{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QTVBZ6NC25M27GOPFR6KNG5MZ7","short_pith_number":"pith:QTVBZ6NC","schema_version":"1.0","canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","source":{"kind":"arxiv","id":"2210.00987","version":1},"attestation_state":"computed","paper":{"title":"Data Budgeting for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James Zou, Weixin Liang, Xinyi Zhao","submitted_at":"2022-10-03T14:53:17Z","abstract_excerpt":"Data is the fuel powering AI and creates tremendous value for many domains. However, collecting datasets for AI is a time-consuming, expensive, and complicated endeavor. For practitioners, data investment remains to be a leap of faith in practice. In this work, we study the data budgeting problem and formulate it as two sub-problems: predicting (1) what is the saturating performance if given enough data, and (2) how many data points are needed to reach near the saturating performance. Different from traditional dataset-independent methods like PowerLaw, we proposed a learning method to solve d"},"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":"2210.00987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-03T14:53:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5656bd4abd82195f7794773b79ef3853b9b6fce7d27a0b584909556909439abc","abstract_canon_sha256":"e1bb9761c474325275f62c2a13fb7ee1211a2ac90a0cb432266c9cb30e6b92ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:49.944767Z","signature_b64":"9sYqFuJ7SmOj4cxm21wDrgn/e730VANom9qZU7tBfKHi8PvVgITJdyFqVVkVfPivPJEbY/syImP30i9KzHPBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ea1cf9a2d759af99cf2c7ca69baccffff4f78e8476bb3d1e542ed6618907d8","last_reissued_at":"2026-07-05T05:02:49.944331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:49.944331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Budgeting for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James Zou, Weixin Liang, Xinyi Zhao","submitted_at":"2022-10-03T14:53:17Z","abstract_excerpt":"Data is the fuel powering AI and creates tremendous value for many domains. However, collecting datasets for AI is a time-consuming, expensive, and complicated endeavor. For practitioners, data investment remains to be a leap of faith in practice. In this work, we study the data budgeting problem and formulate it as two sub-problems: predicting (1) what is the saturating performance if given enough data, and (2) how many data points are needed to reach near the saturating performance. Different from traditional dataset-independent methods like PowerLaw, we proposed a learning method to solve d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00987","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/2210.00987/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":"2210.00987","created_at":"2026-07-05T05:02:49.944395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00987v1","created_at":"2026-07-05T05:02:49.944395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00987","created_at":"2026-07-05T05:02:49.944395+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTVBZ6NC25M2","created_at":"2026-07-05T05:02:49.944395+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTVBZ6NC25M27GOP","created_at":"2026-07-05T05:02:49.944395+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTVBZ6NC","created_at":"2026-07-05T05:02:49.944395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12636","citing_title":"PyAWD: A Library for Generating Large Synthetic Datasets of Acoustic Wave Propagation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7","json":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7.json","graph_json":"https://pith.science/api/pith-number/QTVBZ6NC25M27GOPFR6KNG5MZ7/graph.json","events_json":"https://pith.science/api/pith-number/QTVBZ6NC25M27GOPFR6KNG5MZ7/events.json","paper":"https://pith.science/paper/QTVBZ6NC"},"agent_actions":{"view_html":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7","download_json":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7.json","view_paper":"https://pith.science/paper/QTVBZ6NC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00987&json=true","fetch_graph":"https://pith.science/api/pith-number/QTVBZ6NC25M27GOPFR6KNG5MZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/QTVBZ6NC25M27GOPFR6KNG5MZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/action/storage_attestation","attest_author":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/action/author_attestation","sign_citation":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/action/citation_signature","submit_replication":"https://pith.science/pith/QTVBZ6NC25M27GOPFR6KNG5MZ7/action/replication_record"}},"created_at":"2026-07-05T05:02:49.944395+00:00","updated_at":"2026-07-05T05:02:49.944395+00:00"}