{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TYL5VBDLWD3RTDHLGOFLMB67EZ","short_pith_number":"pith:TYL5VBDL","schema_version":"1.0","canonical_sha256":"9e17da846bb0f7198ceb338ab607df266e7c52183e54fbc047389c3852baebc9","source":{"kind":"arxiv","id":"2605.28700","version":1},"attestation_state":"computed","paper":{"title":"The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Arlindo Oliveira, Dominika Agnieszka D{\\l}ugosz, Natalia D\\'iaz Rodr\\'iguez","submitted_at":"2026-05-27T16:25:31Z","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 "},"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":false},"canonical_record":{"source":{"id":"2605.28700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T16:25:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6ff6fd7a877f185e8d5ac4bc5a86738c6cd0f81e591e63fb0602b98e6628b341","abstract_canon_sha256":"6521f6cc02b918947aba1396d8972e1afcd8863d3eac118cb47d2c541d4da3c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:05:00.357640Z","signature_b64":"FITDQgA0Kqxxb7/TffCa6cTMS/DgAtF/an5qd4KxNAWLmImPuDd/tkxiMkXvNaCASUSyHz5MN9f5AA3Hlge8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e17da846bb0f7198ceb338ab607df266e7c52183e54fbc047389c3852baebc9","last_reissued_at":"2026-05-28T02:05:00.357206Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:05:00.357206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Arlindo Oliveira, Dominika Agnieszka D{\\l}ugosz, Natalia D\\'iaz Rodr\\'iguez","submitted_at":"2026-05-27T16:25:31Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28700","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.28700/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2605.28700","created_at":"2026-05-28T02:05:00.357270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28700v1","created_at":"2026-05-28T02:05:00.357270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28700","created_at":"2026-05-28T02:05:00.357270+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYL5VBDLWD3R","created_at":"2026-05-28T02:05:00.357270+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYL5VBDLWD3RTDHL","created_at":"2026-05-28T02:05:00.357270+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYL5VBDL","created_at":"2026-05-28T02:05:00.357270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ","json":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ.json","graph_json":"https://pith.science/api/pith-number/TYL5VBDLWD3RTDHLGOFLMB67EZ/graph.json","events_json":"https://pith.science/api/pith-number/TYL5VBDLWD3RTDHLGOFLMB67EZ/events.json","paper":"https://pith.science/paper/TYL5VBDL"},"agent_actions":{"view_html":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ","download_json":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ.json","view_paper":"https://pith.science/paper/TYL5VBDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28700&json=true","fetch_graph":"https://pith.science/api/pith-number/TYL5VBDLWD3RTDHLGOFLMB67EZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TYL5VBDLWD3RTDHLGOFLMB67EZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ/action/storage_attestation","attest_author":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ/action/author_attestation","sign_citation":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ/action/citation_signature","submit_replication":"https://pith.science/pith/TYL5VBDLWD3RTDHLGOFLMB67EZ/action/replication_record"}},"created_at":"2026-05-28T02:05:00.357270+00:00","updated_at":"2026-05-28T02:05:00.357270+00:00"}