{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FVNFZXGGDBAMCTPUMX5EEPOQPW","short_pith_number":"pith:FVNFZXGG","canonical_record":{"source":{"id":"2404.13925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T07:03:44Z","cross_cats_sorted":[],"title_canon_sha256":"56ff3a2bd2fc699e22bbd5a2d2ae0b0c4675a73b670089d1c3c4a563d9cb348e","abstract_canon_sha256":"8cfd7d4525704b452d7ed288fadedf63a8d81e67e50b087ea99a46995bc7b83d"},"schema_version":"1.0"},"canonical_sha256":"2d5a5cdcc61840c14df465fa423dd07d85b5dcde9bdcaa229e6938aa685c8a0c","source":{"kind":"arxiv","id":"2404.13925","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13925","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13925v1","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13925","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"pith_short_12","alias_value":"FVNFZXGGDBAM","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"pith_short_16","alias_value":"FVNFZXGGDBAMCTPU","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"pith_short_8","alias_value":"FVNFZXGG","created_at":"2026-07-05T08:10:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FVNFZXGGDBAMCTPUMX5EEPOQPW","target":"record","payload":{"canonical_record":{"source":{"id":"2404.13925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T07:03:44Z","cross_cats_sorted":[],"title_canon_sha256":"56ff3a2bd2fc699e22bbd5a2d2ae0b0c4675a73b670089d1c3c4a563d9cb348e","abstract_canon_sha256":"8cfd7d4525704b452d7ed288fadedf63a8d81e67e50b087ea99a46995bc7b83d"},"schema_version":"1.0"},"canonical_sha256":"2d5a5cdcc61840c14df465fa423dd07d85b5dcde9bdcaa229e6938aa685c8a0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:39.386425Z","signature_b64":"Ev7P/3QZ+hUOJEV6Hawztq7k1Sbx8Tmu9l4yoL4aVfPQwoX2BJCS5p4QpTonxhxUQzSmaEh+UgRUlEElopG6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d5a5cdcc61840c14df465fa423dd07d85b5dcde9bdcaa229e6938aa685c8a0c","last_reissued_at":"2026-07-05T08:10:39.385919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:39.385919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.13925","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HqWQ1rufd73oDPLHjf0m2F9waZ+lUVqrQgRO6gWPimXufrXUuLQvmyLikI29THwmaAzIOX73dK53ptW+bTe7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:44:41.338368Z"},"content_sha256":"d6edef1f8d51ee6d67cef00188e72f943c25651aa2f66ef442947233fe335070","schema_version":"1.0","event_id":"sha256:d6edef1f8d51ee6d67cef00188e72f943c25651aa2f66ef442947233fe335070"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FVNFZXGGDBAMCTPUMX5EEPOQPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boning Zhang, Chengxi Li, Kai Fan","submitted_at":"2024-04-22T07:03:44Z","abstract_excerpt":"Large language models (LLMs) have been explored in a variety of reasoning tasks including solving of mathematical problems. Each math dataset typically includes its own specially designed evaluation script, which, while suitable for its intended use, lacks generalizability across different datasets. Consequently, updates and adaptations to these evaluation tools tend to occur without being systematically reported, leading to inconsistencies and obstacles to fair comparison across studies. To bridge this gap, we introduce a comprehensive mathematical evaluation toolkit that not only utilizes a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13925","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/2404.13925/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":"2026-07-05T08:10:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTqXOaGtPJzTU8blDtgujqiWsE+RG6+pepciLrmjSBJHDn5d02r6MryzIIUzVCs+NeSjG4pjaK5RnbmbufIwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:44:41.338745Z"},"content_sha256":"e6bbeebd97d07b2916f6905d488db43c3ceea0fed6f741dc714cd5e80965e7ca","schema_version":"1.0","event_id":"sha256:e6bbeebd97d07b2916f6905d488db43c3ceea0fed6f741dc714cd5e80965e7ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW/bundle.json","state_url":"https://pith.science/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW/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":"2026-07-24T23:44:41Z","links":{"resolver":"https://pith.science/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW","bundle":"https://pith.science/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW/bundle.json","state":"https://pith.science/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVNFZXGGDBAMCTPUMX5EEPOQPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FVNFZXGGDBAMCTPUMX5EEPOQPW","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":"8cfd7d4525704b452d7ed288fadedf63a8d81e67e50b087ea99a46995bc7b83d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T07:03:44Z","title_canon_sha256":"56ff3a2bd2fc699e22bbd5a2d2ae0b0c4675a73b670089d1c3c4a563d9cb348e"},"schema_version":"1.0","source":{"id":"2404.13925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.13925","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.13925v1","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13925","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"pith_short_12","alias_value":"FVNFZXGGDBAM","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"pith_short_16","alias_value":"FVNFZXGGDBAMCTPU","created_at":"2026-07-05T08:10:39Z"},{"alias_kind":"pith_short_8","alias_value":"FVNFZXGG","created_at":"2026-07-05T08:10:39Z"}],"graph_snapshots":[{"event_id":"sha256:e6bbeebd97d07b2916f6905d488db43c3ceea0fed6f741dc714cd5e80965e7ca","target":"graph","created_at":"2026-07-05T08:10:39Z","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/2404.13925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been explored in a variety of reasoning tasks including solving of mathematical problems. Each math dataset typically includes its own specially designed evaluation script, which, while suitable for its intended use, lacks generalizability across different datasets. Consequently, updates and adaptations to these evaluation tools tend to occur without being systematically reported, leading to inconsistencies and obstacles to fair comparison across studies. To bridge this gap, we introduce a comprehensive mathematical evaluation toolkit that not only utilizes a ","authors_text":"Boning Zhang, Chengxi Li, Kai Fan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T07:03:44Z","title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13925","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:d6edef1f8d51ee6d67cef00188e72f943c25651aa2f66ef442947233fe335070","target":"record","created_at":"2026-07-05T08:10:39Z","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":"8cfd7d4525704b452d7ed288fadedf63a8d81e67e50b087ea99a46995bc7b83d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-22T07:03:44Z","title_canon_sha256":"56ff3a2bd2fc699e22bbd5a2d2ae0b0c4675a73b670089d1c3c4a563d9cb348e"},"schema_version":"1.0","source":{"id":"2404.13925","kind":"arxiv","version":1}},"canonical_sha256":"2d5a5cdcc61840c14df465fa423dd07d85b5dcde9bdcaa229e6938aa685c8a0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d5a5cdcc61840c14df465fa423dd07d85b5dcde9bdcaa229e6938aa685c8a0c","first_computed_at":"2026-07-05T08:10:39.385919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:39.385919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ev7P/3QZ+hUOJEV6Hawztq7k1Sbx8Tmu9l4yoL4aVfPQwoX2BJCS5p4QpTonxhxUQzSmaEh+UgRUlEElopG6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:39.386425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.13925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6edef1f8d51ee6d67cef00188e72f943c25651aa2f66ef442947233fe335070","sha256:e6bbeebd97d07b2916f6905d488db43c3ceea0fed6f741dc714cd5e80965e7ca"],"state_sha256":"d3015b060a9b550cd2832a1005e8ab258c6cc28d7c8336b04c282e2f22b26f5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A3qidNsDVFwCLg0Ea0dWkEoWQaAt27TkUV4un/hUjhhbhpgbO0Rwe0nJz8zi04RSQdi1A+YFZXlQV9yEs6YIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T23:44:41.340895Z","bundle_sha256":"6ef64c8f31c78bd1560ace5ad71fa863246c9533d70db3414ba16f1ce6de569d"}}