{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MLNAWD6YJK2TOUBPS77M6WZ36X","short_pith_number":"pith:MLNAWD6Y","schema_version":"1.0","canonical_sha256":"62da0b0fd84ab537502f97fecf5b3bf5d529a4bb4ffaa9df66917031555bb801","source":{"kind":"arxiv","id":"2404.19146","version":1},"attestation_state":"computed","paper":{"title":"Automated Construction of Theme-specific Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Jiawei Han, Jinfeng Xiao, Linyi Ding, Sizhe Zhou","submitted_at":"2024-04-29T23:14:14Z","abstract_excerpt":"Despite widespread applications of knowledge graphs (KGs) in various tasks such as question answering and intelligent conversational systems, existing KGs face two major challenges: information granularity and deficiency in timeliness. These hinder considerably the retrieval and analysis of in-context, fine-grained, and up-to-date knowledge from KGs, particularly in highly specialized themes (e.g., specialized scientific research) and rapidly evolving contexts (e.g., breaking news or disaster tracking). To tackle such challenges, we propose a theme-specific knowledge graph (i.e., ThemeKG), a K"},"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":"2404.19146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-04-29T23:14:14Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"90c02c4c318820fd290695f5b9e9933b02c494327d16da2cdec4fb099c90bbef","abstract_canon_sha256":"fffbc93b4f4c01ad3cc557a6a0f49f47d58bae04d7c1f2c88036ffee0019998a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:38.358661Z","signature_b64":"zzNRpA4jOSoQqUxikuFEqj3ZKEaZMzrsfFo2y5NKPRc2BkmpOeYT3g3XMdxN6nU1HDMqiK4EXjkpOvysU2MxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62da0b0fd84ab537502f97fecf5b3bf5d529a4bb4ffaa9df66917031555bb801","last_reissued_at":"2026-07-05T08:13:38.358157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:38.358157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Construction of Theme-specific Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Jiawei Han, Jinfeng Xiao, Linyi Ding, Sizhe Zhou","submitted_at":"2024-04-29T23:14:14Z","abstract_excerpt":"Despite widespread applications of knowledge graphs (KGs) in various tasks such as question answering and intelligent conversational systems, existing KGs face two major challenges: information granularity and deficiency in timeliness. These hinder considerably the retrieval and analysis of in-context, fine-grained, and up-to-date knowledge from KGs, particularly in highly specialized themes (e.g., specialized scientific research) and rapidly evolving contexts (e.g., breaking news or disaster tracking). To tackle such challenges, we propose a theme-specific knowledge graph (i.e., ThemeKG), a K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19146","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/2404.19146/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":"2404.19146","created_at":"2026-07-05T08:13:38.358220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19146v1","created_at":"2026-07-05T08:13:38.358220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19146","created_at":"2026-07-05T08:13:38.358220+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLNAWD6YJK2T","created_at":"2026-07-05T08:13:38.358220+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLNAWD6YJK2TOUBP","created_at":"2026-07-05T08:13:38.358220+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLNAWD6Y","created_at":"2026-07-05T08:13:38.358220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19366","citing_title":"Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03540","citing_title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X","json":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X.json","graph_json":"https://pith.science/api/pith-number/MLNAWD6YJK2TOUBPS77M6WZ36X/graph.json","events_json":"https://pith.science/api/pith-number/MLNAWD6YJK2TOUBPS77M6WZ36X/events.json","paper":"https://pith.science/paper/MLNAWD6Y"},"agent_actions":{"view_html":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X","download_json":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X.json","view_paper":"https://pith.science/paper/MLNAWD6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19146&json=true","fetch_graph":"https://pith.science/api/pith-number/MLNAWD6YJK2TOUBPS77M6WZ36X/graph.json","fetch_events":"https://pith.science/api/pith-number/MLNAWD6YJK2TOUBPS77M6WZ36X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X/action/storage_attestation","attest_author":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X/action/author_attestation","sign_citation":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X/action/citation_signature","submit_replication":"https://pith.science/pith/MLNAWD6YJK2TOUBPS77M6WZ36X/action/replication_record"}},"created_at":"2026-07-05T08:13:38.358220+00:00","updated_at":"2026-07-05T08:13:38.358220+00:00"}