{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CVIF262LPIA4NGYUKCH4BZM53T","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"830d9e5aabd0c156f7bc294312973c677ce6a1c42e108457b9f97fd1338d6df2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T19:20:16Z","title_canon_sha256":"380fa229699beab61715b5ecc4126884cf694256be3ae2cc51f90583541e10c3"},"schema_version":"1.0","source":{"id":"2605.14053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14053","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14053v1","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14053","created_at":"2026-05-17T23:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"CVIF262LPIA4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CVIF262LPIA4NGYU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CVIF262L","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4fe7fa49b800a938258c0a82c47eb7fb80750cfc1134abedd857ff01de61ed80","target":"graph","created_at":"2026-05-17T23:39:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"It constructs a derivation tree that is interpretable and adds control over the generation process. We applied this method in a specific case study, significantly reducing unacceptable answers compared to traditional RAG and long-context window methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That predefined rules can be reliably encoded in prompts and followed by the LLM to produce valid, non-deviating derivation steps without introducing new errors or hallucinations in the tree construction itself."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Derivation Prompting constructs logic-based derivation trees in RAG generation to improve interpretability and reduce unacceptable answers compared to standard RAG or long-context methods in a case study."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Derivation Prompting builds an interpretable logic tree from predefined rules to guide RAG generation and reduce unacceptable answers."}],"snapshot_sha256":"cf18f3aed523bf330c6f937c408ec782c5d96b1f8c2842a1a481c50d9955e5e9"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c4e81e499178d01d85ead281904d0725e33dbc985989410505468b0e066647ff"},"paper":{"abstract_excerpt":"The application of Large Language Models to Question Answering has shown great promise, but important challenges such as hallucinations and erroneous reasoning arise when using these models, particularly in knowledge-intensive, domain-specific tasks. To address these issues, we introduce Derivation Prompting, a novel prompting technique for the generation step of the Retrieval-Augmented Generation framework. Inspired by logic derivations, this method involves deriving conclusions from initial hypotheses through the systematic application of predefined rules. It constructs a derivation tree tha","authors_text":"Aiala Ros\\'a, Guillermo Moncecchi, Ignacio Sastre","cross_cats":["cs.AI"],"headline":"Derivation Prompting builds an interpretable logic tree from predefined rules to guide RAG generation and reduce unacceptable answers.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T19:20:16Z","title":"Derivation Prompting: A Logic-Based Method for Improving Retrieval-Augmented Generation"},"references":{"count":19,"internal_anchors":3,"resolved_work":19,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"In: Advances in Neural Infor- Derivation Prompting: A Logic-Based Method for Improving RAG 11 mation Processing Systems","work_id":"6076eda7-b5c4-49f0-90e3-f985b52c873b","year":1901},{"cited_arxiv_id":"2312.10997","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","year":2024},{"cited_arxiv_id":"","doi":"10.18653/v1/","is_internal_anchor":false,"ref_index":3,"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Izacard, G., Lewis, P., Lomeli, M., Hosseini, L., Petroni, F., Schick, T., Dwivedi- Yu, J., Joulin, A., Riedel, S., Grave, E.: Atlas: few-shot learning with retrieval augmented language models. J. Mac","work_id":"1c9a7fe4-c218-4280-b079-f66866a7cd2f","year":2024},{"cited_arxiv_id":"","doi":"10.1145/3571730","is_internal_anchor":false,"ref_index":5,"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","year":2023}],"snapshot_sha256":"b07383cd63ea14b552e000749ade6f7a42c0849112f0e84ec875910d3450b5b8"},"source":{"id":"2605.14053","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:26:46.825466Z","id":"a9051fd1-35bc-4374-b8fe-67bc92d6c440","model_set":{"reader":"grok-4.3"},"one_line_summary":"Derivation Prompting constructs logic-based derivation trees in RAG generation to improve interpretability and reduce unacceptable answers compared to standard RAG or long-context methods in a case study.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Derivation Prompting builds an interpretable logic tree from predefined rules to guide RAG generation and reduce unacceptable answers.","strongest_claim":"It constructs a derivation tree that is interpretable and adds control over the generation process. We applied this method in a specific case study, significantly reducing unacceptable answers compared to traditional RAG and long-context window methods.","weakest_assumption":"That predefined rules can be reliably encoded in prompts and followed by the LLM to produce valid, non-deviating derivation steps without introducing new errors or hallucinations in the tree construction itself."}},"verdict_id":"a9051fd1-35bc-4374-b8fe-67bc92d6c440"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:82564b0f92a7e4803e479a41afc3fbb4b2554bdcfc2ff2c835657067a079b09d","target":"record","created_at":"2026-05-17T23:39:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"830d9e5aabd0c156f7bc294312973c677ce6a1c42e108457b9f97fd1338d6df2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T19:20:16Z","title_canon_sha256":"380fa229699beab61715b5ecc4126884cf694256be3ae2cc51f90583541e10c3"},"schema_version":"1.0","source":{"id":"2605.14053","kind":"arxiv","version":1}},"canonical_sha256":"15505d7b4b7a01c69b14508fc0e59ddcfab5ee9be30e0b18c385edc08ddc1df9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15505d7b4b7a01c69b14508fc0e59ddcfab5ee9be30e0b18c385edc08ddc1df9","first_computed_at":"2026-05-17T23:39:12.619522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:12.619522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"55sZytbg0Tns+tNs2895hbpKphPikSo2wM6Z/LyrY80rfgMd1+zlq5g+5cfsO39HZ7C7QenLPMDTbgWudOdeCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:12.620140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82564b0f92a7e4803e479a41afc3fbb4b2554bdcfc2ff2c835657067a079b09d","sha256:4fe7fa49b800a938258c0a82c47eb7fb80750cfc1134abedd857ff01de61ed80"],"state_sha256":"d4b33dd9c707c75b5241c49e7f41ac6ce108fecf7e9b52735d21df59e0ed6f3f"}