{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DKVJN7NY3VJINP6R22LISMYHOS","short_pith_number":"pith:DKVJN7NY","schema_version":"1.0","canonical_sha256":"1aaa96fdb8dd5286bfd1d69689330774a87df6cff0f040971799b6d507e39b3a","source":{"kind":"arxiv","id":"2604.08571","version":2},"attestation_state":"computed","paper":{"title":"Robust Reasoning Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey, Pavel Golikov","submitted_at":"2026-03-26T22:19:33Z","abstract_excerpt":"While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of 13 deterministic textual perturbations applied to AIME 2024 and AIME 2025. Evaluating 8 state-of-the-art models, we find that frontier models are largely resilient, with the notable exception of Claude, which categorically refuses many transformed prompts. Open-weights reasoning models exhibit a range of failure modes under structural noise (cognitive thrash"},"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":true},"canonical_record":{"source":{"id":"2604.08571","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T22:19:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1506d1d446ef8dad258b04c28e5f6f006c00c5e44e54fb5ae902ba7b52b0030b","abstract_canon_sha256":"5f4b4257e5fef207bee4cc639ca93ecbb7cbd1d84d957c58fbf00cf4e1cd5ace"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:19.299558Z","signature_b64":"HW+ZasmZuJFljqwm84s8X+wmX9r0r1GtYCnSWSIwTXnwYSX050WfqGVOfMUkU9GRQzsYhdFR9c/c0Tv6MSwpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aaa96fdb8dd5286bfd1d69689330774a87df6cff0f040971799b6d507e39b3a","last_reissued_at":"2026-05-22T01:03:19.298591Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:19.298591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Reasoning Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey, Pavel Golikov","submitted_at":"2026-03-26T22:19:33Z","abstract_excerpt":"While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of 13 deterministic textual perturbations applied to AIME 2024 and AIME 2025. Evaluating 8 state-of-the-art models, we find that frontier models are largely resilient, with the notable exception of Claude, which categorically refuses many transformed prompts. Open-weights reasoning models exhibit a range of failure modes under structural noise (cognitive thrash"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"open weights reasoning models suffer catastrophic collapses (up to 55% average accuracy drops across perturbations and up to 100% on some), exposing structural fragility. ... intermediate reasoning steps permanently pollute standard dense attention mechanisms.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 14 perturbations preserve the underlying mathematical content and difficulty so that accuracy drops can be attributed specifically to reasoning or parsing failures rather than altered problem solvability.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Perturbations to math problem text cause up to 55% average accuracy drops in open-weight LLMs and sequential solving reveals context pollution in attention mechanisms.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"634fbc973c4addcee81e54eb1543476f09fba30caccf0dd07cd7f51220c576e4"},"source":{"id":"2604.08571","kind":"arxiv","version":2},"verdict":{"id":"945fc6ea-ed1b-4a0c-8f45-a1cf2c162f6b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:01:42.710966Z","strongest_claim":"open weights reasoning models suffer catastrophic collapses (up to 55% average accuracy drops across perturbations and up to 100% on some), exposing structural fragility. ... intermediate reasoning steps permanently pollute standard dense attention mechanisms.","one_line_summary":"Perturbations to math problem text cause up to 55% average accuracy drops in open-weight LLMs and sequential solving reveals context pollution in attention mechanisms.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 14 perturbations preserve the underlying mathematical content and difficulty so that accuracy drops can be attributed specifically to reasoning or parsing failures rather than altered problem solvability.","pith_extraction_headline":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08571/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":2,"snapshot_sha256":"915672ab613893c5da86adb476506c502bfc505360602597d4e3fd9a0a27ed24"},"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":"2604.08571","created_at":"2026-05-22T01:03:19.298735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.08571v2","created_at":"2026-05-22T01:03:19.298735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08571","created_at":"2026-05-22T01:03:19.298735+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKVJN7NY3VJI","created_at":"2026-05-22T01:03:19.298735+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKVJN7NY3VJINP6R","created_at":"2026-05-22T01:03:19.298735+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKVJN7NY","created_at":"2026-05-22T01:03:19.298735+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/DKVJN7NY3VJINP6R22LISMYHOS","json":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS.json","graph_json":"https://pith.science/api/pith-number/DKVJN7NY3VJINP6R22LISMYHOS/graph.json","events_json":"https://pith.science/api/pith-number/DKVJN7NY3VJINP6R22LISMYHOS/events.json","paper":"https://pith.science/paper/DKVJN7NY"},"agent_actions":{"view_html":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS","download_json":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS.json","view_paper":"https://pith.science/paper/DKVJN7NY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.08571&json=true","fetch_graph":"https://pith.science/api/pith-number/DKVJN7NY3VJINP6R22LISMYHOS/graph.json","fetch_events":"https://pith.science/api/pith-number/DKVJN7NY3VJINP6R22LISMYHOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS/action/storage_attestation","attest_author":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS/action/author_attestation","sign_citation":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS/action/citation_signature","submit_replication":"https://pith.science/pith/DKVJN7NY3VJINP6R22LISMYHOS/action/replication_record"}},"created_at":"2026-05-22T01:03:19.298735+00:00","updated_at":"2026-05-22T01:03:19.298735+00:00"}