{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XK4YWFZRE3BLOD77X34EI6EH2C","short_pith_number":"pith:XK4YWFZR","schema_version":"1.0","canonical_sha256":"bab98b173126c2b70fffbef8447887d096fcdbe9a9c5cf17ddc167ecebce5a9f","source":{"kind":"arxiv","id":"2608.04576","version":1},"attestation_state":"computed","paper":{"title":"Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mourad Oussalah, Yuanjun Zhang","submitted_at":"2026-08-05T08:07:15Z","abstract_excerpt":"Humanitarian reports are long, noisy, and multi-topic, making it difficult to consolidate decision-relevant causal evidence. We present a ReliefWeb study (2000-2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and strength attributes. Query-conditioned extraction restricts output to a specified intervention class, reducing retrieval-induced over-extraction, while snippet grounding links each relation to supporting text for auditability and classification. In an expert-annotated dataset of 100 reports, the best closed-"},"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":"2608.04576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T08:07:15Z","cross_cats_sorted":[],"title_canon_sha256":"1c8253f1f3d998998ca402015190c31f1ec6139e7b225010beba494b9f284894","abstract_canon_sha256":"ebe64baaae481cb56b5029ce31caf0a42174a1637438dbbef2028536b00404e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:36:03.135803Z","signature_b64":"apVHbSBpPbLdA1isF+ugkw8ZBh3Ic1Pzoyk9K29gkzWiokyrYsxnnMKV9fNZW5B0SOyl7w2AhXIHygOZsiUsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bab98b173126c2b70fffbef8447887d096fcdbe9a9c5cf17ddc167ecebce5a9f","last_reissued_at":"2026-08-06T01:36:03.134393Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:36:03.134393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mourad Oussalah, Yuanjun Zhang","submitted_at":"2026-08-05T08:07:15Z","abstract_excerpt":"Humanitarian reports are long, noisy, and multi-topic, making it difficult to consolidate decision-relevant causal evidence. We present a ReliefWeb study (2000-2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and strength attributes. Query-conditioned extraction restricts output to a specified intervention class, reducing retrieval-induced over-extraction, while snippet grounding links each relation to supporting text for auditability and classification. In an expert-annotated dataset of 100 reports, the best closed-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04576","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/2608.04576/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":"2608.04576","created_at":"2026-08-06T01:36:03.136188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04576v1","created_at":"2026-08-06T01:36:03.136188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04576","created_at":"2026-08-06T01:36:03.136188+00:00"},{"alias_kind":"pith_short_12","alias_value":"XK4YWFZRE3BL","created_at":"2026-08-06T01:36:03.136188+00:00"},{"alias_kind":"pith_short_16","alias_value":"XK4YWFZRE3BLOD77","created_at":"2026-08-06T01:36:03.136188+00:00"},{"alias_kind":"pith_short_8","alias_value":"XK4YWFZR","created_at":"2026-08-06T01:36:03.136188+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/XK4YWFZRE3BLOD77X34EI6EH2C","json":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C.json","graph_json":"https://pith.science/api/pith-number/XK4YWFZRE3BLOD77X34EI6EH2C/graph.json","events_json":"https://pith.science/api/pith-number/XK4YWFZRE3BLOD77X34EI6EH2C/events.json","paper":"https://pith.science/paper/XK4YWFZR"},"agent_actions":{"view_html":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C","download_json":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C.json","view_paper":"https://pith.science/paper/XK4YWFZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04576&json=true","fetch_graph":"https://pith.science/api/pith-number/XK4YWFZRE3BLOD77X34EI6EH2C/graph.json","fetch_events":"https://pith.science/api/pith-number/XK4YWFZRE3BLOD77X34EI6EH2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C/action/storage_attestation","attest_author":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C/action/author_attestation","sign_citation":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C/action/citation_signature","submit_replication":"https://pith.science/pith/XK4YWFZRE3BLOD77X34EI6EH2C/action/replication_record"}},"created_at":"2026-08-06T01:36:03.136188+00:00","updated_at":"2026-08-06T01:36:03.136188+00:00"}