{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RDUGTKHLPWBNTCD5NPGNRLN4AB","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":"c249fc9bad26115bf562126a00db6bba2b475632fe2b5acbea7bf023933bbe7c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:52:07Z","title_canon_sha256":"de379e4b024b3f02753eda4fdb1783bfc130aad26ff4fc3cea738a4199cee1ba"},"schema_version":"1.0","source":{"id":"2504.02807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02807","created_at":"2026-07-05T10:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02807v1","created_at":"2026-07-05T10:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02807","created_at":"2026-07-05T10:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"RDUGTKHLPWBN","created_at":"2026-07-05T10:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"RDUGTKHLPWBNTCD5","created_at":"2026-07-05T10:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"RDUGTKHL","created_at":"2026-07-05T10:44:02Z"}],"graph_snapshots":[{"event_id":"sha256:58fea5a249396b92c4113bc37b631032286e88c022e000ea99b16cb67d637386","target":"graph","created_at":"2026-07-05T10:44:02Z","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/2504.02807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mathematical reasoning is a cornerstone of human intelligence and a key benchmark for advanced capabilities in large language models (LLMs). However, the research community still lacks an open, large-scale, high-quality corpus tailored to the demands of math-centric LLM pre-training. We present MegaMath, an open dataset curated from diverse, math-focused sources through following practices: (1) Revisiting web data: We re-extracted mathematical documents from Common Crawl with math-oriented HTML optimizations, fasttext-based filtering and deduplication, all for acquiring higher-quality data on ","authors_text":"Eric P. Xing, Fan Zhou, Guowei He, Liping Tang, Nikhil Ranjan, Zengzhi Wang, Zhengzhong Liu, Zhoujun Cheng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:52:07Z","title":"MegaMath: Pushing the Limits of Open Math Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02807","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:d6b0f16a602d589d78394ee00eaa31d16cca636d3873dedc4fc1ba3fb11dde46","target":"record","created_at":"2026-07-05T10:44:02Z","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":"c249fc9bad26115bf562126a00db6bba2b475632fe2b5acbea7bf023933bbe7c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:52:07Z","title_canon_sha256":"de379e4b024b3f02753eda4fdb1783bfc130aad26ff4fc3cea738a4199cee1ba"},"schema_version":"1.0","source":{"id":"2504.02807","kind":"arxiv","version":1}},"canonical_sha256":"88e869a8eb7d82d9887d6bccd8adbc005f7e91898b5a12682d1e63107339dcb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88e869a8eb7d82d9887d6bccd8adbc005f7e91898b5a12682d1e63107339dcb6","first_computed_at":"2026-07-05T10:44:02.688794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:02.688794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s15Hodr6qgdeGIbHqFnD4P6vwEeRgDlF7EDAhNNN7MhYP6tLMvX2h+I94Im2WqIEP+H0o6tanbsKSERW0HVpBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:02.689268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6b0f16a602d589d78394ee00eaa31d16cca636d3873dedc4fc1ba3fb11dde46","sha256:58fea5a249396b92c4113bc37b631032286e88c022e000ea99b16cb67d637386"],"state_sha256":"df8faec0e9c83d28e5b0423df46709f8ebe2e7f662590f755a397626db9a7f34"}