{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RZKPQ6Q3VBCODOTRWSBHO6QHUF","short_pith_number":"pith:RZKPQ6Q3","canonical_record":{"source":{"id":"2605.14579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:49:36Z","cross_cats_sorted":[],"title_canon_sha256":"aa5e65bbe7efe588f59f9e99497a2ee1bbaf9becd59962d8b79082f5350b1d8a","abstract_canon_sha256":"e0dd9f3c99fd87044bb82bf81627e519e88e82a2db19dc4dbfda9e5314c392ae"},"schema_version":"1.0"},"canonical_sha256":"8e54f87a1ba844e1ba71b482777a07a15196041b5dd0d815ab4d9faf20dc0864","source":{"kind":"arxiv","id":"2605.14579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14579","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14579v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14579","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"RZKPQ6Q3VBCO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RZKPQ6Q3VBCODOTR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RZKPQ6Q3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RZKPQ6Q3VBCODOTRWSBHO6QHUF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:49:36Z","cross_cats_sorted":[],"title_canon_sha256":"aa5e65bbe7efe588f59f9e99497a2ee1bbaf9becd59962d8b79082f5350b1d8a","abstract_canon_sha256":"e0dd9f3c99fd87044bb82bf81627e519e88e82a2db19dc4dbfda9e5314c392ae"},"schema_version":"1.0"},"canonical_sha256":"8e54f87a1ba844e1ba71b482777a07a15196041b5dd0d815ab4d9faf20dc0864","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:05.386080Z","signature_b64":"CkycvcgUKBNLc/eJ72UIypgPbMVVE5P1aFElG+TIfmhrHVfeyGq/fgAAsYBZzAWkc1keTo+Pa5gZBq8wsJakCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e54f87a1ba844e1ba71b482777a07a15196041b5dd0d815ab4d9faf20dc0864","last_reissued_at":"2026-05-17T23:39:05.385486Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:05.385486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14579","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IRsJS3rA+MC7YMQJKfsIPGUzr3hJnKZ5psJtjTlnNYA/R677wnp/+Z1oW7akDrm1qHht/ttjDbiPKICuEFwRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:26:37.269595Z"},"content_sha256":"9fb5ca02e25439ebc08f89f44f9d5d100ba06adb09234a2893a8a6ff0fb30097","schema_version":"1.0","event_id":"sha256:9fb5ca02e25439ebc08f89f44f9d5d100ba06adb09234a2893a8a6ff0fb30097"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RZKPQ6Q3VBCODOTRWSBHO6QHUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A dispersive loss treating batch representations as negatives produces boundary-aware embeddings that improve fine-grained medical image segmentation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guowei Zou, Haitao Wang, Hejun Wu, Zhiquan Chen","submitted_at":"2026-05-14T08:49:36Z","abstract_excerpt":"Accurate medical image segmentation is fundamental to precision medicine, yet robust delineation remains challenging under heterogeneous appearances, ambiguous boundaries, and large anatomical variability. Similar intensity and texture patterns between targets and surrounding tissues often lead to blurred activations and unreliable separation. We attribute these failures to representation collapse during encoding and insufficient fine grained multi scale decoding. To address these issues, we propose Med DisSeg, a dispersion driven medical image segmentation framework that jointly improves repr"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The Dispersive Loss enlarges inter-sample margins by treating in-batch hidden representations as negative pairs, producing well dispersed and boundary aware embeddings with negligible overhead.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That treating in-batch representations as negative pairs will consistently enlarge margins in a way that improves anatomical boundary delineation rather than simply increasing feature variance without semantic benefit.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A dispersive loss treating batch representations as negatives produces boundary-aware embeddings that improve fine-grained medical image segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"99b0a972e04b168fba3c37281f2250b4e1b81a9bd7e36f80fa03a9481ff9fe5d"},"source":{"id":"2605.14579","kind":"arxiv","version":1},"verdict":{"id":"810572ca-56ee-4eca-8e28-e7db66e8e533","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:45:03.754397Z","strongest_claim":"The Dispersive Loss enlarges inter-sample margins by treating in-batch hidden representations as negative pairs, producing well dispersed and boundary aware embeddings with negligible overhead.","one_line_summary":"Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That treating in-batch representations as negative pairs will consistently enlarge margins in a way that improves anatomical boundary delineation rather than simply increasing feature variance without semantic benefit.","pith_extraction_headline":"A dispersive loss treating batch representations as negatives produces boundary-aware embeddings that improve fine-grained medical image segmentation."