{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ENWG2XKPMCBSPT5H7Q5XXEX7HU","short_pith_number":"pith:ENWG2XKP","schema_version":"1.0","canonical_sha256":"236c6d5d4f608327cfa7fc3b7b92ff3d3f3550026e8e6c3cc78bcff3c97c5f66","source":{"kind":"arxiv","id":"2605.15393","version":1},"attestation_state":"computed","paper":{"title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Logic-preserving difficulty scaling finds problem variations that cause language models to fail up to five times more often than random tests.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dieuwke Hupkes, Jesse Dodge, Philipp Mondorf, Samuel J. Bell","submitted_at":"2026-05-14T20:26:59Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed to perform tasks with minimal human oversight, it is crucial that these models operate robustly. In particular, a model that can solve a given problem should not fail simply because certain entities$\\unicode{x2013}$such as names, numbers, or other contextual details$\\unicode{x2013}$have changed while the underlying problem logic remains the same. Prior work suggests that current LLMs still struggle with this form of robustness: they often succeed on some variations of a problem but fail on others. However, existing evaluations often lac"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T20:26:59Z","cross_cats_sorted":[],"title_canon_sha256":"3084e86520bad1b69c41ebd76253a81e4cba3f8551ce75ec8cb122d6bad18f0c","abstract_canon_sha256":"1cef0907d0f498f145adbc8860fb3d834bef77895a396b62279f7af2a33f5c26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:56.319515Z","signature_b64":"pPWA6VAovPj0h/UCqdb7x5YRgsFEKPMduISj5XkGbZYQTcSGP/Ac5dNwdQLDrDrrJB63xkQh10Kc6quKU8jHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236c6d5d4f608327cfa7fc3b7b92ff3d3f3550026e8e6c3cc78bcff3c97c5f66","last_reissued_at":"2026-05-20T00:00:56.318662Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:56.318662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scaling","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Logic-preserving difficulty scaling finds problem variations that cause language models to fail up to five times more often than random tests.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dieuwke Hupkes, Jesse Dodge, Philipp Mondorf, Samuel J. Bell","submitted_at":"2026-05-14T20:26:59Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed to perform tasks with minimal human oversight, it is crucial that these models operate robustly. In particular, a model that can solve a given problem should not fail simply because certain entities$\\unicode{x2013}$such as names, numbers, or other contextual details$\\unicode{x2013}$have changed while the underlying problem logic remains the same. Prior work suggests that current LLMs still struggle with this form of robustness: they often succeed on some variations of a problem but fail on others. However, existing evaluations often lac"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that LPDS efficiently finds difficult problem variations for a model, resulting in performance drops up to 5 times larger compared to random sampling.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The framework assumes that difficulty of a logic-preserving variation can be quantified in a model-agnostic or at least transferable way that reliably predicts where failures will occur, and that the search procedure finds variations that are truly harder rather than merely different.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LPDS quantifies difficulty of logic-preserving problem variations and searches for the hardest ones, producing up to 5x larger performance drops than random sampling and better robustness gains from fine-tuning on difficult examples.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Logic-preserving difficulty scaling finds problem variations that cause language models to fail up to five times more often than random tests.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4868c284b20cd34d47ec39df83f807d8e395912041b769ba1cd18b3fea78ef97"},"source":{"id":"2605.15393","kind":"arxiv","version":1},"verdict":{"id":"f3716853-91ee-4a80-8f50-c16cebf4021b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:28:43.234195Z","strongest_claim":"We show that LPDS efficiently finds difficult problem variations for a model, resulting in performance drops up to 5 times larger compared to random sampling.","one_line_summary":"LPDS quantifies difficulty of logic-preserving problem variations and searches for the hardest ones, producing up to 5x larger performance drops than random sampling and better robustness gains from fine-tuning on difficult examples.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The framework assumes that difficulty of a logic-preserving variation can be quantified in a model-agnostic or at least transferable way that reliably predicts where failures will occur, and that the search procedure finds variations that are truly harder rather than merely different.","pith_extraction_headline":"Logic-preserving difficulty scaling finds problem variations that cause language models to fail up to five times more often than random tests."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15393/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:18.258220Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:35:47.406696Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T16:26:23.761732Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T15:50:56.443617Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.167704Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.721310Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2a6e65153d0868f98a03a80e4de9ddc6b180ac3634a4fd94fe06996ca19c1e01"},"references":{"count":74,"sample":[{"doi":"10.1145/3641289","year":2024,"title":"and Yang, Qiang and Xie, Xing , number =","work_id":"baa1ad58-22ae-43a4-86d6-49b6915c12d6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3747588","year":2025,"title":"A survey on large language models for code generation","work_id":"2362b076-10d0-4e85-8b67-08ac034b2069","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2023.acl-long.307","year":2023,"title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","work_id":"4c6f7651-e3e6-412e-acdc-0cbc939ca956","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","work_id":"0b361fed-cf2a-4b90-b61a-de88de4b8840","ref_index":4,"cited_arxiv_id":"2503.09567","is_internal_anchor":true},{"doi":"10.1038/s41586-025-09422-z","year":null,"title":"Nature645(8081), 633–638 (2025) https://doi.org/10.1038/s41586-025-09422-z","work_id":"9835b482-5032-4135-93dd-82a066677569","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":74,"snapshot_sha256":"8d521af3a732175332d3a8294f64a2f501aa840d73096aa720ca9f7b35373ea0","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b2597318cb21bd8a4d7b69ba05971b9da37bd0e8e8b9f7c0c1e3d77a0a99665b"},"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":"2605.15393","created_at":"2026-05-20T00:00:56.318809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15393v1","created_at":"2026-05-20T00:00:56.318809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15393","created_at":"2026-05-20T00:00:56.318809+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENWG2XKPMCBS","created_at":"2026-05-20T00:00:56.318809+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENWG2XKPMCBSPT5H","created_at":"2026-05-20T00:00:56.318809+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENWG2XKP","created_at":"2026-05-20T00:00:56.318809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU","json":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU.json","graph_json":"https://pith.science/api/pith-number/ENWG2XKPMCBSPT5H7Q5XXEX7HU/graph.json","events_json":"https://pith.science/api/pith-number/ENWG2XKPMCBSPT5H7Q5XXEX7HU/events.json","paper":"https://pith.science/paper/ENWG2XKP"},"agent_actions":{"view_html":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU","download_json":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU.json","view_paper":"https://pith.science/paper/ENWG2XKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15393&json=true","fetch_graph":"https://pith.science/api/pith-number/ENWG2XKPMCBSPT5H7Q5XXEX7HU/graph.json","fetch_events":"https://pith.science/api/pith-number/ENWG2XKPMCBSPT5H7Q5XXEX7HU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU/action/storage_attestation","attest_author":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU/action/author_attestation","sign_citation":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU/action/citation_signature","submit_replication":"https://pith.science/pith/ENWG2XKPMCBSPT5H7Q5XXEX7HU/action/replication_record"}},"created_at":"2026-05-20T00:00:56.318809+00:00","updated_at":"2026-05-20T00:00:56.318809+00:00"}