{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XHZKSEMV7BQ6VNCVGOQ5EWFDGU","short_pith_number":"pith:XHZKSEMV","schema_version":"1.0","canonical_sha256":"b9f2a91195f861eab45533a1d258a335001afe20315b043569687f9845b26601","source":{"kind":"arxiv","id":"2411.09126","version":1},"attestation_state":"computed","paper":{"title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mohan Kankanhalli, Yangyang Guo","submitted_at":"2024-11-14T01:53:17Z","abstract_excerpt":"While contrastive pre-training is widely employed, its data efficiency problem has remained relatively under-explored thus far. Existing methods often rely on static coreset selection algorithms to pre-identify important data for training. However, this static nature renders them unable to dynamically track the data usefulness throughout pre-training, leading to subpar pre-trained models. To address this challenge, our paper introduces a novel dynamic bootstrapping dataset pruning method. It involves pruning data preparation followed by dataset mutation operations, both of which undergo iterat"},"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":"2411.09126","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T01:53:17Z","cross_cats_sorted":[],"title_canon_sha256":"697cc39531b3793f7ec659de19b9a32f9545abceb02117396ea81c1aa10eaa19","abstract_canon_sha256":"db1a0b62b60f7df373abf50ac7b928d1c5afe2cfbd3e0920c5300dc778d3846a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:20.581104Z","signature_b64":"jn2qFlazmyBz4D010ZBgBKHvol5zkKvd/66THZzbccgNgu+JLNSbv/VWg5+ESDomjewWziveqsEPrv9vhpSwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9f2a91195f861eab45533a1d258a335001afe20315b043569687f9845b26601","last_reissued_at":"2026-07-05T09:35:20.580605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:20.580605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mohan Kankanhalli, Yangyang Guo","submitted_at":"2024-11-14T01:53:17Z","abstract_excerpt":"While contrastive pre-training is widely employed, its data efficiency problem has remained relatively under-explored thus far. Existing methods often rely on static coreset selection algorithms to pre-identify important data for training. However, this static nature renders them unable to dynamically track the data usefulness throughout pre-training, leading to subpar pre-trained models. To address this challenge, our paper introduces a novel dynamic bootstrapping dataset pruning method. It involves pruning data preparation followed by dataset mutation operations, both of which undergo iterat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09126","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/2411.09126/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":"2411.09126","created_at":"2026-07-05T09:35:20.580667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09126v1","created_at":"2026-07-05T09:35:20.580667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09126","created_at":"2026-07-05T09:35:20.580667+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHZKSEMV7BQ6","created_at":"2026-07-05T09:35:20.580667+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHZKSEMV7BQ6VNCV","created_at":"2026-07-05T09:35:20.580667+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHZKSEMV","created_at":"2026-07-05T09:35:20.580667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12998","citing_title":"Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU","json":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU.json","graph_json":"https://pith.science/api/pith-number/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/graph.json","events_json":"https://pith.science/api/pith-number/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/events.json","paper":"https://pith.science/paper/XHZKSEMV"},"agent_actions":{"view_html":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU","download_json":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU.json","view_paper":"https://pith.science/paper/XHZKSEMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09126&json=true","fetch_graph":"https://pith.science/api/pith-number/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/graph.json","fetch_events":"https://pith.science/api/pith-number/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/action/storage_attestation","attest_author":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/action/author_attestation","sign_citation":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/action/citation_signature","submit_replication":"https://pith.science/pith/XHZKSEMV7BQ6VNCVGOQ5EWFDGU/action/replication_record"}},"created_at":"2026-07-05T09:35:20.580667+00:00","updated_at":"2026-07-05T09:35:20.580667+00:00"}