{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YHKMQZU6MWYNX7EXBGSOJLRFUY","short_pith_number":"pith:YHKMQZU6","schema_version":"1.0","canonical_sha256":"c1d4c8669e65b0dbfc9709a4e4ae25a614f9d278324e0fc4570df392b14eca6e","source":{"kind":"arxiv","id":"2503.07584","version":3},"attestation_state":"computed","paper":{"title":"Talking to GDELT Through Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Audun Myers, Benjamin Wilson, Cliff Joslyn, Lee Burke, Max Vargas, Sinan G. Aksoy, Tom Grimes","submitted_at":"2025-03-10T17:48:10Z","abstract_excerpt":"In this work we study various Retrieval Augmented Regeneration (RAG) approaches to gain an understanding of the strengths and weaknesses of each approach in a question-answering analysis. To gain this understanding we use a case-study subset of the Global Database of Events, Language, and Tone (GDELT) dataset as well as a corpus of raw text scraped from the online news articles. To retrieve information from the text corpus we implement a traditional vector store RAG as well as state-of-the-art large language model (LLM) based approaches for automatically constructing KGs and retrieving the rel"},"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":"2503.07584","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-10T17:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"e6068a0ef3949e5c8f9dc0c1f4ded74323b8f95b8cf4a1aafc2736a93001bbc6","abstract_canon_sha256":"7f8ee83f88c52c714b43929f854aa46dfdd3a306eaf0487be38288a8b4b8f5cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:03.347145Z","signature_b64":"4jf46D2swSWT69yNYWuH7e7b+rOIAAQBQxJlWo9nD3LvoUyPiwGsDam271vIQMoR6AvJpA7L1jGjLqydniB1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1d4c8669e65b0dbfc9709a4e4ae25a614f9d278324e0fc4570df392b14eca6e","last_reissued_at":"2026-07-05T11:26:03.346685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:03.346685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Talking to GDELT Through Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Audun Myers, Benjamin Wilson, Cliff Joslyn, Lee Burke, Max Vargas, Sinan G. Aksoy, Tom Grimes","submitted_at":"2025-03-10T17:48:10Z","abstract_excerpt":"In this work we study various Retrieval Augmented Regeneration (RAG) approaches to gain an understanding of the strengths and weaknesses of each approach in a question-answering analysis. To gain this understanding we use a case-study subset of the Global Database of Events, Language, and Tone (GDELT) dataset as well as a corpus of raw text scraped from the online news articles. To retrieve information from the text corpus we implement a traditional vector store RAG as well as state-of-the-art large language model (LLM) based approaches for automatically constructing KGs and retrieving the rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07584","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/2503.07584/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":"2503.07584","created_at":"2026-07-05T11:26:03.346740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07584v3","created_at":"2026-07-05T11:26:03.346740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07584","created_at":"2026-07-05T11:26:03.346740+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHKMQZU6MWYN","created_at":"2026-07-05T11:26:03.346740+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHKMQZU6MWYNX7EX","created_at":"2026-07-05T11:26:03.346740+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHKMQZU6","created_at":"2026-07-05T11:26:03.346740+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/YHKMQZU6MWYNX7EXBGSOJLRFUY","json":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY.json","graph_json":"https://pith.science/api/pith-number/YHKMQZU6MWYNX7EXBGSOJLRFUY/graph.json","events_json":"https://pith.science/api/pith-number/YHKMQZU6MWYNX7EXBGSOJLRFUY/events.json","paper":"https://pith.science/paper/YHKMQZU6"},"agent_actions":{"view_html":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY","download_json":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY.json","view_paper":"https://pith.science/paper/YHKMQZU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07584&json=true","fetch_graph":"https://pith.science/api/pith-number/YHKMQZU6MWYNX7EXBGSOJLRFUY/graph.json","fetch_events":"https://pith.science/api/pith-number/YHKMQZU6MWYNX7EXBGSOJLRFUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY/action/storage_attestation","attest_author":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY/action/author_attestation","sign_citation":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY/action/citation_signature","submit_replication":"https://pith.science/pith/YHKMQZU6MWYNX7EXBGSOJLRFUY/action/replication_record"}},"created_at":"2026-07-05T11:26:03.346740+00:00","updated_at":"2026-07-05T11:26:03.346740+00:00"}