{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TNLFRSXEWBKK7R35PMEIPMYETI","short_pith_number":"pith:TNLFRSXE","canonical_record":{"source":{"id":"2605.07053","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-08T00:02:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b12fcc959e16c1191c6aeda69560f2bb55d3fa18855ad926969714c3239ae50e","abstract_canon_sha256":"4116b5593d96bf058a5e034488929109127afda11fb9ad99ef15e4e0942ceb57"},"schema_version":"1.0"},"canonical_sha256":"9b5658cae4b054afc77d7b0887b3049a3764ac62ff8dee1df1aad848b5259ee2","source":{"kind":"arxiv","id":"2605.07053","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07053","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07053v2","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07053","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"TNLFRSXEWBKK","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"TNLFRSXEWBKK7R35","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"TNLFRSXE","created_at":"2026-05-27T01:05:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TNLFRSXEWBKK7R35PMEIPMYETI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.07053","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-08T00:02:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b12fcc959e16c1191c6aeda69560f2bb55d3fa18855ad926969714c3239ae50e","abstract_canon_sha256":"4116b5593d96bf058a5e034488929109127afda11fb9ad99ef15e4e0942ceb57"},"schema_version":"1.0"},"canonical_sha256":"9b5658cae4b054afc77d7b0887b3049a3764ac62ff8dee1df1aad848b5259ee2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:56.461791Z","signature_b64":"qJ8uznidqJbGrWOz+leyI8eH+ctR5fTb+KQ83uqZR/aHqeYn+XfL7+DBItUpzxOsyi3WLHlUdnC746WWux4LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b5658cae4b054afc77d7b0887b3049a3764ac62ff8dee1df1aad848b5259ee2","last_reissued_at":"2026-05-27T01:05:56.460991Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:56.460991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.07053","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mzYHaGPiiv2nQMKVjE0/LLK0VDS2zlqZr7euTQS7V35Dz50CvAtldS+tJfvsX5jWfUJhCQ+UwXyTHFAZJIlUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:29:13.342622Z"},"content_sha256":"78d6cd0ebfdbe287c32a919142044b5404a3416da33d1ef23b798fc8e15d6bbe","schema_version":"1.0","event_id":"sha256:78d6cd0ebfdbe287c32a919142044b5404a3416da33d1ef23b798fc8e15d6bbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TNLFRSXEWBKK7R35PMEIPMYETI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"GSM-SEM creates fresh math problem variants by changing facts and entities while preserving the original answers and calculations.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Aziza Mirsaidova, Dan Roth, Fang Tu, Graham Horwood, Hitesh Laxmichand Patel, Jyotika Singh, Karan Dua, Miguel Ballesteros, Sandip Ghoshal, Sujith Ravi, Tao Sheng, Weiyi Sun, Yassine Benajiba","submitted_at":"2026-05-08T00:02:39Z","abstract_excerpt":"Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets. Most robustness variants apply surface-level perturbations (paraphrases, renamings, number swaps, distractors) that largely preserve the underlying facts, and static releases can themselves become memorization targets over time. We introduce GSM-SEM, a reusable and stochastic framework for generating semantically diverse benchmark variants with substantially higher semantic variance than prior approaches. GSM-SEM perturbs problem stat"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluating 14 SOTA LLMs, we observe consistent performance drops with larger decline when semantic perturbations are coupled with symbolic/plus variations (average drop rate 28% in maximum strictness configuration of GSM-SEM).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modifications to entities, attributes, and relationships can be constrained to alter underlying facts and require recomputation while still preserving the original calculations, answer, and approximate problem difficulty.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GSM-SEM generates reusable, stochastic semantic variants of math reasoning benchmarks that alter underlying facts but preserve answers, producing larger LLM performance drops than prior surface-level variants.