{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LS3OPROZYC5QIBS44SAMVTI6P6","short_pith_number":"pith:LS3OPROZ","schema_version":"1.0","canonical_sha256":"5cb6e7c5d9c0bb04065ce480cacd1e7fb907f847fe22badc25acb5a6ff322e6e","source":{"kind":"arxiv","id":"2412.05586","version":1},"attestation_state":"computed","paper":{"title":"Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SC"],"primary_cat":"cs.AI","authors_text":"Abbas Rahimi, Abu Sebastian, Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer","submitted_at":"2024-12-07T08:45:39Z","abstract_excerpt":"This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the understanding of mathematical rules such as progression or arithmetic addition. Providing the visual attributes directly as textual prompts, which assumes an oracle visual perception module, allows us to measure the model's abstract reasoning capability in isolation. Despite providing such compositionally structured representations from the oracle visual perception and advanced prompting techniques, both GPT-4 and Llama-"},"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":"2412.05586","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T08:45:39Z","cross_cats_sorted":["cs.LG","cs.SC"],"title_canon_sha256":"a621d7fb6b0dd052be8f7f3a9e1f70e8ab03835843e0e6f3fa772f044f8ea672","abstract_canon_sha256":"dbf01aa9f98558840847019aad0bbec9e482644e68403cbceeb6cb25f49a3983"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:05.759072Z","signature_b64":"YUuWl04+eX5yKav7Wa785s8uW2xKlftlP8BqGEdae/+73QFL2lWLy8+DjHwPNGo2Zbx+1vUG9AwrG2+UewebCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb6e7c5d9c0bb04065ce480cacd1e7fb907f847fe22badc25acb5a6ff322e6e","last_reissued_at":"2026-07-05T09:46:05.758631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:05.758631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SC"],"primary_cat":"cs.AI","authors_text":"Abbas Rahimi, Abu Sebastian, Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer","submitted_at":"2024-12-07T08:45:39Z","abstract_excerpt":"This work compares large language models (LLMs) and neuro-symbolic approaches in solving Raven's progressive matrices (RPM), a visual abstract reasoning test that involves the understanding of mathematical rules such as progression or arithmetic addition. Providing the visual attributes directly as textual prompts, which assumes an oracle visual perception module, allows us to measure the model's abstract reasoning capability in isolation. Despite providing such compositionally structured representations from the oracle visual perception and advanced prompting techniques, both GPT-4 and Llama-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05586","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/2412.05586/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":"2412.05586","created_at":"2026-07-05T09:46:05.758689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05586v1","created_at":"2026-07-05T09:46:05.758689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05586","created_at":"2026-07-05T09:46:05.758689+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS3OPROZYC5Q","created_at":"2026-07-05T09:46:05.758689+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS3OPROZYC5QIBS4","created_at":"2026-07-05T09:46:05.758689+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS3OPROZ","created_at":"2026-07-05T09:46:05.758689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10057","citing_title":"Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6","json":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6.json","graph_json":"https://pith.science/api/pith-number/LS3OPROZYC5QIBS44SAMVTI6P6/graph.json","events_json":"https://pith.science/api/pith-number/LS3OPROZYC5QIBS44SAMVTI6P6/events.json","paper":"https://pith.science/paper/LS3OPROZ"},"agent_actions":{"view_html":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6","download_json":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6.json","view_paper":"https://pith.science/paper/LS3OPROZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05586&json=true","fetch_graph":"https://pith.science/api/pith-number/LS3OPROZYC5QIBS44SAMVTI6P6/graph.json","fetch_events":"https://pith.science/api/pith-number/LS3OPROZYC5QIBS44SAMVTI6P6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6/action/storage_attestation","attest_author":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6/action/author_attestation","sign_citation":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6/action/citation_signature","submit_replication":"https://pith.science/pith/LS3OPROZYC5QIBS44SAMVTI6P6/action/replication_record"}},"created_at":"2026-07-05T09:46:05.758689+00:00","updated_at":"2026-07-05T09:46:05.758689+00:00"}