{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:S7SNYK5DTUSWB3SSDI4PVB67GF","short_pith_number":"pith:S7SNYK5D","schema_version":"1.0","canonical_sha256":"97e4dc2ba39d2560ee521a38fa87df316055ba67a40089cb5648aa8a2d9113c8","source":{"kind":"arxiv","id":"2307.14430","version":1},"attestation_state":"computed","paper":{"title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ce Zhang, Christopher R\\'e, Frederic Sala, Jue Wang, Kush Bhatia, Mayee F. Chen, Nicholas Roberts","submitted_at":"2023-07-26T18:01:49Z","abstract_excerpt":"The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new framework based on a simple hypothesis: just as humans acquire interdependent skills in a deliberate order, language models also follow a natural order when learning a set of skills from their training data. If such an order exists, it can be utilized for improved understanding of LMs and for data-efficient training. Using this intuition, our framework form"},"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":"2307.14430","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T18:01:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ee69d87a0b5d85a47dc464bde0bbb14d64490d0fac806034c610bc011292583d","abstract_canon_sha256":"adc47828f562240971e1921b4b55e9c49a992f5393a01e456446d6b3f14a6661"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:54.134270Z","signature_b64":"HOj7gpi9KTAnp/TDdel+cNN1B1jWRZUUZhweNBShegwvPLcf/t++JSPETdyIt+dqrO/eiv32Ex6fA/gUedznBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97e4dc2ba39d2560ee521a38fa87df316055ba67a40089cb5648aa8a2d9113c8","last_reissued_at":"2026-07-05T06:35:54.133892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:54.133892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ce Zhang, Christopher R\\'e, Frederic Sala, Jue Wang, Kush Bhatia, Mayee F. Chen, Nicholas Roberts","submitted_at":"2023-07-26T18:01:49Z","abstract_excerpt":"The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new framework based on a simple hypothesis: just as humans acquire interdependent skills in a deliberate order, language models also follow a natural order when learning a set of skills from their training data. If such an order exists, it can be utilized for improved understanding of LMs and for data-efficient training. Using this intuition, our framework form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14430","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/2307.14430/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":"2307.14430","created_at":"2026-07-05T06:35:54.133948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14430v1","created_at":"2026-07-05T06:35:54.133948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14430","created_at":"2026-07-05T06:35:54.133948+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7SNYK5DTUSW","created_at":"2026-07-05T06:35:54.133948+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7SNYK5DTUSWB3SS","created_at":"2026-07-05T06:35:54.133948+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7SNYK5D","created_at":"2026-07-05T06:35:54.133948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09844","citing_title":"MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Training","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11255","citing_title":"HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language Model","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":257,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF","json":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF.json","graph_json":"https://pith.science/api/pith-number/S7SNYK5DTUSWB3SSDI4PVB67GF/graph.json","events_json":"https://pith.science/api/pith-number/S7SNYK5DTUSWB3SSDI4PVB67GF/events.json","paper":"https://pith.science/paper/S7SNYK5D"},"agent_actions":{"view_html":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF","download_json":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF.json","view_paper":"https://pith.science/paper/S7SNYK5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14430&json=true","fetch_graph":"https://pith.science/api/pith-number/S7SNYK5DTUSWB3SSDI4PVB67GF/graph.json","fetch_events":"https://pith.science/api/pith-number/S7SNYK5DTUSWB3SSDI4PVB67GF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF/action/storage_attestation","attest_author":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF/action/author_attestation","sign_citation":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF/action/citation_signature","submit_replication":"https://pith.science/pith/S7SNYK5DTUSWB3SSDI4PVB67GF/action/replication_record"}},"created_at":"2026-07-05T06:35:54.133948+00:00","updated_at":"2026-07-05T06:35:54.133948+00:00"}