{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LL24SY5YFHOI3WCIWVETXMZFFJ","short_pith_number":"pith:LL24SY5Y","schema_version":"1.0","canonical_sha256":"5af5c963b829dc8dd848b5493bb3252a5f798b46cb4a36155758ac66fcfcae2b","source":{"kind":"arxiv","id":"2407.08348","version":2},"attestation_state":"computed","paper":{"title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Han Fang, Jujie He, Liangjun Zhong, Liang Zeng, Liang Zhao, Liu Yang, Rui Hu, Shuicheng Yan, Tianwen Wei, Yahui Zhou, Yang Liu","submitted_at":"2024-07-11T09:56:51Z","abstract_excerpt":"In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs). We argue that the data scaling law for math reasoning capabilities in modern LLMs is far from being saturated, highlighting how the model's quality improves with increases in data quantity. To support this claim, we introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B LLMs using our proposed 2.5M-instance Skywork-MathQA dataset. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH"},"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":"2407.08348","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T09:56:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"0e0e0bb4dfe205c9b2e4917ae65d8318ad22763f56a617e409ca692ebb1bd495","abstract_canon_sha256":"50dfad138185a5e4339de90b6668c33ecf9eb8e3a61c843d84acc9783ff7e6b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:56.337099Z","signature_b64":"htS7ohLGt07yl6zKp1d5HMB06SZnlyBzucEBQ/iXqnBz0BWMFSOlR959/QpBIz4nbXO+rq1KQ3oC1QIaVRHvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5af5c963b829dc8dd848b5493bb3252a5f798b46cb4a36155758ac66fcfcae2b","last_reissued_at":"2026-07-05T08:44:56.336645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:56.336645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cheng cheng, Han Fang, Jujie He, Liangjun Zhong, Liang Zeng, Liang Zhao, Liu Yang, Rui Hu, Shuicheng Yan, Tianwen Wei, Yahui Zhou, Yang Liu","submitted_at":"2024-07-11T09:56:51Z","abstract_excerpt":"In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs). We argue that the data scaling law for math reasoning capabilities in modern LLMs is far from being saturated, highlighting how the model's quality improves with increases in data quantity. To support this claim, we introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B LLMs using our proposed 2.5M-instance Skywork-MathQA dataset. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08348","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/2407.08348/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":"2407.08348","created_at":"2026-07-05T08:44:56.336712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08348v2","created_at":"2026-07-05T08:44:56.336712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08348","created_at":"2026-07-05T08:44:56.336712+00:00"},{"alias_kind":"pith_short_12","alias_value":"LL24SY5YFHOI","created_at":"2026-07-05T08:44:56.336712+00:00"},{"alias_kind":"pith_short_16","alias_value":"LL24SY5YFHOI3WCI","created_at":"2026-07-05T08:44:56.336712+00:00"},{"alias_kind":"pith_short_8","alias_value":"LL24SY5Y","created_at":"2026-07-05T08:44:56.336712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ","json":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ.json","graph_json":"https://pith.science/api/pith-number/LL24SY5YFHOI3WCIWVETXMZFFJ/graph.json","events_json":"https://pith.science/api/pith-number/LL24SY5YFHOI3WCIWVETXMZFFJ/events.json","paper":"https://pith.science/paper/LL24SY5Y"},"agent_actions":{"view_html":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ","download_json":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ.json","view_paper":"https://pith.science/paper/LL24SY5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08348&json=true","fetch_graph":"https://pith.science/api/pith-number/LL24SY5YFHOI3WCIWVETXMZFFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LL24SY5YFHOI3WCIWVETXMZFFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ/action/storage_attestation","attest_author":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ/action/author_attestation","sign_citation":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ/action/citation_signature","submit_replication":"https://pith.science/pith/LL24SY5YFHOI3WCIWVETXMZFFJ/action/replication_record"}},"created_at":"2026-07-05T08:44:56.336712+00:00","updated_at":"2026-07-05T08:44:56.336712+00:00"}