{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DKVJN7NY3VJINP6R22LISMYHOS","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":"5f4b4257e5fef207bee4cc639ca93ecbb7cbd1d84d957c58fbf00cf4e1cd5ace","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T22:19:33Z","title_canon_sha256":"1506d1d446ef8dad258b04c28e5f6f006c00c5e44e54fb5ae902ba7b52b0030b"},"schema_version":"1.0","source":{"id":"2604.08571","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08571","created_at":"2026-05-22T01:03:19Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08571v2","created_at":"2026-05-22T01:03:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08571","created_at":"2026-05-22T01:03:19Z"},{"alias_kind":"pith_short_12","alias_value":"DKVJN7NY3VJI","created_at":"2026-05-22T01:03:19Z"},{"alias_kind":"pith_short_16","alias_value":"DKVJN7NY3VJINP6R","created_at":"2026-05-22T01:03:19Z"},{"alias_kind":"pith_short_8","alias_value":"DKVJN7NY","created_at":"2026-05-22T01:03:19Z"}],"graph_snapshots":[{"event_id":"sha256:1071cbf5264b7a8a352933f0bc6800e8506031d7ef02caf643eceea6b4997b4d","target":"graph","created_at":"2026-05-22T01:03:19Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations."}],"snapshot_sha256":"634fbc973c4addcee81e54eb1543476f09fba30caccf0dd07cd7f51220c576e4"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"915672ab613893c5da86adb476506c502bfc505360602597d4e3fd9a0a27ed24"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.08571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey, Pavel Golikov","cross_cats":["cs.AI","cs.CL"],"headline":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T22:19:33Z","title":"Robust Reasoning Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.08571","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T00:01:42.710966Z","id":"945fc6ea-ed1b-4a0c-8f45-a1cf2c162f6b","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Open-weight reasoning models lose up to 55 percent accuracy when AIME problems receive 14 simple text perturbations.","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.","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."}},"verdict_id":"945fc6ea-ed1b-4a0c-8f45-a1cf2c162f6b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cfc2712db4ef52fd37359f0b436edbc53102699ae21b31f5fd1853e871285674","target":"record","created_at":"2026-05-22T01:03:19Z","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":"5f4b4257e5fef207bee4cc639ca93ecbb7cbd1d84d957c58fbf00cf4e1cd5ace","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-26T22:19:33Z","title_canon_sha256":"1506d1d446ef8dad258b04c28e5f6f006c00c5e44e54fb5ae902ba7b52b0030b"},"schema_version":"1.0","source":{"id":"2604.08571","kind":"arxiv","version":2}},"canonical_sha256":"1aaa96fdb8dd5286bfd1d69689330774a87df6cff0f040971799b6d507e39b3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aaa96fdb8dd5286bfd1d69689330774a87df6cff0f040971799b6d507e39b3a","first_computed_at":"2026-05-22T01:03:19.298591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:19.298591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HW+ZasmZuJFljqwm84s8X+wmX9r0r1GtYCnSWSIwTXnwYSX050WfqGVOfMUkU9GRQzsYhdFR9c/c0Tv6MSwpBw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:19.299558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.08571","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfc2712db4ef52fd37359f0b436edbc53102699ae21b31f5fd1853e871285674","sha256:1071cbf5264b7a8a352933f0bc6800e8506031d7ef02caf643eceea6b4997b4d"],"state_sha256":"04ecaa945f563c026d939e43495aec11627f62c7894a93d612f8d1d57185e5ff"}