{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VQTMFE5FVMJANJ5YFIH6VP5HGY","short_pith_number":"pith:VQTMFE5F","schema_version":"1.0","canonical_sha256":"ac26c293a5ab1206a7b82a0feabfa7360f36ea1420beaa051d78b15c2a15a6df","source":{"kind":"arxiv","id":"2308.01189","version":1},"attestation_state":"computed","paper":{"title":"Data-Centric Diet: Effective Multi-center Dataset Pruning for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mingjin Chen, Yongkang He, Yongyi Lu, Zhijing Yang","submitted_at":"2023-08-02T14:53:43Z","abstract_excerpt":"This paper seeks to address the dense labeling problems where a significant fraction of the dataset can be pruned without sacrificing much accuracy. We observe that, on standard medical image segmentation benchmarks, the loss gradient norm-based metrics of individual training examples applied in image classification fail to identify the important samples. To address this issue, we propose a data pruning method by taking into consideration the training dynamics on target regions using Dynamic Average Dice (DAD) score. To the best of our knowledge, we are among the first to address the data impo"},"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":"2308.01189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-02T14:53:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2828fb2b5182708e79ad961034cdf57036d4f476fb6dfa57e69f44111803caa7","abstract_canon_sha256":"d886740ce3754d5a580a25783abce6f561f7ebd1b362aa6d28809573d2f92c34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:06.584297Z","signature_b64":"M8NmOgQZl53DjDJ4gfE5Qs/PkyFNv8kYLaeNlFdIQ5xVkcxAfTBjc8PnWvuxEwEXEsPpOsRhMeuun0oTuzkPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac26c293a5ab1206a7b82a0feabfa7360f36ea1420beaa051d78b15c2a15a6df","last_reissued_at":"2026-07-05T06:37:06.583876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:06.583876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Centric Diet: Effective Multi-center Dataset Pruning for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mingjin Chen, Yongkang He, Yongyi Lu, Zhijing Yang","submitted_at":"2023-08-02T14:53:43Z","abstract_excerpt":"This paper seeks to address the dense labeling problems where a significant fraction of the dataset can be pruned without sacrificing much accuracy. We observe that, on standard medical image segmentation benchmarks, the loss gradient norm-based metrics of individual training examples applied in image classification fail to identify the important samples. To address this issue, we propose a data pruning method by taking into consideration the training dynamics on target regions using Dynamic Average Dice (DAD) score. To the best of our knowledge, we are among the first to address the data impo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01189","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/2308.01189/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":"2308.01189","created_at":"2026-07-05T06:37:06.583932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01189v1","created_at":"2026-07-05T06:37:06.583932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01189","created_at":"2026-07-05T06:37:06.583932+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQTMFE5FVMJA","created_at":"2026-07-05T06:37:06.583932+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQTMFE5FVMJANJ5Y","created_at":"2026-07-05T06:37:06.583932+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQTMFE5F","created_at":"2026-07-05T06:37:06.583932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21883","citing_title":"GRASP-PsONet: Gradient-based Removal of Spurious Patterns for PsOriasis Severity Classification","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY","json":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY.json","graph_json":"https://pith.science/api/pith-number/VQTMFE5FVMJANJ5YFIH6VP5HGY/graph.json","events_json":"https://pith.science/api/pith-number/VQTMFE5FVMJANJ5YFIH6VP5HGY/events.json","paper":"https://pith.science/paper/VQTMFE5F"},"agent_actions":{"view_html":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY","download_json":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY.json","view_paper":"https://pith.science/paper/VQTMFE5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01189&json=true","fetch_graph":"https://pith.science/api/pith-number/VQTMFE5FVMJANJ5YFIH6VP5HGY/graph.json","fetch_events":"https://pith.science/api/pith-number/VQTMFE5FVMJANJ5YFIH6VP5HGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY/action/storage_attestation","attest_author":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY/action/author_attestation","sign_citation":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY/action/citation_signature","submit_replication":"https://pith.science/pith/VQTMFE5FVMJANJ5YFIH6VP5HGY/action/replication_record"}},"created_at":"2026-07-05T06:37:06.583932+00:00","updated_at":"2026-07-05T06:37:06.583932+00:00"}