},"references":{"count":18,"sample":[{"doi":"","year":2020,"title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","work_id":"ffa2ac60-2755-4390-9f66-07815aa6cb27","ref_index":1,"cited_arxiv_id":"2102.04306","is_internal_anchor":true},{"doi":"10.1016/j.eswa","year":2023,"title":"Expert Systems with Applications 238:122347","work_id":"9c9cb038-132a-4e28-a6f4-d9d10885170d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic)","work_id":"a1680554-54cc-449f-aa92-0acb940cad0a","ref_index":3,"cited_arxiv_id":"1902.03368","is_internal_anchor":true},{"doi":"","year":2019,"title":"Cpfnet: Context pyramid and feature fusion network for medical image segmentation. Neurocomputing 376, 222–235. Gu,Z.,etal.,2019. Ce-net:Contextencodernetworkfor2dmedicalimage segmentation. IEEE Trans","work_id":"af195e66-9430-446c-bb8c-464f9fc16f5b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Skin lesion analysis toward melanoma detection: A challenge at the isic 2016, in: IEEE International Symposium on Biomedical Imaging (ISBI) Challenge, pp. 1–10. Hatamizadeh, A., Tang, Y., Nath, V., Ya","work_id":"0127026d-83cf-4f14-95bd-a83cc7da58f5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"8c42d5b7cacbc53ac01f965ce352e4126716b0cf0256f3381c8fce2922f5f6cd","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3e17c869d7732187e465137dca4426c02fac824c1916681e12ab4a47ae74b0d5"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"810572ca-56ee-4eca-8e28-e7db66e8e533"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bxlJG/BBNIpndooBhgQv7jrHk3t0IZLbLMfOUZQfTZaE3woGHr8rcneh31dI+bc3B1HdiyzbsFR1tEGk2sU1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:26:37.270803Z"},"content_sha256":"da2e9b3b9803b1cbb7cf0d3d9dd88b4e551a65716ba8dd7bc724221d2af665b0","schema_version":"1.0","event_id":"sha256:da2e9b3b9803b1cbb7cf0d3d9dd88b4e551a65716ba8dd7bc724221d2af665b0"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:RZKPQ6Q3VBCODOTRWSBHO6QHUF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.eswa.2023.122567.Codella) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Combining contrastive learning and shape awareness for semi-supervised medical image segmentation. Expert Systems with Applications 242, 122567. doi:10.1016/j.eswa. 2023.122567. Codella, N., et al.,","arxiv_id":"2605.14579","detector":"doi_compliance","evidence":{"ref_index":2,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Combining contrastive learning and shape awareness for semi-supervised medical image segmentation. Expert Systems with Applications 242, 122567. doi:10.1016/j.eswa. 2023.122567. Codella, N., et al.,","reconstructed_doi":"10.1016/j.eswa.2023.122567.Codella"},"severity":"advisory","ref_index":2,"audited_at":"2026-05-19T05:29:10.933926Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.eswa.2023.122567.Codella","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"f549d59d5fb949d428b8458694b09c4ce35891c9be562bf1df4b5f40e96d406e","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":20,"payload_sha256":"46ab6ea2d427ff866001b16ab24670683b1270d09cd90d37bf58ca170f3d053f","signature_b64":"kvKEXOCeYcvAIZ3ZZ6P3JzgBTCMZn8SpQFdnqKSX3NgMDYHvQxgBYVdEV1pBwtVFbXsavBmItSdESmXMMyuJAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T05:31:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLGACHW2lYcMoMxUzq2iVlsAzzmDjt3cfEXdBJg6VebGAmUCHlrZYjW3HGLiwEtFSizVQE/y778f2CEGIz82Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:26:37.272478Z"},"content_sha256":"96170b03a0c9b69c58689afd9145fa76abf58e8ba772b92166c8b1847b55032b","schema_version":"1.0","event_id":"sha256:96170b03a0c9b69c58689afd9145fa76abf58e8ba772b92166c8b1847b55032b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:RZKPQ6Q3VBCODOTRWSBHO6QHUF","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/j.eswa.2023.121574.Liu) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"arXiv preprint arXiv:2511.16719 URL:https://arxiv.org/abs/2511.16719. Lei,M.,Wu,H.,Lv,X.,Wang,X.,2025.Condseg:Ageneralmedicalimage