{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S7SNYK5DTUSWB3SSDI4PVB67GF","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":"adc47828f562240971e1921b4b55e9c49a992f5393a01e456446d6b3f14a6661","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T18:01:49Z","title_canon_sha256":"ee69d87a0b5d85a47dc464bde0bbb14d64490d0fac806034c610bc011292583d"},"schema_version":"1.0","source":{"id":"2307.14430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.14430","created_at":"2026-07-05T06:35:54Z"},{"alias_kind":"arxiv_version","alias_value":"2307.14430v1","created_at":"2026-07-05T06:35:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14430","created_at":"2026-07-05T06:35:54Z"},{"alias_kind":"pith_short_12","alias_value":"S7SNYK5DTUSW","created_at":"2026-07-05T06:35:54Z"},{"alias_kind":"pith_short_16","alias_value":"S7SNYK5DTUSWB3SS","created_at":"2026-07-05T06:35:54Z"},{"alias_kind":"pith_short_8","alias_value":"S7SNYK5D","created_at":"2026-07-05T06:35:54Z"}],"graph_snapshots":[{"event_id":"sha256:7db1a76a6bee3efa35118ff496d33c459bc32afe8835b50a0d730ae4bb42bc30","target":"graph","created_at":"2026-07-05T06:35:54Z","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/2307.14430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ce Zhang, Christopher R\\'e, Frederic Sala, Jue Wang, Kush Bhatia, Mayee F. Chen, Nicholas Roberts","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T18:01:49Z","title":"Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14430","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":"sha256:72120cae0ea008f42e78d7a8ffe6630d183402d024e09f3b990fd4d5db6e8807","target":"record","created_at":"2026-07-05T06:35:54Z","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":"adc47828f562240971e1921b4b55e9c49a992f5393a01e456446d6b3f14a6661","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T18:01:49Z","title_canon_sha256":"ee69d87a0b5d85a47dc464bde0bbb14d64490d0fac806034c610bc011292583d"},"schema_version":"1.0","source":{"id":"2307.14430","kind":"arxiv","version":1}},"canonical_sha256":"97e4dc2ba39d2560ee521a38fa87df316055ba67a40089cb5648aa8a2d9113c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97e4dc2ba39d2560ee521a38fa87df316055ba67a40089cb5648aa8a2d9113c8","first_computed_at":"2026-07-05T06:35:54.133892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:54.133892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HOj7gpi9KTAnp/TDdel+cNN1B1jWRZUUZhweNBShegwvPLcf/t++JSPETdyIt+dqrO/eiv32Ex6fA/gUedznBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:54.134270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.14430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72120cae0ea008f42e78d7a8ffe6630d183402d024e09f3b990fd4d5db6e8807","sha256:7db1a76a6bee3efa35118ff496d33c459bc32afe8835b50a0d730ae4bb42bc30"],"state_sha256":"75ea21836a6fcabb58c7582ae4dd0398a779f8ba59135cc0293f9d45043dfe18"}