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GSM-SEM creates fresh math problem variants by changing facts and entities while preserving the original answers and calculations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"15b0f1c6e3ece1c4cb400345eec721233817542048c569fdbcffe98d34e965fd"},"source":{"id":"2605.07053","kind":"arxiv","version":2},"verdict":{"id":"44d2e8d9-c7c6-436a-af5a-07e3a9f48aeb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:50:17.185012Z","strongest_claim":"Evaluating 14 SOTA LLMs, we observe consistent performance drops with larger decline when semantic perturbations are coupled with symbolic/plus variations (average drop rate 28% in maximum strictness configuration of GSM-SEM).","one_line_summary":"GSM-SEM generates reusable, stochastic semantic variants of math reasoning benchmarks that alter underlying facts but preserve answers, producing larger LLM performance drops than prior surface-level variants.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modifications to entities, attributes, and relationships can be constrained to alter underlying facts and require recomputation while still preserving the original calculations, answer, and approximate problem difficulty.","pith_extraction_headline":"GSM-SEM creates fresh math problem variants by changing facts and entities while preserving the original answers and calculations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07053/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:42:03.403367Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T06:37:24.207279Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.786006Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:09:47.524745Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"aea27fb16682fe46102a92d2c37c4ef54db18829159f8a0ade344cb7eca492d6"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6bbc3aa22f9ffe389ed7d57dd04c4976bd7364b04bd0a541b3ee2026542888cd"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"44d2e8d9-c7c6-436a-af5a-07e3a9f48aeb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JIQX3icP0laadqezzKvcX/6z7KFWyFoxfjg7dTIHZSxp+GEjCipj59HZdz5gPIpXnTkH4ErQDmD1iZprB+2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T22:29:13.343789Z"},"content_sha256":"623e5f9d1485a7f74ae2b667430eef035b7fa06bb328eea7593e79a95a0334a0","schema_version":"1.0","event_id":"sha256:623e5f9d1485a7f74ae2b667430eef035b7fa06bb328eea7593e79a95a0334a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNLFRSXEWBKK7R35PMEIPMYETI/bundle.json","state_url":"https://pith.science/pith/TNLFRSXEWBKK7R35PMEIPMYETI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNLFRSXEWBKK7R35PMEIPMYETI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T22:29:13Z","links":{"resolver":"https://pith.science/pith/TNLFRSXEWBKK7R35PMEIPMYETI","bundle":"https://pith.science/pith/TNLFRSXEWBKK7R35PMEIPMYETI/bundle.json","state":"https://pith.science/pith/TNLFRSXEWBKK7R35PMEIPMYETI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNLFRSXEWBKK7R35PMEIPMYETI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TNLFRSXEWBKK7R35PMEIPMYETI","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":"4116b5593d96bf058a5e034488929109127afda11fb9ad99ef15e4e0942ceb57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-08T00:02:39Z","title_canon_sha256":"b12fcc959e16c1191c6aeda69560f2bb55d3fa18855ad926969714c3239ae50e"},"schema_version":"1.0","source":{"id":"2605.07053","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07053","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07053v2","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07053","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"TNLFRSXEWBKK","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"TNLFRSXEWBKK7R35","created_at":"2026-05-27T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"TNLFRSXE","created_at":"2026-05-27T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:623e5f9d1485a7f74ae2b667430eef035b7fa06bb328eea7593e79a95a0334a0","target":"graph","created_at":"2026-05-27T01:05:56Z","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":"Evaluating 14 SOTA LLMs, we observe consistent performance drops with larger decline when semantic perturbations are coupled with symbolic/plus variations (average drop rate 28% in maximum strictness configuration of GSM-SEM)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That modifications to entities, attributes, and relationships can be constrained to alter underlying facts and require recomputation while still preserving the original calculations, answer, and approximate problem difficulty."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GSM-SEM generates reusable, stochastic semantic variants of math reasoning benchmarks that alter underlying facts but preserve answers, producing larger LLM performance drops than prior surface-level variants."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GSM-SEM creates fresh math problem variants by changing facts and entities while preserving the original answers and calculations."