segmentation framework via contrast-driven feature enhancement, in: ProceedingsoftheAAAIConferenceonArtificia","arxiv_id":"2605.14579","detector":"doi_compliance","evidence":{"ref_index":8,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"arXiv preprint arXiv:2511.16719 URL:https://arxiv.org/abs/2511.16719. Lei,M.,Wu,H.,Lv,X.,Wang,X.,2025.Condseg:Ageneralmedicalimage segmentation framework via contrast-driven feature enhancement, in: ProceedingsoftheAAAIConferenceonArtificia","reconstructed_doi":"10.1016/j.eswa.2023.121574.Liu"},"severity":"advisory","ref_index":8,"audited_at":"2026-05-19T05:29:10.933926Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.eswa.2023.121574.Liu","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"7eb49164562563d411c9ef3c6c87d83220f6e55611de3f97f4ead3326559cd36","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":19,"payload_sha256":"fac5b699682be47834a7fa6532fccf64168b5451b5ea4fb15da9b9b4797181e7","signature_b64":"OxlSt5mKg1L/S0SAIfxb85G/D15WRsqMkExAyNIO8ikbx0S+ZjeS43ruV+ZU8Cx1O79Im1nvRbiII6+HxrqdAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T05:31:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ad3by73rLvqqRJMROJHXtmHeTphFTXRNn3UsGXk+wZq0Z3K0EyDjcrQ5vxMdRBJ9K+tlje2yFSnqgsULIOvuAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T21:26:37.273058Z"},"content_sha256":"1168e3d5ec2479a6e4dce1ad894dc474e70ef453983d2748e555af722845650e","schema_version":"1.0","event_id":"sha256:1168e3d5ec2479a6e4dce1ad894dc474e70ef453983d2748e555af722845650e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF/bundle.json","state_url":"https://pith.science/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T21:26:37Z","links":{"resolver":"https://pith.science/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF","bundle":"https://pith.science/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF/bundle.json","state":"https://pith.science/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZKPQ6Q3VBCODOTRWSBHO6QHUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RZKPQ6Q3VBCODOTRWSBHO6QHUF","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e0dd9f3c99fd87044bb82bf81627e519e88e82a2db19dc4dbfda9e5314c392ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:49:36Z","title_canon_sha256":"aa5e65bbe7efe588f59f9e99497a2ee1bbaf9becd59962d8b79082f5350b1d8a"},"schema_version":"1.0","source":{"id":"2605.14579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14579","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14579v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14579","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"RZKPQ6Q3VBCO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"RZKPQ6Q3VBCODOTR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"RZKPQ6Q3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:da2e9b3b9803b1cbb7cf0d3d9dd88b4e551a65716ba8dd7bc724221d2af665b0","target":"graph","created_at":"2026-05-17T23:39:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The Dispersive Loss enlarges inter-sample margins by treating in-batch hidden representations as negative pairs, producing well dispersed and boundary aware embeddings with negligible overhead."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That treating in-batch representations as negative pairs will consistently enlarge margins in a way that improves anatomical boundary delineation rather than simply increasing feature variance without semantic benefit."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A dispersive loss treating batch representations as negatives produces boundary-aware embeddings that improve fine-grained medical image segmentation."}],"snapshot_sha256":"99b0a972e04b168fba3c37281f2250b4e1b81a9bd7e36f80fa03a9481ff9fe5d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3e17c869d7732187e465137dca4426c02fac824c1916681e12ab4a47ae74b0d5"},"paper":{"abstract_excerpt":"Accurate medical image segmentation is fundamental to precision medicine, yet robust delineation remains challenging under heterogeneous appearances, ambiguous boundaries, and large anatomical variability. Similar intensity and texture patterns between targets and surrounding tissues often lead to blurred activations and unreliable separation. We attribute these failures to representation collapse during encoding and insufficient fine grained multi scale decoding. To address these issues, we propose Med DisSeg, a dispersion driven medical image segmentation framework