{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OEBOCQUGNATC2UAPYI4W3UFBSY","short_pith_number":"pith:OEBOCQUG","schema_version":"1.0","canonical_sha256":"7102e1428668262d500fc2396dd0a1963d1c05c07825ebf6aac41f89b7a520a1","source":{"kind":"arxiv","id":"2401.17542","version":3},"attestation_state":"computed","paper":{"title":"A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Yan, Weimin Tan, Wenxuan Yang, Yuqi Sun","submitted_at":"2024-01-31T02:09:21Z","abstract_excerpt":"Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. Data-effective learning plays a profound role in accelerating foundation model training, reducing computatio"},"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":"2401.17542","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T02:09:21Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2fe3317a902f9205433e83085db3ed1bd3333f4271125afa1808c48b686f412f","abstract_canon_sha256":"1e70ab155e8c41ed3597b8b8af86f063292e903f07b2511b9e18db8fcba4d751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:03.280950Z","signature_b64":"YBp3rj/PWZuwagxsWb3MKp7PfPo7oRXqNfgYa6HNKVsptTA+Kj97ezlNYELLWHi5/Q46XTWacC/m5Qm5SCTMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7102e1428668262d500fc2396dd0a1963d1c05c07825ebf6aac41f89b7a520a1","last_reissued_at":"2026-07-05T08:56:03.280539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:03.280539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Yan, Weimin Tan, Wenxuan Yang, Yuqi Sun","submitted_at":"2024-01-31T02:09:21Z","abstract_excerpt":"Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. Data-effective learning plays a profound role in accelerating foundation model training, reducing computatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17542","kind":"arxiv","version":3},"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/2401.17542/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":"2401.17542","created_at":"2026-07-05T08:56:03.280595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17542v3","created_at":"2026-07-05T08:56:03.280595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17542","created_at":"2026-07-05T08:56:03.280595+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEBOCQUGNATC","created_at":"2026-07-05T08:56:03.280595+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEBOCQUGNATC2UAP","created_at":"2026-07-05T08:56:03.280595+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEBOCQUG","created_at":"2026-07-05T08:56:03.280595+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/OEBOCQUGNATC2UAPYI4W3UFBSY","json":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY.json","graph_json":"https://pith.science/api/pith-number/OEBOCQUGNATC2UAPYI4W3UFBSY/graph.json","events_json":"https://pith.science/api/pith-number/OEBOCQUGNATC2UAPYI4W3UFBSY/events.json","paper":"https://pith.science/paper/OEBOCQUG"},"agent_actions":{"view_html":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY","download_json":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY.json","view_paper":"https://pith.science/paper/OEBOCQUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17542&json=true","fetch_graph":"https://pith.science/api/pith-number/OEBOCQUGNATC2UAPYI4W3UFBSY/graph.json","fetch_events":"https://pith.science/api/pith-number/OEBOCQUGNATC2UAPYI4W3UFBSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/action/storage_attestation","attest_author":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/action/author_attestation","sign_citation":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/action/citation_signature","submit_replication":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/action/replication_record"}},"created_at":"2026-07-05T08:56:03.280595+00:00","updated_at":"2026-07-05T08:56:03.280595+00:00"}