{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:POCTVI3M6WOHKXBU4ZGUNNR6XD","short_pith_number":"pith:POCTVI3M","schema_version":"1.0","canonical_sha256":"7b853aa36cf59c755c34e64d46b63eb8ca6eef8d548a2fc6c31c20c9e098d1bc","source":{"kind":"arxiv","id":"2310.07248","version":4},"attestation_state":"computed","paper":{"title":"IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongkuan Shi, Li He, Man He, Mei Liu, Qiang Hu, Qiang Li, Wenxuan Dai, Xin Yang, Yinjiao Tian, Zhiwei Wang","submitted_at":"2023-10-11T07:25:50Z","abstract_excerpt":"Box-supervised polyp segmentation attracts increasing attention for its cost-effective potential. Existing solutions often rely on learning-free methods or pretrained models to laboriously generate pseudo masks, triggering Dice constraint subsequently. In this paper, we found that a model guided by the simplest box-filled masks can accurately predict polyp locations/sizes, but suffers from shape collapsing. In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA. The"},"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":"2310.07248","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T07:25:50Z","cross_cats_sorted":[],"title_canon_sha256":"3e486391fef221d3e0019330673f2da4e552728b4b937baaa88222c7786a92b6","abstract_canon_sha256":"a10ac775152d21c1b506fd8e45c4ce5049c237edfe630a0e58502dad89cd3995"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:39.711179Z","signature_b64":"kVP2+psWPuegtjRHuTUFdAqPQEenK0EynuxhuwioPN+UjdDCgHP2nleosWh7/Ni1fmctFff3uIm4rTEYwts8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b853aa36cf59c755c34e64d46b63eb8ca6eef8d548a2fc6c31c20c9e098d1bc","last_reissued_at":"2026-07-05T09:06:39.710631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:39.710631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IBoxCLA: Towards Robust Box-supervised Segmentation of Polyp via Improved Box-dice and Contrastive Latent-anchors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongkuan Shi, Li He, Man He, Mei Liu, Qiang Hu, Qiang Li, Wenxuan Dai, Xin Yang, Yinjiao Tian, Zhiwei Wang","submitted_at":"2023-10-11T07:25:50Z","abstract_excerpt":"Box-supervised polyp segmentation attracts increasing attention for its cost-effective potential. Existing solutions often rely on learning-free methods or pretrained models to laboriously generate pseudo masks, triggering Dice constraint subsequently. In this paper, we found that a model guided by the simplest box-filled masks can accurately predict polyp locations/sizes, but suffers from shape collapsing. In response, we propose two innovative learning fashions, Improved Box-dice (IBox) and Contrastive Latent-Anchors (CLA), and combine them to train a robust box-supervised model IBoxCLA. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07248","kind":"arxiv","version":4},"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/2310.07248/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":"2310.07248","created_at":"2026-07-05T09:06:39.710689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07248v4","created_at":"2026-07-05T09:06:39.710689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07248","created_at":"2026-07-05T09:06:39.710689+00:00"},{"alias_kind":"pith_short_12","alias_value":"POCTVI3M6WOH","created_at":"2026-07-05T09:06:39.710689+00:00"},{"alias_kind":"pith_short_16","alias_value":"POCTVI3M6WOHKXBU","created_at":"2026-07-05T09:06:39.710689+00:00"},{"alias_kind":"pith_short_8","alias_value":"POCTVI3M","created_at":"2026-07-05T09:06:39.710689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16503","citing_title":"First-frame Supervised Video Polyp Segmentation via Propagative and Semantic Dual-teacher Network","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD","json":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD.json","graph_json":"https://pith.science/api/pith-number/POCTVI3M6WOHKXBU4ZGUNNR6XD/graph.json","events_json":"https://pith.science/api/pith-number/POCTVI3M6WOHKXBU4ZGUNNR6XD/events.json","paper":"https://pith.science/paper/POCTVI3M"},"agent_actions":{"view_html":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD","download_json":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD.json","view_paper":"https://pith.science/paper/POCTVI3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07248&json=true","fetch_graph":"https://pith.science/api/pith-number/POCTVI3M6WOHKXBU4ZGUNNR6XD/graph.json","fetch_events":"https://pith.science/api/pith-number/POCTVI3M6WOHKXBU4ZGUNNR6XD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD/action/storage_attestation","attest_author":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD/action/author_attestation","sign_citation":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD/action/citation_signature","submit_replication":"https://pith.science/pith/POCTVI3M6WOHKXBU4ZGUNNR6XD/action/replication_record"}},"created_at":"2026-07-05T09:06:39.710689+00:00","updated_at":"2026-07-05T09:06:39.710689+00:00"}