{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJFIT6CCJDKLJZDOLIOXFASTNG","short_pith_number":"pith:GJFIT6CC","schema_version":"1.0","canonical_sha256":"324a89f84248d4b4e46e5a1d72825369b2b14c18a0efffd96f446ab8db6e3c4f","source":{"kind":"arxiv","id":"2405.17893","version":1},"attestation_state":"computed","paper":{"title":"Arithmetic Reasoning with LLM: Prolog Generation & Permutation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingsen Chen, Xiaocheng Yang, Yik-Cheung Tam","submitted_at":"2024-05-28T07:13:25Z","abstract_excerpt":"Instructing large language models (LLMs) to solve elementary school math problems has shown great success using Chain of Thought (CoT). However, the CoT approach relies on an LLM to generate a sequence of arithmetic calculations which can be prone to cascaded calculation errors. We hypothesize that an LLM should focus on extracting predicates and generating symbolic formulas from the math problem description so that the underlying calculation can be done via an external code interpreter. We investigate using LLM to generate Prolog programs to solve mathematical questions. Experimental results "},"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":"2405.17893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T07:13:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3247a64b50eb9b89a961d025a79a462cef20d547dd05ef163fc9ca4499290249","abstract_canon_sha256":"f55a71945356ca253aca1cd7b862899170bfb54c23058c4a04cc7475eac2315d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:12.557884Z","signature_b64":"xUd474CxyoN4AvC6YDoIo6QkCMDKfAdZ+8mL8tMV7kH7xPQSr5B3JTIFHdHkDdb5CXsqnpY4TsgrKxMm+vSeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"324a89f84248d4b4e46e5a1d72825369b2b14c18a0efffd96f446ab8db6e3c4f","last_reissued_at":"2026-07-05T08:24:12.557419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:12.557419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Arithmetic Reasoning with LLM: Prolog Generation & Permutation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bingsen Chen, Xiaocheng Yang, Yik-Cheung Tam","submitted_at":"2024-05-28T07:13:25Z","abstract_excerpt":"Instructing large language models (LLMs) to solve elementary school math problems has shown great success using Chain of Thought (CoT). However, the CoT approach relies on an LLM to generate a sequence of arithmetic calculations which can be prone to cascaded calculation errors. We hypothesize that an LLM should focus on extracting predicates and generating symbolic formulas from the math problem description so that the underlying calculation can be done via an external code interpreter. We investigate using LLM to generate Prolog programs to solve mathematical questions. Experimental results "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17893","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/2405.17893/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":"2405.17893","created_at":"2026-07-05T08:24:12.557479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17893v1","created_at":"2026-07-05T08:24:12.557479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17893","created_at":"2026-07-05T08:24:12.557479+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJFIT6CCJDKL","created_at":"2026-07-05T08:24:12.557479+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJFIT6CCJDKLJZDO","created_at":"2026-07-05T08:24:12.557479+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJFIT6CC","created_at":"2026-07-05T08:24:12.557479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.15599","citing_title":"Autonomous Business System via Neuro-symbolic AI","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG","json":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG.json","graph_json":"https://pith.science/api/pith-number/GJFIT6CCJDKLJZDOLIOXFASTNG/graph.json","events_json":"https://pith.science/api/pith-number/GJFIT6CCJDKLJZDOLIOXFASTNG/events.json","paper":"https://pith.science/paper/GJFIT6CC"},"agent_actions":{"view_html":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG","download_json":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG.json","view_paper":"https://pith.science/paper/GJFIT6CC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17893&json=true","fetch_graph":"https://pith.science/api/pith-number/GJFIT6CCJDKLJZDOLIOXFASTNG/graph.json","fetch_events":"https://pith.science/api/pith-number/GJFIT6CCJDKLJZDOLIOXFASTNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG/action/storage_attestation","attest_author":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG/action/author_attestation","sign_citation":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG/action/citation_signature","submit_replication":"https://pith.science/pith/GJFIT6CCJDKLJZDOLIOXFASTNG/action/replication_record"}},"created_at":"2026-07-05T08:24:12.557479+00:00","updated_at":"2026-07-05T08:24:12.557479+00:00"}