{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NGC5PE4YZ6YU2C5FJA2EPF56CK","short_pith_number":"pith:NGC5PE4Y","schema_version":"1.0","canonical_sha256":"6985d79398cfb14d0ba548344797be1292cee04ed7d946eab5dd49d44aea7916","source":{"kind":"arxiv","id":"2502.08347","version":1},"attestation_state":"computed","paper":{"title":"Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxu Wu, Fenghe Tang, Qingsong Yao, S. Kevin Zhou, Wenxin Ma, Zihang Jiang","submitted_at":"2025-02-12T12:14:02Z","abstract_excerpt":"Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution, providing both computational efficiency and model generalization for various downstream tasks. However, current ViT-based MIM pre-training frameworks predominantly emphasize local aggregation representations in output layers and fail to exploit the rich representations across different ViT layers that better capture fine-grained semantic information needed for more "},"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":"2502.08347","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T12:14:02Z","cross_cats_sorted":[],"title_canon_sha256":"052d3a567add55acbe348e2fb38b2c709dc17fd939a68884fdacb23b243c270f","abstract_canon_sha256":"508d2aa8407ebde9889b7fbc352a0899eecdfc96d78cc3a304cd20a65c9dcabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:21.548262Z","signature_b64":"ocWOfzAjDe0mVuMuUCFQqqxNbAEse6gtOLnHtHbM/XHnju64LvBLrJkITHlCQVQxKLKFtktJM0ZQAFQfWNybDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6985d79398cfb14d0ba548344797be1292cee04ed7d946eab5dd49d44aea7916","last_reissued_at":"2026-07-05T10:13:21.547857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:21.547857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxu Wu, Fenghe Tang, Qingsong Yao, S. Kevin Zhou, Wenxin Ma, Zihang Jiang","submitted_at":"2025-02-12T12:14:02Z","abstract_excerpt":"Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution, providing both computational efficiency and model generalization for various downstream tasks. However, current ViT-based MIM pre-training frameworks predominantly emphasize local aggregation representations in output layers and fail to exploit the rich representations across different ViT layers that better capture fine-grained semantic information needed for more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08347","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/2502.08347/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":"2502.08347","created_at":"2026-07-05T10:13:21.547916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08347v1","created_at":"2026-07-05T10:13:21.547916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08347","created_at":"2026-07-05T10:13:21.547916+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGC5PE4YZ6YU","created_at":"2026-07-05T10:13:21.547916+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGC5PE4YZ6YU2C5F","created_at":"2026-07-05T10:13:21.547916+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGC5PE4Y","created_at":"2026-07-05T10:13:21.547916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08311","citing_title":"SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK","json":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK.json","graph_json":"https://pith.science/api/pith-number/NGC5PE4YZ6YU2C5FJA2EPF56CK/graph.json","events_json":"https://pith.science/api/pith-number/NGC5PE4YZ6YU2C5FJA2EPF56CK/events.json","paper":"https://pith.science/paper/NGC5PE4Y"},"agent_actions":{"view_html":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK","download_json":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK.json","view_paper":"https://pith.science/paper/NGC5PE4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08347&json=true","fetch_graph":"https://pith.science/api/pith-number/NGC5PE4YZ6YU2C5FJA2EPF56CK/graph.json","fetch_events":"https://pith.science/api/pith-number/NGC5PE4YZ6YU2C5FJA2EPF56CK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK/action/storage_attestation","attest_author":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK/action/author_attestation","sign_citation":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK/action/citation_signature","submit_replication":"https://pith.science/pith/NGC5PE4YZ6YU2C5FJA2EPF56CK/action/replication_record"}},"created_at":"2026-07-05T10:13:21.547916+00:00","updated_at":"2026-07-05T10:13:21.547916+00:00"}