{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B7RJLJ6FXNKZHR3LJJ47LQEBIP","short_pith_number":"pith:B7RJLJ6F","schema_version":"1.0","canonical_sha256":"0fe295a7c5bb5593c76b4a79f5c08143f993cecf1f08e979bb421bf899c768ee","source":{"kind":"arxiv","id":"2406.00672","version":1},"attestation_state":"computed","paper":{"title":"Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lianghui Zhu, Qiehe Sun, Renao Yan, Shanshan Shi, Tian Guan, Xuenian Wang, Yonghong He","submitted_at":"2024-06-02T08:53:45Z","abstract_excerpt":"In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation reveals that discriminative embeddings are crucial for aggregation to the final prediction. Among all feature updating strategies, task-oriented ones can capture characteristics specifically for certain tasks. However, they can be prone to overfitting and contaminated by samples assigned with noisy labels. To address this issue, we propose a heuristic clustering-driven feature fine-"},"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":"2406.00672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-02T08:53:45Z","cross_cats_sorted":[],"title_canon_sha256":"0b2f94048300e8dc2927fdaca43507bc36afb1dff357beab66a31c11be967d33","abstract_canon_sha256":"094adcf5fcd54a6730bbaacadd639d5601ba93d1b7ecd1d98b951b5b0c41adbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:28.859042Z","signature_b64":"XixgkYhuduvBctOWVFcXTuB8AfWd4yq8V7n2/echrg2Og/6asVTdYTkK92x4thXDyh12+OUlbndWVv/4sIWaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fe295a7c5bb5593c76b4a79f5c08143f993cecf1f08e979bb421bf899c768ee","last_reissued_at":"2026-07-05T08:26:28.858556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:28.858556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-oriented Embedding Counts: Heuristic Clustering-driven Feature Fine-tuning for Whole Slide Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lianghui Zhu, Qiehe Sun, Renao Yan, Shanshan Shi, Tian Guan, Xuenian Wang, Yonghong He","submitted_at":"2024-06-02T08:53:45Z","abstract_excerpt":"In the field of whole slide image (WSI) classification, multiple instance learning (MIL) serves as a promising approach, commonly decoupled into feature extraction and aggregation. In this paradigm, our observation reveals that discriminative embeddings are crucial for aggregation to the final prediction. Among all feature updating strategies, task-oriented ones can capture characteristics specifically for certain tasks. However, they can be prone to overfitting and contaminated by samples assigned with noisy labels. To address this issue, we propose a heuristic clustering-driven feature fine-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00672","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/2406.00672/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":"2406.00672","created_at":"2026-07-05T08:26:28.858611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00672v1","created_at":"2026-07-05T08:26:28.858611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00672","created_at":"2026-07-05T08:26:28.858611+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7RJLJ6FXNKZ","created_at":"2026-07-05T08:26:28.858611+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7RJLJ6FXNKZHR3L","created_at":"2026-07-05T08:26:28.858611+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7RJLJ6F","created_at":"2026-07-05T08:26:28.858611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14176","citing_title":"One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP","json":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP.json","graph_json":"https://pith.science/api/pith-number/B7RJLJ6FXNKZHR3LJJ47LQEBIP/graph.json","events_json":"https://pith.science/api/pith-number/B7RJLJ6FXNKZHR3LJJ47LQEBIP/events.json","paper":"https://pith.science/paper/B7RJLJ6F"},"agent_actions":{"view_html":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP","download_json":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP.json","view_paper":"https://pith.science/paper/B7RJLJ6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00672&json=true","fetch_graph":"https://pith.science/api/pith-number/B7RJLJ6FXNKZHR3LJJ47LQEBIP/graph.json","fetch_events":"https://pith.science/api/pith-number/B7RJLJ6FXNKZHR3LJJ47LQEBIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP/action/storage_attestation","attest_author":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP/action/author_attestation","sign_citation":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP/action/citation_signature","submit_replication":"https://pith.science/pith/B7RJLJ6FXNKZHR3LJJ47LQEBIP/action/replication_record"}},"created_at":"2026-07-05T08:26:28.858611+00:00","updated_at":"2026-07-05T08:26:28.858611+00:00"}