{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OEBOCQUGNATC2UAPYI4W3UFBSY","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":"1e70ab155e8c41ed3597b8b8af86f063292e903f07b2511b9e18db8fcba4d751","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T02:09:21Z","title_canon_sha256":"2fe3317a902f9205433e83085db3ed1bd3333f4271125afa1808c48b686f412f"},"schema_version":"1.0","source":{"id":"2401.17542","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17542","created_at":"2026-07-05T08:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17542v3","created_at":"2026-07-05T08:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17542","created_at":"2026-07-05T08:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"OEBOCQUGNATC","created_at":"2026-07-05T08:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"OEBOCQUGNATC2UAP","created_at":"2026-07-05T08:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"OEBOCQUG","created_at":"2026-07-05T08:56:03Z"}],"graph_snapshots":[{"event_id":"sha256:0994ee2603fc2182578cec3226610f165597c6291617910f4452685c41c5a5db","target":"graph","created_at":"2026-07-05T08:56:03Z","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/2401.17542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Yan, Weimin Tan, Wenxuan Yang, Yuqi Sun","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T02:09:21Z","title":"A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17542","kind":"arxiv","version":3},"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":"sha256:0e4dcab74cba1d52d0779f5ed59ee73ed045fcf6b8bf4ecd9364b3174ccb846e","target":"record","created_at":"2026-07-05T08:56:03Z","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":"1e70ab155e8c41ed3597b8b8af86f063292e903f07b2511b9e18db8fcba4d751","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T02:09:21Z","title_canon_sha256":"2fe3317a902f9205433e83085db3ed1bd3333f4271125afa1808c48b686f412f"},"schema_version":"1.0","source":{"id":"2401.17542","kind":"arxiv","version":3}},"canonical_sha256":"7102e1428668262d500fc2396dd0a1963d1c05c07825ebf6aac41f89b7a520a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7102e1428668262d500fc2396dd0a1963d1c05c07825ebf6aac41f89b7a520a1","first_computed_at":"2026-07-05T08:56:03.280539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:03.280539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YBp3rj/PWZuwagxsWb3MKp7PfPo7oRXqNfgYa6HNKVsptTA+Kj97ezlNYELLWHi5/Q46XTWacC/m5Qm5SCTMAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:03.280950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17542","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e4dcab74cba1d52d0779f5ed59ee73ed045fcf6b8bf4ecd9364b3174ccb846e","sha256:0994ee2603fc2182578cec3226610f165597c6291617910f4452685c41c5a5db"],"state_sha256":"1953ef73d54d0a47313cfaec043ab6cbe9685b0a75231f8fb6beceb810f79470"}