{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KIXHE2AEHCRMQHRQ62ZKBOQDHO","short_pith_number":"pith:KIXHE2AE","canonical_record":{"source":{"id":"2408.10839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"731cd04e118918629469a0ee2f36ac42ea177e931f11fcf00b0eb3df79fbf276","abstract_canon_sha256":"b9e6b967301fdc615d7f5b933530ed00104c04755509b1ba29ae33d093463c4e"},"schema_version":"1.0"},"canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","source":{"kind":"arxiv","id":"2408.10839","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10839","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10839v2","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10839","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"KIXHE2AEHCRM","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"KIXHE2AEHCRMQHRQ","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"KIXHE2AE","created_at":"2026-07-05T09:51:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KIXHE2AEHCRMQHRQ62ZKBOQDHO","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"731cd04e118918629469a0ee2f36ac42ea177e931f11fcf00b0eb3df79fbf276","abstract_canon_sha256":"b9e6b967301fdc615d7f5b933530ed00104c04755509b1ba29ae33d093463c4e"},"schema_version":"1.0"},"canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:35.528603Z","signature_b64":"EBle04dT60+mNA6w4iZnpV/+fu7hKqFFWlBfal0EBGFimYcWS1d0BaWU4Ij8W1xR5LcAiygfSH7cmnJ5Q6ogDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","last_reissued_at":"2026-07-05T09:51:35.528133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:35.528133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10839","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":"2026-07-05T09:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPj8uRQEHXgfYfzz+ZnSnPhpWrELSALWoiymHTkYRu7SjGc0eloEt3H0bRE3YFIIBJjW1wTjN59fVhjJD5wbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:32:16.709931Z"},"content_sha256":"2dc1f7ff8c9b8a92adf7db8be6420a52e6f3b6cde8d6757251bebb08c79e891f","schema_version":"1.0","event_id":"sha256:2dc1f7ff8c9b8a92adf7db8be6420a52e6f3b6cde8d6757251bebb08c79e891f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KIXHE2AEHCRMQHRQ62ZKBOQDHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models for Math Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Emek G\\\"ozl\\\"ukl\\\"u, Enkelejda Kasneci, Kathrin Se{\\ss}ler, Yao Rong","submitted_at":"2024-08-20T13:34:17Z","abstract_excerpt":"The use of Large Language Models (LLMs) in mathematical reasoning has become a cornerstone of related research, demonstrating the intelligence of these models and enabling potential practical applications through their advanced performance, such as in educational settings. Despite the variety of datasets and in-context learning algorithms designed to improve the ability of LLMs to automate mathematical problem solving, the lack of comprehensive benchmarking across different datasets makes it complicated to select an appropriate model for specific tasks. In this project, we present a benchmark "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10839","kind":"arxiv","version":2},"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/2408.10839/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":"2026-07-05T09:51:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtGBGhl9NAjjZ2u3x5pZaCDZ3JnflUA4+2cYcpM1g0ktZUTZfMfFG6lXrptxN++JrGPCcj1jzJKtbNHfzsgDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:32:16.710511Z"},"content_sha256":"74005399b3f4ee7a33c194f2ba006caf72364844069e3a54e3e9b86b1721645d","schema_version":"1.0","event_id":"sha256:74005399b3f4ee7a33c194f2ba006caf72364844069e3a54e3e9b86b1721645d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO/bundle.json","state_url":"https://pith.science/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO/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":"2026-08-05T12:32:16Z","links":{"resolver":"https://pith.science/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO","bundle":"https://pith.science/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO/bundle.json","state":"https://pith.science/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KIXHE2AEHCRMQHRQ62ZKBOQDHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KIXHE2AEHCRMQHRQ62ZKBOQDHO","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":"b9e6b967301fdc615d7f5b933530ed00104c04755509b1ba29ae33d093463c4e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","title_canon_sha256":"731cd04e118918629469a0ee2f36ac42ea177e931f11fcf00b0eb3df79fbf276"},"schema_version":"1.0","source":{"id":"2408.10839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10839","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10839v2","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10839","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_12","alias_value":"KIXHE2AEHCRM","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_16","alias_value":"KIXHE2AEHCRMQHRQ","created_at":"2026-07-05T09:51:35Z"},{"alias_kind":"pith_short_8","alias_value":"KIXHE2AE","created_at":"2026-07-05T09:51:35Z"}],"graph_snapshots":[{"event_id":"sha256:74005399b3f4ee7a33c194f2ba006caf72364844069e3a54e3e9b86b1721645d","target":"graph","created_at":"2026-07-05T09:51:35Z","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/2408.10839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of Large Language Models (LLMs) in mathematical reasoning has become a cornerstone of related research, demonstrating the intelligence of these models and enabling potential practical applications through their advanced performance, such as in educational settings. Despite the variety of datasets and in-context learning algorithms designed to improve the ability of LLMs to automate mathematical problem solving, the lack of comprehensive benchmarking across different datasets makes it complicated to select an appropriate model for specific tasks. In this project, we present a benchmark ","authors_text":"Emek G\\\"ozl\\\"ukl\\\"u, Enkelejda Kasneci, Kathrin Se{\\ss}ler, Yao Rong","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","title":"Benchmarking Large Language Models for Math Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10839","kind":"arxiv","version":2},"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":"sha256:2dc1f7ff8c9b8a92adf7db8be6420a52e6f3b6cde8d6757251bebb08c79e891f","target":"record","created_at":"2026-07-05T09:51:35Z","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":"b9e6b967301fdc615d7f5b933530ed00104c04755509b1ba29ae33d093463c4e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:34:17Z","title_canon_sha256":"731cd04e118918629469a0ee2f36ac42ea177e931f11fcf00b0eb3df79fbf276"},"schema_version":"1.0","source":{"id":"2408.10839","kind":"arxiv","version":2}},"canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"522e72680438a2c81e30f6b2a0ba033b9d903d64695ce3791de4fb6f18867964","first_computed_at":"2026-07-05T09:51:35.528133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:35.528133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EBle04dT60+mNA6w4iZnpV/+fu7hKqFFWlBfal0EBGFimYcWS1d0BaWU4Ij8W1xR5LcAiygfSH7cmnJ5Q6ogDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:35.528603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dc1f7ff8c9b8a92adf7db8be6420a52e6f3b6cde8d6757251bebb08c79e891f","sha256:74005399b3f4ee7a33c194f2ba006caf72364844069e3a54e3e9b86b1721645d"],"state_sha256":"18d5236e5be0fdbe4b591ff6891394f0f1280f89754efd860e7d5c863d13d968"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LMEGtYoKskLZ1fV2wy6OB7a++Lv9qGd9BjBoKVTg/9h9p3H5BLZmG/nOLNECujNZ96WIZW5F+Jf/h4qD6/WBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:32:16.715613Z","bundle_sha256":"a54a2fb12ba1560f10394b4bb52453330ad8cc2ec89a26e81937f21fa47a6023"}}