{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KSFTAYDZL7PGBQUAECKY2JTT56","short_pith_number":"pith:KSFTAYDZ","schema_version":"1.0","canonical_sha256":"548b3060795fde60c28020958d2673ef9fb5fb726a510c1360f37d0e70d5d6c1","source":{"kind":"arxiv","id":"2306.14113","version":1},"attestation_state":"computed","paper":{"title":"Exploring Data Redundancy in Real-world Image Classification through Data Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shaoting Zhang, Xiaosong Wang, Zhenyu Tang","submitted_at":"2023-06-25T03:31:05Z","abstract_excerpt":"Deep learning models often require large amounts of data for training, leading to increased costs. It is particularly challenging in medical imaging, i.e., gathering distributed data for centralized training, and meanwhile, obtaining quality labels remains a tedious job. Many methods have been proposed to address this issue in various training paradigms, e.g., continual learning, active learning, and federated learning, which indeed demonstrate certain forms of the data valuation process. However, existing methods are either overly intuitive or limited to common clean/toy datasets in the exper"},"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":"2306.14113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-25T03:31:05Z","cross_cats_sorted":[],"title_canon_sha256":"8eec5cdf040b805ee6c5850895fd58c7ef18760aae6e8369ef6f33f4b25e6cf2","abstract_canon_sha256":"c0496c200f0cc2bd98032506d64c705dfaff5365bb908305dd990f8e60f59379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:20.326047Z","signature_b64":"bjmjWOgoE4r85Uo44GF1acWlpVSee8t1uk8hYaSa9ph+ARX2wMqc3fUBX9q6FX52148XZn7sBP/rFHC+cLDNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548b3060795fde60c28020958d2673ef9fb5fb726a510c1360f37d0e70d5d6c1","last_reissued_at":"2026-07-05T06:24:20.325462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:20.325462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Data Redundancy in Real-world Image Classification through Data Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shaoting Zhang, Xiaosong Wang, Zhenyu Tang","submitted_at":"2023-06-25T03:31:05Z","abstract_excerpt":"Deep learning models often require large amounts of data for training, leading to increased costs. It is particularly challenging in medical imaging, i.e., gathering distributed data for centralized training, and meanwhile, obtaining quality labels remains a tedious job. Many methods have been proposed to address this issue in various training paradigms, e.g., continual learning, active learning, and federated learning, which indeed demonstrate certain forms of the data valuation process. However, existing methods are either overly intuitive or limited to common clean/toy datasets in the exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14113","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/2306.14113/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":"2306.14113","created_at":"2026-07-05T06:24:20.325532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14113v1","created_at":"2026-07-05T06:24:20.325532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14113","created_at":"2026-07-05T06:24:20.325532+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSFTAYDZL7PG","created_at":"2026-07-05T06:24:20.325532+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSFTAYDZL7PGBQUA","created_at":"2026-07-05T06:24:20.325532+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSFTAYDZ","created_at":"2026-07-05T06:24:20.325532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09010","citing_title":"Effective Data Pruning through Score Extrapolation","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56","json":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56.json","graph_json":"https://pith.science/api/pith-number/KSFTAYDZL7PGBQUAECKY2JTT56/graph.json","events_json":"https://pith.science/api/pith-number/KSFTAYDZL7PGBQUAECKY2JTT56/events.json","paper":"https://pith.science/paper/KSFTAYDZ"},"agent_actions":{"view_html":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56","download_json":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56.json","view_paper":"https://pith.science/paper/KSFTAYDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14113&json=true","fetch_graph":"https://pith.science/api/pith-number/KSFTAYDZL7PGBQUAECKY2JTT56/graph.json","fetch_events":"https://pith.science/api/pith-number/KSFTAYDZL7PGBQUAECKY2JTT56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56/action/storage_attestation","attest_author":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56/action/author_attestation","sign_citation":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56/action/citation_signature","submit_replication":"https://pith.science/pith/KSFTAYDZL7PGBQUAECKY2JTT56/action/replication_record"}},"created_at":"2026-07-05T06:24:20.325532+00:00","updated_at":"2026-07-05T06:24:20.325532+00:00"}