{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I4LAHCZE33BJQZKD7DYN76KUSY","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":"2791b358f7f6042bb93f314c00905fd19ee2e46b1bdbc0c5b7bced482cb13780","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T15:57:11Z","title_canon_sha256":"01b8e6c89c91e66eae4f3af3dea1d05be43b71423482161120bc9583565b57af"},"schema_version":"1.0","source":{"id":"2605.25981","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25981","created_at":"2026-05-26T02:05:21Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25981v1","created_at":"2026-05-26T02:05:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25981","created_at":"2026-05-26T02:05:21Z"},{"alias_kind":"pith_short_12","alias_value":"I4LAHCZE33BJ","created_at":"2026-05-26T02:05:21Z"},{"alias_kind":"pith_short_16","alias_value":"I4LAHCZE33BJQZKD","created_at":"2026-05-26T02:05:21Z"},{"alias_kind":"pith_short_8","alias_value":"I4LAHCZE","created_at":"2026-05-26T02:05:21Z"}],"graph_snapshots":[{"event_id":"sha256:a50093159f954e805cd48760eeca67e00ca72208e6d3cbd41550f0f23c62b2e0","target":"graph","created_at":"2026-05-26T02:05:21Z","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/2605.25981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-bearing perturbations (e.g., paraphrase, synonym) alter final answers more often than presentation perturbations (e.g., formatting, reordering) of comparable severity. Across 68 cells spanning GSM8K, MATH, and HotpotQA (1,530 originals and $\\sim$11,150 variants), the inconsistency gap averages +19.69 pp after severity matching (paired $t=9.58$, $p<0.0001$), with 64/68 cells positive. The gap survives four severity-proxy audits and remains signif","authors_text":"Jiayi Guo, Liyun Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T15:57:11Z","title":"When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25981","kind":"arxiv","version":1},"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:f8c38199c45bcfed5e48bf9e551a6d270d32e40d4653f66695c47709cb6f6125","target":"record","created_at":"2026-05-26T02:05:21Z","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":"2791b358f7f6042bb93f314c00905fd19ee2e46b1bdbc0c5b7bced482cb13780","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T15:57:11Z","title_canon_sha256":"01b8e6c89c91e66eae4f3af3dea1d05be43b71423482161120bc9583565b57af"},"schema_version":"1.0","source":{"id":"2605.25981","kind":"arxiv","version":1}},"canonical_sha256":"4716038b24dec2986543f8f0dff954960a522e0f599af31127f9a59ce2582515","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4716038b24dec2986543f8f0dff954960a522e0f599af31127f9a59ce2582515","first_computed_at":"2026-05-26T02:05:21.738994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:21.738994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zxENZz6fHqLjSLUTkcOPR8PoyhcZfn7CkFPmyI36plUylg7nzEu/tI6TWGa1JhGAdM218wpmYRjZr/bYfA6xBA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:21.739751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25981","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8c38199c45bcfed5e48bf9e551a6d270d32e40d4653f66695c47709cb6f6125","sha256:a50093159f954e805cd48760eeca67e00ca72208e6d3cbd41550f0f23c62b2e0"],"state_sha256":"5823b9913b1df85a7de62bb81d660857e29197195311abdfb9d96bb5136947db"}