{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YJVGME47C4WH5SR3NZ2BZNDI3Q","short_pith_number":"pith:YJVGME47","canonical_record":{"source":{"id":"2410.13502","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T12:48:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"30fda0f30498f124e8128529ceeab6197b42518b39ccc33eb64e878d06d039f0","abstract_canon_sha256":"53a3e47d2c8a1a698acbe8c5f88cf17eb016bb740636dfab8efafd4f29aa131d"},"schema_version":"1.0"},"canonical_sha256":"c26a66139f172c7eca3b6e741cb468dc0861c341239fee7d1ebc77f70997fb55","source":{"kind":"arxiv","id":"2410.13502","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13502","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13502v3","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13502","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"YJVGME47C4WH","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"YJVGME47C4WH5SR3","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"YJVGME47","created_at":"2026-07-05T10:14:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YJVGME47C4WH5SR3NZ2BZNDI3Q","target":"record","payload":{"canonical_record":{"source":{"id":"2410.13502","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T12:48:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"30fda0f30498f124e8128529ceeab6197b42518b39ccc33eb64e878d06d039f0","abstract_canon_sha256":"53a3e47d2c8a1a698acbe8c5f88cf17eb016bb740636dfab8efafd4f29aa131d"},"schema_version":"1.0"},"canonical_sha256":"c26a66139f172c7eca3b6e741cb468dc0861c341239fee7d1ebc77f70997fb55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:24.565116Z","signature_b64":"OUYdj9pgWslTUGVLtAAdRyLBII7Ub9KHtOcjnw++ymvTImE80Thn6H2xi/HNn6wJrsIaPvrGzHTnk2H6PaiyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c26a66139f172c7eca3b6e741cb468dc0861c341239fee7d1ebc77f70997fb55","last_reissued_at":"2026-07-05T10:14:24.564583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:24.564583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.13502","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZEqm1LQXOuZo210EvU5JsoxUTob1nCx9iFwz90+Xkt5PaksI/1ytPxZCOwDH28UasBkcx3VDbw+vFxOhPGrZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:24:42.550244Z"},"content_sha256":"1c9392c844a924a0ca272564a63c93ac31d9975e90914cdfbc79f29d06cce1a0","schema_version":"1.0","event_id":"sha256:1c9392c844a924a0ca272564a63c93ac31d9975e90914cdfbc79f29d06cce1a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YJVGME47C4WH5SR3NZ2BZNDI3Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Abulhair Saparov, Andreas Opedal, Bernhard Sch\\\"olkopf, Haruki Shirakami, Mrinmaya Sachan","submitted_at":"2024-10-17T12:48:14Z","abstract_excerpt":"Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to more complex problems. This is difficult to study, as (i) much of the available evaluation data has already been seen by the most capable models during training, and (ii) existing benchmarks do not capture how problem proofs may be arbitrarily complex in various ways. In this paper, we present a data-generation framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP. MathGAP generates problem statements and chain-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13502","kind":"arxiv","version":3},"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/2410.13502/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sb9QyCJZfu9Rpvgn6iCMEE0jEpBf+ITnooA/KRidpcBCkHVcl8kEvjD6462qu8YfPigxF2KmUn/+xOJ46edMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:24:42.551206Z"},"content_sha256":"e012937b3982516756350c6957ec2747571ce9b6ed315843a3da9e3458a2f47b","schema_version":"1.0","event_id":"sha256:e012937b3982516756350c6957ec2747571ce9b6ed315843a3da9e3458a2f47b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q/bundle.json","state_url":"https://pith.science/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q/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":"2026-08-18T00:24:42Z","links":{"resolver":"https://pith.science/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q","bundle":"https://pith.science/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q/bundle.json","state":"https://pith.science/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJVGME47C4WH5SR3NZ2BZNDI3Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJVGME47C4WH5SR3NZ2BZNDI3Q","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":"53a3e47d2c8a1a698acbe8c5f88cf17eb016bb740636dfab8efafd4f29aa131d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T12:48:14Z","title_canon_sha256":"30fda0f30498f124e8128529ceeab6197b42518b39ccc33eb64e878d06d039f0"},"schema_version":"1.0","source":{"id":"2410.13502","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13502","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13502v3","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13502","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"YJVGME47C4WH","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"YJVGME47C4WH5SR3","created_at":"2026-07-05T10:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"YJVGME47","created_at":"2026-07-05T10:14:24Z"}],"graph_snapshots":[{"event_id":"sha256:e012937b3982516756350c6957ec2747571ce9b6ed315843a3da9e3458a2f47b","target":"graph","created_at":"2026-07-05T10:14:24Z","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/2410.13502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to more complex problems. This is difficult to study, as (i) much of the available evaluation data has already been seen by the most capable models during training, and (ii) existing benchmarks do not capture how problem proofs may be arbitrarily complex in various ways. In this paper, we present a data-generation framework for evaluating LLMs on problems with arbitrarily complex arithmetic proofs, called MathGAP. MathGAP generates problem statements and chain-","authors_text":"Abulhair Saparov, Andreas Opedal, Bernhard Sch\\\"olkopf, Haruki Shirakami, Mrinmaya Sachan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T12:48:14Z","title":"MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13502","kind":"arxiv","version":3},"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":"sha256:1c9392c844a924a0ca272564a63c93ac31d9975e90914cdfbc79f29d06cce1a0","target":"record","created_at":"2026-07-05T10:14:24Z","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":"53a3e47d2c8a1a698acbe8c5f88cf17eb016bb740636dfab8efafd4f29aa131d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T12:48:14Z","title_canon_sha256":"30fda0f30498f124e8128529ceeab6197b42518b39ccc33eb64e878d06d039f0"},"schema_version":"1.0","source":{"id":"2410.13502","kind":"arxiv","version":3}},"canonical_sha256":"c26a66139f172c7eca3b6e741cb468dc0861c341239fee7d1ebc77f70997fb55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c26a66139f172c7eca3b6e741cb468dc0861c341239fee7d1ebc77f70997fb55","first_computed_at":"2026-07-05T10:14:24.564583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:24.564583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OUYdj9pgWslTUGVLtAAdRyLBII7Ub9KHtOcjnw++ymvTImE80Thn6H2xi/HNn6wJrsIaPvrGzHTnk2H6PaiyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:24.565116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13502","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c9392c844a924a0ca272564a63c93ac31d9975e90914cdfbc79f29d06cce1a0","sha256:e012937b3982516756350c6957ec2747571ce9b6ed315843a3da9e3458a2f47b"],"state_sha256":"65cbafe1d275f85fdbd54f227be20c812cb98cf71cd47ba9aaa80075d36cc1ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLkYRge0ZNdZP3s1nMKjKeWBOk0fxw56cqMI2Bb8Pw793C62iiotUiEx/fhD4IaIgU04KIkkPRrwL0WbzE1NBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:24:42.589565Z","bundle_sha256":"78a8c76dc9af23103b33c8472c685b54644d690b99dce5c62a4186ffc482d695"}}