{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y3HTHTBDNW33ZLNQQDMMHP4I3K","short_pith_number":"pith:Y3HTHTBD","schema_version":"1.0","canonical_sha256":"c6cf33cc236db7bcadb080d8c3bf88da83934170bc41710043d849686b5d4e32","source":{"kind":"arxiv","id":"2411.18564","version":2},"attestation_state":"computed","paper":{"title":"Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jonas Kuhn, Kun Sun, Rong Wang","submitted_at":"2024-11-27T18:04:05Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning. This paper presents a novel neural-symbolic framework that enhances LLMs' spatial reasoning abilities through iterative feedback between LLMs and Answer Set Programming (ASP). We evaluate our approach on two benchmark datasets: StepGame and SparQA, implementing three distinct strategies: (1) direct prompting baseline, (2) Facts+Rules prompting, and (3) DSPy-based LLM+ASP pipeline with iterative refinement. Our experimental results demonstrate that the LLM"},"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":"2411.18564","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-27T18:04:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"22e83b31dc98dcd4ba9db6fbac41e51489748a29dee5849a9d75550aba9867b2","abstract_canon_sha256":"69c9811370f31ca7fc6807e2d1a3f2259af7a785693354019a0a4630ef062773"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:17.063014Z","signature_b64":"KEMmjWjRKXd7NTQ0vAsXsOLnFf6XMK3/AD13MoXT+wIXHGzcRSBkqnDcfcESntuc4EujqvDtK//4FkrMkP/rCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6cf33cc236db7bcadb080d8c3bf88da83934170bc41710043d849686b5d4e32","last_reissued_at":"2026-07-05T09:48:17.062458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:17.062458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jonas Kuhn, Kun Sun, Rong Wang","submitted_at":"2024-11-27T18:04:05Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often struggle with spatial reasoning. This paper presents a novel neural-symbolic framework that enhances LLMs' spatial reasoning abilities through iterative feedback between LLMs and Answer Set Programming (ASP). We evaluate our approach on two benchmark datasets: StepGame and SparQA, implementing three distinct strategies: (1) direct prompting baseline, (2) Facts+Rules prompting, and (3) DSPy-based LLM+ASP pipeline with iterative refinement. Our experimental results demonstrate that the LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18564","kind":"arxiv","version":2},"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/2411.18564/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":"2411.18564","created_at":"2026-07-05T09:48:17.062546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18564v2","created_at":"2026-07-05T09:48:17.062546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18564","created_at":"2026-07-05T09:48:17.062546+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3HTHTBDNW33","created_at":"2026-07-05T09:48:17.062546+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3HTHTBDNW33ZLNQ","created_at":"2026-07-05T09:48:17.062546+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3HTHTBD","created_at":"2026-07-05T09:48:17.062546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09712","citing_title":"LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K","json":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K.json","graph_json":"https://pith.science/api/pith-number/Y3HTHTBDNW33ZLNQQDMMHP4I3K/graph.json","events_json":"https://pith.science/api/pith-number/Y3HTHTBDNW33ZLNQQDMMHP4I3K/events.json","paper":"https://pith.science/paper/Y3HTHTBD"},"agent_actions":{"view_html":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K","download_json":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K.json","view_paper":"https://pith.science/paper/Y3HTHTBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18564&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3HTHTBDNW33ZLNQQDMMHP4I3K/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3HTHTBDNW33ZLNQQDMMHP4I3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K/action/storage_attestation","attest_author":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K/action/author_attestation","sign_citation":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K/action/citation_signature","submit_replication":"https://pith.science/pith/Y3HTHTBDNW33ZLNQQDMMHP4I3K/action/replication_record"}},"created_at":"2026-07-05T09:48:17.062546+00:00","updated_at":"2026-07-05T09:48:17.062546+00:00"}