{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RDUGTKHLPWBNTCD5NPGNRLN4AB","short_pith_number":"pith:RDUGTKHL","schema_version":"1.0","canonical_sha256":"88e869a8eb7d82d9887d6bccd8adbc005f7e91898b5a12682d1e63107339dcb6","source":{"kind":"arxiv","id":"2504.02807","version":1},"attestation_state":"computed","paper":{"title":"MegaMath: Pushing the Limits of Open Math Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric P. Xing, Fan Zhou, Guowei He, Liping Tang, Nikhil Ranjan, Zengzhi Wang, Zhengzhong Liu, Zhoujun Cheng","submitted_at":"2025-04-03T17:52:07Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.02807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-03T17:52:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"de379e4b024b3f02753eda4fdb1783bfc130aad26ff4fc3cea738a4199cee1ba","abstract_canon_sha256":"c249fc9bad26115bf562126a00db6bba2b475632fe2b5acbea7bf023933bbe7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:02.689268Z","signature_b64":"s15Hodr6qgdeGIbHqFnD4P6vwEeRgDlF7EDAhNNN7MhYP6tLMvX2h+I94Im2WqIEP+H0o6tanbsKSERW0HVpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88e869a8eb7d82d9887d6bccd8adbc005f7e91898b5a12682d1e63107339dcb6","last_reissued_at":"2026-07-05T10:44:02.688794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:02.688794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegaMath: Pushing the Limits of Open Math Corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric P. Xing, Fan Zhou, Guowei He, Liping Tang, Nikhil Ranjan, Zengzhi Wang, Zhengzhong Liu, Zhoujun Cheng","submitted_at":"2025-04-03T17:52:07Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02807","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/2504.02807/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.02807","created_at":"2026-07-05T10:44:02.688851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02807v1","created_at":"2026-07-05T10:44:02.688851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02807","created_at":"2026-07-05T10:44:02.688851+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDUGTKHLPWBN","created_at":"2026-07-05T10:44:02.688851+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDUGTKHLPWBNTCD5","created_at":"2026-07-05T10:44:02.688851+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDUGTKHL","created_at":"2026-07-05T10:44:02.688851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19005","citing_title":"Sumi: Open Uniform Diffusion Language Model from Scratch","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12385","citing_title":"Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15079","citing_title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18025","citing_title":"TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06499","citing_title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20856","citing_title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14067","citing_title":"Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2504.11456","citing_title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25741","citing_title":"Scaling Latent Reasoning via Looped Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05688","citing_title":"Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB","json":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB.json","graph_json":"https://pith.science/api/pith-number/RDUGTKHLPWBNTCD5NPGNRLN4AB/graph.json","events_json":"https://pith.science/api/pith-number/RDUGTKHLPWBNTCD5NPGNRLN4AB/events.json","paper":"https://pith.science/paper/RDUGTKHL"},"agent_actions":{"view_html":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB","download_json":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB.json","view_paper":"https://pith.science/paper/RDUGTKHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02807&json=true","fetch_graph":"https://pith.science/api/pith-number/RDUGTKHLPWBNTCD5NPGNRLN4AB/graph.json","fetch_events":"https://pith.science/api/pith-number/RDUGTKHLPWBNTCD5NPGNRLN4AB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB/action/storage_attestation","attest_author":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB/action/author_attestation","sign_citation":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB/action/citation_signature","submit_replication":"https://pith.science/pith/RDUGTKHLPWBNTCD5NPGNRLN4AB/action/replication_record"}},"created_at":"2026-07-05T10:44:02.688851+00:00","updated_at":"2026-07-05T10:44:02.688851+00:00"}