{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TYL5VBDLWD3RTDHLGOFLMB67EZ","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":"6521f6cc02b918947aba1396d8972e1afcd8863d3eac118cb47d2c541d4da3c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:31Z","title_canon_sha256":"6ff6fd7a877f185e8d5ac4bc5a86738c6cd0f81e591e63fb0602b98e6628b341"},"schema_version":"1.0","source":{"id":"2605.28700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28700","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28700v1","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28700","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"TYL5VBDLWD3R","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"TYL5VBDLWD3RTDHL","created_at":"2026-05-28T02:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"TYL5VBDL","created_at":"2026-05-28T02:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:a9be1690aac5b4cde1d8ad50e75b7dcf19a4235e1dd47248be429b8f2bee83f3","target":"graph","created_at":"2026-05-28T02:05:00Z","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/2605.28700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The GSM-Symbolic benchmark (Mirzadeh et al., 2025) reported consistent performance drops across 25 Large Language Models (LLMs) when tested on template-generated variants of GSM8K problems, concluding that the models lack genuine reasoning capabilities. We argue that this conclusion rests on shaky statistical ground. Re-evaluating 20 open-weight models using Generalised Linear Mixed Models with per-question random effects, we find that only half exhibit statistically significant performance changes under the original prompt format. Moreover, we identify a previously unacknowledged factor: the ","authors_text":"Arlindo Oliveira, Dominika Agnieszka D{\\l}ugosz, Natalia D\\'iaz Rodr\\'iguez","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:31Z","title":"The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28700","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:a4a8300c698be68d35269175e4470bccd91248c730f9a44255c43f11c7873fb1","target":"record","created_at":"2026-05-28T02:05:00Z","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":"6521f6cc02b918947aba1396d8972e1afcd8863d3eac118cb47d2c541d4da3c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:31Z","title_canon_sha256":"6ff6fd7a877f185e8d5ac4bc5a86738c6cd0f81e591e63fb0602b98e6628b341"},"schema_version":"1.0","source":{"id":"2605.28700","kind":"arxiv","version":1}},"canonical_sha256":"9e17da846bb0f7198ceb338ab607df266e7c52183e54fbc047389c3852baebc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e17da846bb0f7198ceb338ab607df266e7c52183e54fbc047389c3852baebc9","first_computed_at":"2026-05-28T02:05:00.357206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:05:00.357206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FITDQgA0Kqxxb7/TffCa6cTMS/DgAtF/an5qd4KxNAWLmImPuDd/tkxiMkXvNaCASUSyHz5MN9f5AA3Hlge8AA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:05:00.357640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4a8300c698be68d35269175e4470bccd91248c730f9a44255c43f11c7873fb1","sha256:a9be1690aac5b4cde1d8ad50e75b7dcf19a4235e1dd47248be429b8f2bee83f3"],"state_sha256":"d6eed956e687fb501d13379be4da8ff96ac098f4945ebd32807ef4160316053b"}