{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZYACM3DLRJJTUBTDDWLO7XLRNB","short_pith_number":"pith:ZYACM3DL","schema_version":"1.0","canonical_sha256":"ce00266c6b8a533a06631d96efdd71684bd8705e281273bc89711adb58c6130e","source":{"kind":"arxiv","id":"2301.02458","version":3},"attestation_state":"computed","paper":{"title":"Topics as Entity Clusters: Entity-based Topics from Large Language Models and Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya","submitted_at":"2023-01-06T10:54:54Z","abstract_excerpt":"Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable, language-independent features linked to external knowledge resources -- have been used in place of word-level tokens, as words typically require extensive language processing with a minimal assurance of interpretability. However, current literature is limited when it comes to exploring purely entity-driven neural topic modeling. For instance, despite the advantages of"},"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":"2301.02458","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-06T10:54:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e043710f7e9108a7473b24671e4735ad73fd56a7bef7f459f2f7586619846f48","abstract_canon_sha256":"84ea5ddec03cca3f6a15ec6dc538c632317a187cb69d9a08c08eace25dbad552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:02.169149Z","signature_b64":"h0zAIg/afSy4H2+mtvL5khoVDJ+MCXcO1CqQmeFOEw1kDMdQelxFGR5TDj0pPRWZk1omFQZvIJPJK3uTRmIGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce00266c6b8a533a06631d96efdd71684bd8705e281273bc89711adb58c6130e","last_reissued_at":"2026-07-05T08:59:02.168727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:02.168727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Topics as Entity Clusters: Entity-based Topics from Large Language Models and Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Manuel V. Loureiro, Steven Derby, Tri Kurniawan Wijaya","submitted_at":"2023-01-06T10:54:54Z","abstract_excerpt":"Topic models aim to reveal latent structures within a corpus of text, typically through the use of term-frequency statistics over bag-of-words representations from documents. In recent years, conceptual entities -- interpretable, language-independent features linked to external knowledge resources -- have been used in place of word-level tokens, as words typically require extensive language processing with a minimal assurance of interpretability. However, current literature is limited when it comes to exploring purely entity-driven neural topic modeling. For instance, despite the advantages of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02458","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/2301.02458/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":"2301.02458","created_at":"2026-07-05T08:59:02.168783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02458v3","created_at":"2026-07-05T08:59:02.168783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02458","created_at":"2026-07-05T08:59:02.168783+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYACM3DLRJJT","created_at":"2026-07-05T08:59:02.168783+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYACM3DLRJJTUBTD","created_at":"2026-07-05T08:59:02.168783+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYACM3DL","created_at":"2026-07-05T08:59:02.168783+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/ZYACM3DLRJJTUBTDDWLO7XLRNB","json":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB.json","graph_json":"https://pith.science/api/pith-number/ZYACM3DLRJJTUBTDDWLO7XLRNB/graph.json","events_json":"https://pith.science/api/pith-number/ZYACM3DLRJJTUBTDDWLO7XLRNB/events.json","paper":"https://pith.science/paper/ZYACM3DL"},"agent_actions":{"view_html":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB","download_json":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB.json","view_paper":"https://pith.science/paper/ZYACM3DL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02458&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYACM3DLRJJTUBTDDWLO7XLRNB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYACM3DLRJJTUBTDDWLO7XLRNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB/action/storage_attestation","attest_author":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB/action/author_attestation","sign_citation":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB/action/citation_signature","submit_replication":"https://pith.science/pith/ZYACM3DLRJJTUBTDDWLO7XLRNB/action/replication_record"}},"created_at":"2026-07-05T08:59:02.168783+00:00","updated_at":"2026-07-05T08:59:02.168783+00:00"}