{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TPHHUFJOMFSDWSP55NEJFTTCSQ","short_pith_number":"pith:TPHHUFJO","schema_version":"1.0","canonical_sha256":"9bce7a152e61643b49fdeb4892ce62940012cb573ede05b50ce286236d01cdca","source":{"kind":"arxiv","id":"2504.12560","version":1},"attestation_state":"computed","paper":{"title":"CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir M. Rahmani, Elahe Khatibi, Ziyu Wang","submitted_at":"2025-04-17T01:15:13Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity and correlation-driven retrieval, limiting their ability to distinguish true causal relationships from spurious associations. This results in responses that may be factually grounded but fail to establish cause-and-effect mechanisms, leading to incomplete or misleading insights. To address this issue, we introduce Causal Dynamic Feedback for Adaptive Retriev"},"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":"2504.12560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T01:15:13Z","cross_cats_sorted":[],"title_canon_sha256":"4b048b79d3cbd0aca4cc757dc06ea03aa0f8e30fc713a5b1173d3413ec52b08a","abstract_canon_sha256":"fe77d57ec5391402067b6f90fd8efd80f3dd7da16fa9c73292c8a8be4f2567ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:18.352206Z","signature_b64":"g7WOoTyRDBJNUPbtaGWnhIAbKtw32XEApGgoqyMfiLxyj/1PJL5E6Kyvd0yBR+0mw39b4OeMMdrNWhcr5PyoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bce7a152e61643b49fdeb4892ce62940012cb573ede05b50ce286236d01cdca","last_reissued_at":"2026-07-05T10:50:18.351646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:18.351646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir M. Rahmani, Elahe Khatibi, Ziyu Wang","submitted_at":"2025-04-17T01:15:13Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG frameworks primarily rely on semantic similarity and correlation-driven retrieval, limiting their ability to distinguish true causal relationships from spurious associations. This results in responses that may be factually grounded but fail to establish cause-and-effect mechanisms, leading to incomplete or misleading insights. To address this issue, we introduce Causal Dynamic Feedback for Adaptive Retriev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12560","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/2504.12560/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":"2504.12560","created_at":"2026-07-05T10:50:18.351712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.12560v1","created_at":"2026-07-05T10:50:18.351712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12560","created_at":"2026-07-05T10:50:18.351712+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPHHUFJOMFSD","created_at":"2026-07-05T10:50:18.351712+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPHHUFJOMFSDWSP5","created_at":"2026-07-05T10:50:18.351712+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPHHUFJO","created_at":"2026-07-05T10:50:18.351712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10420","citing_title":"CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07267","citing_title":"PerCaM-Health: Personalized Dynamic Causal Graphs for Healthcare Reasoning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ","json":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ.json","graph_json":"https://pith.science/api/pith-number/TPHHUFJOMFSDWSP55NEJFTTCSQ/graph.json","events_json":"https://pith.science/api/pith-number/TPHHUFJOMFSDWSP55NEJFTTCSQ/events.json","paper":"https://pith.science/paper/TPHHUFJO"},"agent_actions":{"view_html":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ","download_json":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ.json","view_paper":"https://pith.science/paper/TPHHUFJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.12560&json=true","fetch_graph":"https://pith.science/api/pith-number/TPHHUFJOMFSDWSP55NEJFTTCSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TPHHUFJOMFSDWSP55NEJFTTCSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ/action/storage_attestation","attest_author":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ/action/author_attestation","sign_citation":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ/action/citation_signature","submit_replication":"https://pith.science/pith/TPHHUFJOMFSDWSP55NEJFTTCSQ/action/replication_record"}},"created_at":"2026-07-05T10:50:18.351712+00:00","updated_at":"2026-07-05T10:50:18.351712+00:00"}