{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H3SE3KEB5GDBSDC5OIK5SLNB54","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":"27c9a15c0c80ccd7d43039de75906f02b0045f92c349daa8b11608981fd4b4c2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T16:55:40Z","title_canon_sha256":"9ec0e5cbfc6e6eb2118f28c8b1dd5a8b3213db69591db3bba83bb4877539d4c4"},"schema_version":"1.0","source":{"id":"2312.17120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17120","created_at":"2026-07-05T09:27:52Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17120v2","created_at":"2026-07-05T09:27:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17120","created_at":"2026-07-05T09:27:52Z"},{"alias_kind":"pith_short_12","alias_value":"H3SE3KEB5GDB","created_at":"2026-07-05T09:27:52Z"},{"alias_kind":"pith_short_16","alias_value":"H3SE3KEB5GDBSDC5","created_at":"2026-07-05T09:27:52Z"},{"alias_kind":"pith_short_8","alias_value":"H3SE3KEB","created_at":"2026-07-05T09:27:52Z"}],"graph_snapshots":[{"event_id":"sha256:d8ede69edd9855590d6dea96cc61b84b6efae25679b943d8b81588aaa075ac42","target":"graph","created_at":"2026-07-05T09:27:52Z","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/2312.17120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality, large-scale corpora are the cornerstone of building foundation models. In this work, we introduce MathPile, a diverse and high-quality math-centric corpus comprising about 9.5 billion tokens. Throughout its creation, we adhered to the principle of \"less is more\", firmly believing in the supremacy of data quality over quantity, even in the pre-training phase. Our meticulous data collection and processing efforts included a complex suite of preprocessing, prefiltering, language identification, cleaning, filtering, and deduplication, ensuring the high quality of our corpus. Furtherm","authors_text":"Pengfei Liu, Rui Xia, Xuefeng Li, Zengzhi Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T16:55:40Z","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17120","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":"sha256:1fae071d357fb8db983b80a6201c61e0ac347a03f7f6eaf231b71fe46e0dedb3","target":"record","created_at":"2026-07-05T09:27:52Z","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":"27c9a15c0c80ccd7d43039de75906f02b0045f92c349daa8b11608981fd4b4c2","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-28T16:55:40Z","title_canon_sha256":"9ec0e5cbfc6e6eb2118f28c8b1dd5a8b3213db69591db3bba83bb4877539d4c4"},"schema_version":"1.0","source":{"id":"2312.17120","kind":"arxiv","version":2}},"canonical_sha256":"3ee44da881e986190c5d7215d92da1ef3b3b17853ead404f738bf87493a64600","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ee44da881e986190c5d7215d92da1ef3b3b17853ead404f738bf87493a64600","first_computed_at":"2026-07-05T09:27:52.178171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:52.178171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCgnCRxxheR1AnIlaf9aUhvwh+57SCX7+Vf/MUdYpztaQSv8bR6JeND3M6fHUYjsvVOVet/E3NfITIX27YLPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:52.178653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fae071d357fb8db983b80a6201c61e0ac347a03f7f6eaf231b71fe46e0dedb3","sha256:d8ede69edd9855590d6dea96cc61b84b6efae25679b943d8b81588aaa075ac42"],"state_sha256":"a122d70905828ee088f32b3731a6d09281b0130da0593de6d5bc7a8e3dde39cc"}