{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PJ5AF2UV76ET7VB3P6NRZRBYTD","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":"2d57a5729bb6ab898af325270f21b64288efe4847a3b59552f671baf740cee6a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T17:16:51Z","title_canon_sha256":"46a61b840967c218c79dbd20445a4297b9538a0fc36b733e8186279598f5eacd"},"schema_version":"1.0","source":{"id":"2502.04352","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04352","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04352v2","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04352","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"pith_short_12","alias_value":"PJ5AF2UV76ET","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"pith_short_16","alias_value":"PJ5AF2UV76ET7VB3","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"pith_short_8","alias_value":"PJ5AF2UV","created_at":"2026-07-05T11:58:24Z"}],"graph_snapshots":[{"event_id":"sha256:3e55d973ab01afaf1a2bb78c480b3af6d126a10c5a1105b24fc98b117391ae9a","target":"graph","created_at":"2026-07-05T11:58:24Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.04352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and autoformalisation methods, are robust on logical deduction tasks. Moreover, while many LLM-based deduction methods have been proposed, a systematic study that analyses the impact of their design components is lacking. Addressing these two challenges, we propose the first study of the robustness of formal and informal LLM-based deductive reasoning methods. We de","authors_text":"Fabian Hoppe, Filip Ilievski, Jan-Christoph Kalo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T17:16:51Z","title":"Investigating the Robustness of Deductive Reasoning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04352","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c43ef751c2a3bbec09d662f12b7f780e51d1a995dff9b1e4cd37c54be2409524","target":"record","created_at":"2026-07-05T11:58:24Z","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":"2d57a5729bb6ab898af325270f21b64288efe4847a3b59552f671baf740cee6a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T17:16:51Z","title_canon_sha256":"46a61b840967c218c79dbd20445a4297b9538a0fc36b733e8186279598f5eacd"},"schema_version":"1.0","source":{"id":"2502.04352","kind":"arxiv","version":2}},"canonical_sha256":"7a7a02ea95ff893fd43b7f9b1cc43898fea0a83938ef12effcdcd1cd1ab13573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a7a02ea95ff893fd43b7f9b1cc43898fea0a83938ef12effcdcd1cd1ab13573","first_computed_at":"2026-07-05T11:58:24.676946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:24.676946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VFEH4ZzxNuD3o8vlqipHAM951BLVmA84ieKJ3E8ma8PubVUnAc4uf8oCLWy2qEomsTjI5/aQqn3VDRaquYJBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:24.677404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04352","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c43ef751c2a3bbec09d662f12b7f780e51d1a995dff9b1e4cd37c54be2409524","sha256:3e55d973ab01afaf1a2bb78c480b3af6d126a10c5a1105b24fc98b117391ae9a"],"state_sha256":"8e1c5159984b5886ecd1ed4e504c90922a7f16a95b894775f32b1b1582d01094"}