that jointly improves repr","authors_text":"Guowei Zou, Haitao Wang, Hejun Wu, Zhiquan Chen","cross_cats":[],"headline":"A dispersive loss treating batch representations as negatives produces boundary-aware embeddings that improve fine-grained medical image segmentation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:49:36Z","title":"Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation"},"references":{"count":18,"internal_anchors":4,"resolved_work":18,"sample":[{"cited_arxiv_id":"2102.04306","doi":"","is_internal_anchor":true,"ref_index":1,"title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","work_id":"ffa2ac60-2755-4390-9f66-07815aa6cb27","year":2020},{"cited_arxiv_id":"","doi":"10.1016/j.eswa","is_internal_anchor":false,"ref_index":2,"title":"Expert Systems with Applications 238:122347","work_id":"9c9cb038-132a-4e28-a6f4-d9d10885170d","year":2023},{"cited_arxiv_id":"1902.03368","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic)","work_id":"a1680554-54cc-449f-aa92-0acb940cad0a","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Cpfnet: Context pyramid and feature fusion network for medical image segmentation. Neurocomputing 376, 222–235. Gu,Z.,etal.,2019. Ce-net:Contextencodernetworkfor2dmedicalimage segmentation. IEEE Trans","work_id":"af195e66-9430-446c-bb8c-464f9fc16f5b","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Skin lesion analysis toward melanoma detection: A challenge at the isic 2016, in: IEEE International Symposium on Biomedical Imaging (ISBI) Challenge, pp. 1–10. Hatamizadeh, A., Tang, Y., Nath, V., Ya","work_id":"0127026d-83cf-4f14-95bd-a83cc7da58f5","year":2016}],"snapshot_sha256":"8c42d5b7cacbc53ac01f965ce352e4126716b0cf0256f3381c8fce2922f5f6cd"},"source":{"id":"2605.14579","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:45:03.754397Z","id":"810572ca-56ee-4eca-8e28-e7db66e8e533","model_set":{"reader":"grok-4.3"},"one_line_summary":"Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A dispersive loss treating batch representations as negatives produces boundary-aware embeddings that improve fine-grained medical image segmentation.","strongest_claim":"The Dispersive Loss enlarges inter-sample margins by treating in-batch hidden representations as negative pairs, producing well dispersed and boundary aware embeddings with negligible overhead.","weakest_assumption":"That treating in-batch representations as negative pairs will consistently enlarge margins in a way that improves anatomical boundary delineation rather than simply increasing feature variance without semantic benefit."}},"verdict_id":"810572ca-56ee-4eca-8e28-e7db66e8e533"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9fb5ca02e25439ebc08f89f44f9d5d100ba06adb09234a2893a8a6ff0fb30097","target":"record","created_at":"2026-05-17T23:39:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e0dd9f3c99fd87044bb82bf81627e519e88e82a2db19dc4dbfda9e5314c392ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:49:36Z","title_canon_sha256":"aa5e65bbe7efe588f59f9e99497a2ee1bbaf9becd59962d8b79082f5350b1d8a"},"schema_version":"1.0","source":{"id":"2605.14579","kind":"arxiv","version":1}},"canonical_sha256":"8e54f87a1ba844e1ba71b482777a07a15196041b5dd0d815ab4d9faf20dc0864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e54f87a1ba844e1ba71b482777a07a15196041b5dd0d815ab4d9faf20dc0864","first_computed_at":"2026-05-17T23:39:05.385486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:05.385486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CkycvcgUKBNLc/eJ72UIypgPbMVVE5P1aFElG+TIfmhrHVfeyGq/fgAAsYBZzAWkc1keTo+Pa5gZBq8wsJakCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:05.386080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14579","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:1168e3d5ec2479a6e4dce1ad894dc474e70ef453983d2748e555af722845650e","sha256:96170b03a0c9b69c58689afd9145fa76abf58e8ba772b92166c8b1847b55032b"]}],"invalid_events":[],"applied_event_ids":["sha256:9fb5ca02e25439ebc08f89f44f9d5d100ba06adb09234a2893a8a6ff0fb30097","sha256:da2e9b3b9803b1cbb7cf0d3d9dd88b4e551a65716ba8dd7bc724221d2af665b0"],"state_sha256":"90f02d5470c3ec970bc9d9c55481c229056133ae1fa10ea2abb1629e45cef7a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/f6VXMQ2q7sVtSPaVNz+Per3Xx/yRNp2dLO91N5tVHFVmLTqF7xGr0V+2kOm0zqIyE2cSI5Xswke3SawcTXCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T21:26:37.278232Z","bundle_sha256":"2d5d121ba3898513e1f030b664d48a398e2663a8c702dce6793b734029c20656"}}