{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IBO3S53MLIB2AOUSIKXE5OHYCS","short_pith_number":"pith:IBO3S53M","schema_version":"1.0","canonical_sha256":"405db9776c5a03a03a9242ae4eb8f81481259937ad85400838707f0398c6fa17","source":{"kind":"arxiv","id":"2605.00675","version":2},"attestation_state":"computed","paper":{"title":"DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Dynamic margins based on label frequency improve open-set recognition for rare medical conditions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnav Aditya, Nitin Kumar, Saurabh J. Shigwan, Vishal","submitted_at":"2026-05-01T13:57:41Z","abstract_excerpt":"Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to common conditions. This imbalance poses a dual challenge for Open-Set Recognition (OSR): models must maintain high classification accuracy on known classes while reliably rejecting unknown samples unseen during training in the clinical settings. While recently proposed Deep Simplex Classifier (DSC)~\\cite{cevikalp2024reaching} and UnCertainty-aware Deep Simplex Classifier (UCDSC)~\\cite{Aditya_2026_WACV} successfully leverage Neural Collapse to ensur"},"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":"2605.00675","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-01T13:57:41Z","cross_cats_sorted":[],"title_canon_sha256":"c78611ff4001e3c4433bb068fc3102edc101ffb30d1b239c0acf5f28997f8239","abstract_canon_sha256":"ecccc5fed1b698536c2b760f0db0fe5cd1570d9e38972ba040d4bcfe852c12c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:39.001099Z","signature_b64":"XejHf9zo/5phvHAH8zlRTTHO1xsVsfpOjkXeABl484WuQJaZtEYuaTKUkKZZAwnqDxM7ojGTsZX0aHslPgyQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405db9776c5a03a03a9242ae4eb8f81481259937ad85400838707f0398c6fa17","last_reissued_at":"2026-06-30T01:17:39.000249Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:39.000249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Dynamic margins based on label frequency improve open-set recognition for rare medical conditions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnav Aditya, Nitin Kumar, Saurabh J. Shigwan, Vishal","submitted_at":"2026-05-01T13:57:41Z","abstract_excerpt":"Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to common conditions. This imbalance poses a dual challenge for Open-Set Recognition (OSR): models must maintain high classification accuracy on known classes while reliably rejecting unknown samples unseen during training in the clinical settings. While recently proposed Deep Simplex Classifier (DSC)~\\cite{cevikalp2024reaching} and UnCertainty-aware Deep Simplex Classifier (UCDSC)~\\cite{Aditya_2026_WACV} successfully leverage Neural Collapse to ensur"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach automatically adapts class-specific margins based on label frequency, enforcing a higher penalty and tighter feature clustering for rare pathologies to counteract the effects of data imbalance. Extensive experiments ... demonstrate that our framework outperforms state-of-the-art methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a margin scaled solely by label frequency will produce tighter, more separable clusters for rare classes without introducing new overfitting to frequency statistics or harming performance on common classes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DMDSC adapts simplex-classifier margins dynamically according to label frequency to tighten clustering on rare medical classes and improve open-set rejection on imbalanced imaging datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dynamic margins based on label frequency improve open-set recognition for rare medical conditions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0ab769614aa036a4029b4bdc3f945d727c824f623bc69e107cdee4e29c0033d2"},"source":{"id":"2605.00675","kind":"arxiv","version":2},"verdict":{"id":"c7568e90-8db5-409f-a191-6423ab2473a2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T19:43:28.709654Z","strongest_claim":"Our approach automatically adapts class-specific margins based on label frequency, enforcing a higher penalty and tighter feature clustering for rare pathologies to counteract the effects of data imbalance. Extensive experiments ... demonstrate that our framework outperforms state-of-the-art methods.","one_line_summary":"DMDSC adapts simplex-classifier margins dynamically according to label frequency to tighten clustering on rare medical classes and improve open-set rejection on imbalanced imaging datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a margin scaled solely by label frequency will produce tighter, more separable clusters for rare classes without introducing new overfitting to frequency statistics or harming performance on common classes.","pith_extraction_headline":"Dynamic margins based on label frequency improve open-set recognition for rare medical conditions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00675/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T19:37:44.135220Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:56:14.663476Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fa9461bec7971e3f6b3e141a4304ea258d3a08dd13ab7c947fe48b08f3b91381"},"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":"2605.00675","created_at":"2026-06-30T01:17:39.000344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.00675v2","created_at":"2026-06-30T01:17:39.000344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00675","created_at":"2026-06-30T01:17:39.000344+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBO3S53MLIB2","created_at":"2026-06-30T01:17:39.000344+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBO3S53MLIB2AOUS","created_at":"2026-06-30T01:17:39.000344+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBO3S53M","created_at":"2026-06-30T01:17:39.000344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.01883","citing_title":"Beyond the Simplex: Balanced Prototype Geometry for Scorer-Agnostic Open-Set Recognition","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS","json":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS.json","graph_json":"https://pith.science/api/pith-number/IBO3S53MLIB2AOUSIKXE5OHYCS/graph.json","events_json":"https://pith.science/api/pith-number/IBO3S53MLIB2AOUSIKXE5OHYCS/events.json","paper":"https://pith.science/paper/IBO3S53M"},"agent_actions":{"view_html":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS","download_json":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS.json","view_paper":"https://pith.science/paper/IBO3S53M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.00675&json=true","fetch_graph":"https://pith.science/api/pith-number/IBO3S53MLIB2AOUSIKXE5OHYCS/graph.json","fetch_events":"https://pith.science/api/pith-number/IBO3S53MLIB2AOUSIKXE5OHYCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS/action/storage_attestation","attest_author":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS/action/author_attestation","sign_citation":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS/action/citation_signature","submit_replication":"https://pith.science/pith/IBO3S53MLIB2AOUSIKXE5OHYCS/action/replication_record"}},"created_at":"2026-06-30T01:17:39.000344+00:00","updated_at":"2026-06-30T01:17:39.000344+00:00"}