{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OEBOCQUGNATC2UAPYI4W3UFBSY","short_pith_number":"pith:OEBOCQUG","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"},"canonical_sha256":"7102e1428668262d500fc2396dd0a1963d1c05c07825ebf6aac41f89b7a520a1","source":{"kind":"arxiv","id":"2401.17542","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OEBOCQUGNATC2UAPYI4W3UFBSY","target":"record","payload":{"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"},"canonical_sha256":"7102e1428668262d500fc2396dd0a1963d1c05c07825ebf6aac41f89b7a520a1","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"},"source_kind":"arxiv","source_id":"2401.17542","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvF0d2muCiwiTOhuVUaABRhvys65nxQdjRbV8rCexoCj0ppWQgzToX1EhPaikBRuH78M2ZRDgDNoV5+Lib4+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:24:48.105735Z"},"content_sha256":"0e4dcab74cba1d52d0779f5ed59ee73ed045fcf6b8bf4ecd9364b3174ccb846e","schema_version":"1.0","event_id":"sha256:0e4dcab74cba1d52d0779f5ed59ee73ed045fcf6b8bf4ecd9364b3174ccb846e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OEBOCQUGNATC2UAPYI4W3UFBSY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJPz11ObKzxNP1gAu37FmCmqAM5h1P4Q/r5bvR2Vfqohv858Ez9VmUvCulYVIBep3LxugF6ii5h8/Hu7/QgrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:24:48.106050Z"},"content_sha256":"0994ee2603fc2182578cec3226610f165597c6291617910f4452685c41c5a5db","schema_version":"1.0","event_id":"sha256:0994ee2603fc2182578cec3226610f165597c6291617910f4452685c41c5a5db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/bundle.json","state_url":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T13:24:48Z","links":{"resolver":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY","bundle":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/bundle.json","state":"https://pith.science/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OEBOCQUGNATC2UAPYI4W3UFBSY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fsfvKt/7AWqak1MKiOtwUbggfZ1Hk864EYE57HEsDFKEgbI5SuZRIJsNrA5Qxsh0DlYszueUOCNXjUmKLgvJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:24:48.109085Z","bundle_sha256":"b38000d8410fb897f2ab73acb58035dc70c7c211a1be9abadb3231499796d732"}}