}],"snapshot_sha256":"15b0f1c6e3ece1c4cb400345eec721233817542048c569fdbcffe98d34e965fd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6bbc3aa22f9ffe389ed7d57dd04c4976bd7364b04bd0a541b3ee2026542888cd"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T11:42:03.403367Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T06:37:24.207279Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.786006Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T12:09:47.524745Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.07053/integrity.json","findings":[],"snapshot_sha256":"aea27fb16682fe46102a92d2c37c4ef54db18829159f8a0ade344cb7eca492d6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarks like GSM8K are popular measures of mathematical reasoning, but leaderboard gains can overstate true capability due to memorization of fixed test sets. Most robustness variants apply surface-level perturbations (paraphrases, renamings, number swaps, distractors) that largely preserve the underlying facts, and static releases can themselves become memorization targets over time. We introduce GSM-SEM, a reusable and stochastic framework for generating semantically diverse benchmark variants with substantially higher semantic variance than prior approaches. GSM-SEM perturbs problem stat","authors_text":"Amit Agarwal, Aziza Mirsaidova, Dan Roth, Fang Tu, Graham Horwood, Hitesh Laxmichand Patel, Jyotika Singh, Karan Dua, Miguel Ballesteros, Sandip Ghoshal, Sujith Ravi, Tao Sheng, Weiyi Sun, Yassine Benajiba","cross_cats":["cs.AI"],"headline":"GSM-SEM creates fresh math problem variants by changing facts and entities while preserving the original answers and calculations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-08T00:02:39Z","title":"GSM-SEM: Benchmark and Framework for Generating Semantically Variant Augmentations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07053","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T00:50:17.185012Z","id":"44d2e8d9-c7c6-436a-af5a-07e3a9f48aeb","model_set":{"reader":"grok-4.3"},"one_line_summary":"GSM-SEM generates reusable, stochastic semantic variants of math reasoning benchmarks that alter underlying facts but preserve answers, producing larger LLM performance drops than prior surface-level variants.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GSM-SEM creates fresh math problem variants by changing facts and entities while preserving the original answers and calculations.","strongest_claim":"Evaluating 14 SOTA LLMs, we observe consistent performance drops with larger decline when semantic perturbations are coupled with symbolic/plus variations (average drop rate 28% in maximum strictness configuration of GSM-SEM).","weakest_assumption":"That modifications to entities, attributes, and relationships can be constrained to alter underlying facts and require recomputation while still preserving the original calculations, answer, and approximate problem difficulty."}},"verdict_id":"44d2e8d9-c7c6-436a-af5a-07e3a9f48aeb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78d6cd0ebfdbe287c32a919142044b5404a3416da33d1ef23b798fc8e15d6bbe","target":"record","created_at":"2026-05-27T01:05:56Z","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":"4116b5593d96bf058a5e034488929109127afda11fb9ad99ef15e4e0942ceb57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-08T00:02:39Z","title_canon_sha256":"b12fcc959e16c1191c6aeda69560f2bb55d3fa18855ad926969714c3239ae50e"},"schema_version":"1.0","source":{"id":"2605.07053","kind":"arxiv","version":2}},"canonical_sha256":"9b5658cae4b054afc77d7b0887b3049a3764ac62ff8dee1df1aad848b5259ee2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b5658cae4b054afc77d7b0887b3049a3764ac62ff8dee1df1aad848b5259ee2","first_computed_at":"2026-05-27T01:05:56.460991Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:56.460991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qJ8uznidqJbGrWOz+leyI8eH+ctR5fTb+KQ83uqZR/aHqeYn+XfL7+DBItUpzxOsyi3WLHlUdnC746WWux4LAg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:56.461791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07053","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78d6cd0ebfdbe287c32a919142044b5404a3416da33d1ef23b798fc8e15d6bbe","sha256:623e5f9d1485a7f74ae2b667430eef035b7fa06bb328eea7593e79a95a0334a0"],"state_sha256":"2d4ed75827ff53922b0bee30e6c681020cf4c395f48517bfd255606baed61a83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pU+Esolawd5X2+LxfvGZEHL78EEdYFlCJLCtk8a8+iWn4GrLKbqN1Gya+l7zUuLrcINWWa64ufoDfsa+vzbfCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T22:29:13.348893Z","bundle_sha256":"4210b850e6c77da8675d0eb13b3f131aa3e4191e8b7d56fe1c634fcfcfcd352d"}}