{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBIBH2LZYSQORQIBQSPFWZ326T","short_pith_number":"pith:BBIBH2LZ","schema_version":"1.0","canonical_sha256":"085013e979c4a0e8c101849e5b677af4cee3bf14a74eccb2d8e1e466fb39ac73","source":{"kind":"arxiv","id":"2509.04523","version":1},"attestation_state":"computed","paper":{"title":"Using LLMs to create analytical datasets: A case study of reconstructing the historical memory of Colombia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"David Anderson, Galia Benitez, Margret Bjarnadottir, Shriyan Reyya","submitted_at":"2025-09-03T14:12:03Z","abstract_excerpt":"Colombia has been submerged in decades of armed conflict, yet until recently, the systematic documentation of violence was not a priority for the Colombian government. This has resulted in a lack of publicly available conflict information and, consequently, a lack of historical accounts. This study contributes to Colombia's historical memory by utilizing GPT, a large language model (LLM), to read and answer questions about over 200,000 violence-related newspaper articles in Spanish. We use the resulting dataset to conduct both descriptive analysis and a study of the relationship between violen"},"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":"2509.04523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T14:12:03Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"1f95ea407c71fe539aaca5b5e41960654c7f22e5862c0600cd3e8ce003c4b9fb","abstract_canon_sha256":"c278ebab2c1075a20e74f12b1757fe7bc842458ecb4038fc29d5e19d46c2be27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:24.638065Z","signature_b64":"UlTHARch/yNj0qEClAH5L8wG4TxHaULCUa50yJXh5Wp/9MDjMWPBLxpOanqLqGWQ9goEFnJj1LdcVQ/74pxIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085013e979c4a0e8c101849e5b677af4cee3bf14a74eccb2d8e1e466fb39ac73","last_reissued_at":"2026-07-05T12:05:24.637562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:24.637562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using LLMs to create analytical datasets: A case study of reconstructing the historical memory of Colombia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"David Anderson, Galia Benitez, Margret Bjarnadottir, Shriyan Reyya","submitted_at":"2025-09-03T14:12:03Z","abstract_excerpt":"Colombia has been submerged in decades of armed conflict, yet until recently, the systematic documentation of violence was not a priority for the Colombian government. This has resulted in a lack of publicly available conflict information and, consequently, a lack of historical accounts. This study contributes to Colombia's historical memory by utilizing GPT, a large language model (LLM), to read and answer questions about over 200,000 violence-related newspaper articles in Spanish. We use the resulting dataset to conduct both descriptive analysis and a study of the relationship between violen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04523","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/2509.04523/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":"2509.04523","created_at":"2026-07-05T12:05:24.637631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04523v1","created_at":"2026-07-05T12:05:24.637631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04523","created_at":"2026-07-05T12:05:24.637631+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBIBH2LZYSQO","created_at":"2026-07-05T12:05:24.637631+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBIBH2LZYSQORQIB","created_at":"2026-07-05T12:05:24.637631+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBIBH2LZ","created_at":"2026-07-05T12:05:24.637631+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/BBIBH2LZYSQORQIBQSPFWZ326T","json":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T.json","graph_json":"https://pith.science/api/pith-number/BBIBH2LZYSQORQIBQSPFWZ326T/graph.json","events_json":"https://pith.science/api/pith-number/BBIBH2LZYSQORQIBQSPFWZ326T/events.json","paper":"https://pith.science/paper/BBIBH2LZ"},"agent_actions":{"view_html":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T","download_json":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T.json","view_paper":"https://pith.science/paper/BBIBH2LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04523&json=true","fetch_graph":"https://pith.science/api/pith-number/BBIBH2LZYSQORQIBQSPFWZ326T/graph.json","fetch_events":"https://pith.science/api/pith-number/BBIBH2LZYSQORQIBQSPFWZ326T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T/action/storage_attestation","attest_author":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T/action/author_attestation","sign_citation":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T/action/citation_signature","submit_replication":"https://pith.science/pith/BBIBH2LZYSQORQIBQSPFWZ326T/action/replication_record"}},"created_at":"2026-07-05T12:05:24.637631+00:00","updated_at":"2026-07-05T12:05:24.637631+00:00"}