated data. Moreover, HTC often faces issues with large label spaces and long-tail distributions. In this work, we present Knowledge Graphs for zero-shot Hierarchical Text Classification (KG-HTC), which aims to address these challenges of HTC in applications by integrating knowledge graphs with Large Language Models (LLMs) to p"},"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":"2505.05583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T18:27:27Z","cross_cats_sorted":[],"title_canon_sha256":"0768a257fa8e81edd1f91d7d437da6c58c86c104627a2e38925c31a02207940d","abstract_canon_sha256":"471af3824d9108f792da55dbee62e00fe8efb330df4e78956d5d1b44c0d2301b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:33.909758Z","signature_b64":"cll5jqfJLHkc214KGXqVhBfLiKkUHD0N0Lv/2kWDOYahH7UNqc+dEJFTueEYe2TDJZewRDo6FIreNunOEcHPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2712e1e8e2f12fbc0f26b2fcc2379a93dc6ac2034e0f8e067f2ff8f753a9e233","last_reissued_at":"2026-05-20T00:01:33.908958Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:33.908958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afshin Khadangi, Christophe Zgrzendek, Igor Tchappi, Johannes Sedlmeir, Qianbo Zang","submitted_at":"2025-05-08T18:27:27Z","abstract_excerpt":"Hierarchical Text Classification (HTC) involves assigning documents to labels organized within a taxonomy. Most previous research on HTC has focused on supervised methods. However, in real-world scenarios, employing supervised HTC can be challenging due to a lack of annotated data. Moreover, HTC often faces issues with large label spaces and long-tail distributions. In this work, we present Knowledge Graphs for zero-shot Hierarchical Text Classification (KG-HTC), which aims to address these challenges of HTC in applications by integrating knowledge graphs with Large Language Models (LLMs) to p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05583","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/2505.05583/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":"2505.05583","created_at":"2026-05-20T00:01:33.909094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05583v1","created_at":"2026-05-20T00:01:33.909094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05583","created_at":"2026-05-20T00:01:33.909094+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4JOD2HC6EX3","created_at":"2026-05-20T00:01:33.909094+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4JOD2HC6EX3YDZG","created_at":"2026-05-20T00:01:33.909094+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4JOD2HC","created_at":"2026-05-20T00:01:33.909094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2601.08418","citing_title":"Taxon: Hierarchical Tax Code Prediction with Semantically Aligned LLM Expert Guidance","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00620","citing_title":"SC-Taxo: Hierarchical Taxonomy Generation under Semantic Consistency Constraints using Large Language Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP","json":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP.json","graph_json":"https://pith.science/api/pith-number/E4JOD2HC6EX3YDZGWL6MEN42SP/graph.json","events_json":"https://pith.science/api/pith-number/E4JOD2HC6EX3YDZGWL6MEN42SP/events.json","paper":"https://pith.science/paper/E4JOD2HC"},"agent_actions":{"view_html":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP","download_json":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP.json","view_paper":"https://pith.science/paper/E4JOD2HC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05583&json=true","fetch_graph":"https://pith.science/api/pith-number/E4JOD2HC6EX3YDZGWL6MEN42SP/graph.json","fetch_events":"https://pith.science/api/pith-number/E4JOD2HC6EX3YDZGWL6MEN42SP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP/action/storage_attestation","attest_author":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP/action/author_attestation","sign_citation":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP/action/citation_signature","submit_replication":"https://pith.science/pith/E4JOD2HC6EX3YDZGWL6MEN42SP/action/replication_record"}},"created_at":"2026-05-20T00:01:33.909094+00:00","updated_at":"2026-05-20T00:01:33.909094+00:00"}