{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BNQNP2HFJ42FH33YOJDUAKEILF","short_pith_number":"pith:BNQNP2HF","schema_version":"1.0","canonical_sha256":"0b60d7e8e54f3453ef787247402888597c528cbc8c3b82d43817e70ee6e640f6","source":{"kind":"arxiv","id":"2608.06292","version":1},"attestation_state":"computed","paper":{"title":"NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.CL","authors_text":"Jonas Gann, Michael Gertz","submitted_at":"2026-08-06T17:16:28Z","abstract_excerpt":"Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often leading to incomplete or incorrect output.\n  We propose NeSy-RAG, a modular neuro-symbolic RAG framework that synthesizes attributable Prolog modules from retrieved text chunks. For each chunk, the system"},"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":"2608.06292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T17:16:28Z","cross_cats_sorted":["cs.SC"],"title_canon_sha256":"cf69e604715a2699376dd129f522f88a27d4d7c897bc693b1bffd66d9cf055bd","abstract_canon_sha256":"e31b308c93c46259f3ce050f18810f641f4afde42b69a862898d7eba88efe05b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:41:18.630564Z","signature_b64":"ntw69K70MF6p8Ckk4ORIMcnUi2HvyA3dGTytG2W6cDud7HqbvB0+ie/e2REczp0Rw1X6yuYaSqfuMOtxFHGZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b60d7e8e54f3453ef787247402888597c528cbc8c3b82d43817e70ee6e640f6","last_reissued_at":"2026-08-07T01:41:18.628868Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:41:18.628868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.CL","authors_text":"Jonas Gann, Michael Gertz","submitted_at":"2026-08-06T17:16:28Z","abstract_excerpt":"Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. However, its reasoning process remains largely opaque: intermediate reasoning steps are difficult to verify and cannot be reliably attributed to specific evidence. Moreover, missing user-specific context is rarely detected systematically, often leading to incomplete or incorrect output.\n  We propose NeSy-RAG, a modular neuro-symbolic RAG framework that synthesizes attributable Prolog modules from retrieved text chunks. For each chunk, the system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06292","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/2608.06292/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":"2608.06292","created_at":"2026-08-07T01:41:18.631431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06292v1","created_at":"2026-08-07T01:41:18.631431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06292","created_at":"2026-08-07T01:41:18.631431+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNQNP2HFJ42F","created_at":"2026-08-07T01:41:18.631431+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNQNP2HFJ42FH33Y","created_at":"2026-08-07T01:41:18.631431+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNQNP2HF","created_at":"2026-08-07T01:41:18.631431+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/BNQNP2HFJ42FH33YOJDUAKEILF","json":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF.json","graph_json":"https://pith.science/api/pith-number/BNQNP2HFJ42FH33YOJDUAKEILF/graph.json","events_json":"https://pith.science/api/pith-number/BNQNP2HFJ42FH33YOJDUAKEILF/events.json","paper":"https://pith.science/paper/BNQNP2HF"},"agent_actions":{"view_html":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF","download_json":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF.json","view_paper":"https://pith.science/paper/BNQNP2HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06292&json=true","fetch_graph":"https://pith.science/api/pith-number/BNQNP2HFJ42FH33YOJDUAKEILF/graph.json","fetch_events":"https://pith.science/api/pith-number/BNQNP2HFJ42FH33YOJDUAKEILF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF/action/storage_attestation","attest_author":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF/action/author_attestation","sign_citation":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF/action/citation_signature","submit_replication":"https://pith.science/pith/BNQNP2HFJ42FH33YOJDUAKEILF/action/replication_record"}},"created_at":"2026-08-07T01:41:18.631431+00:00","updated_at":"2026-08-07T01:41:18.631431+00:00"}