{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3D2ECFM4Z4BBAET2C5AZJ3QTPS","short_pith_number":"pith:3D2ECFM4","schema_version":"1.0","canonical_sha256":"d8f441159ccf0210127a174194ee137cbcaaf7f8be5a064774a6aedfcce4bf9b","source":{"kind":"arxiv","id":"2203.15202","version":2},"attestation_state":"computed","paper":{"title":"SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Liu, Tongliang Liu, Xiaoqing Guo, Yixuan Yuan","submitted_at":"2022-03-29T02:48:08Z","abstract_excerpt":"This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. In this paper, we propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT. By exploiting computational geometry analysis and properties of segmentation, we design three complementary regulariz"},"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":"2203.15202","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T02:48:08Z","cross_cats_sorted":[],"title_canon_sha256":"5a41c827350eb9e60be8a5df162293fd61e2725651e656e317a9426c694f1fe8","abstract_canon_sha256":"b3ad9b406a65e39286c0aa4cf364766109f5cabadc5eee532a78717e25a8e373"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:18.375985Z","signature_b64":"zr767a4ODaVBz/kcedObogyIA6m2iUUm9tt1BHfZGLXy2LJkBYb/E5fPo2+lFJ1lnZqvBgUgK7iwWTC4RwhNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8f441159ccf0210127a174194ee137cbcaaf7f8be5a064774a6aedfcce4bf9b","last_reissued_at":"2026-07-05T04:12:18.375415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:18.375415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Liu, Tongliang Liu, Xiaoqing Guo, Yixuan Yuan","submitted_at":"2022-03-29T02:48:08Z","abstract_excerpt":"This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. In this paper, we propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT. By exploiting computational geometry analysis and properties of segmentation, we design three complementary regulariz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15202","kind":"arxiv","version":2},"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/2203.15202/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":"2203.15202","created_at":"2026-07-05T04:12:18.375488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15202v2","created_at":"2026-07-05T04:12:18.375488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15202","created_at":"2026-07-05T04:12:18.375488+00:00"},{"alias_kind":"pith_short_12","alias_value":"3D2ECFM4Z4BB","created_at":"2026-07-05T04:12:18.375488+00:00"},{"alias_kind":"pith_short_16","alias_value":"3D2ECFM4Z4BBAET2","created_at":"2026-07-05T04:12:18.375488+00:00"},{"alias_kind":"pith_short_8","alias_value":"3D2ECFM4","created_at":"2026-07-05T04:12:18.375488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS","json":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS.json","graph_json":"https://pith.science/api/pith-number/3D2ECFM4Z4BBAET2C5AZJ3QTPS/graph.json","events_json":"https://pith.science/api/pith-number/3D2ECFM4Z4BBAET2C5AZJ3QTPS/events.json","paper":"https://pith.science/paper/3D2ECFM4"},"agent_actions":{"view_html":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS","download_json":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS.json","view_paper":"https://pith.science/paper/3D2ECFM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15202&json=true","fetch_graph":"https://pith.science/api/pith-number/3D2ECFM4Z4BBAET2C5AZJ3QTPS/graph.json","fetch_events":"https://pith.science/api/pith-number/3D2ECFM4Z4BBAET2C5AZJ3QTPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS/action/storage_attestation","attest_author":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS/action/author_attestation","sign_citation":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS/action/citation_signature","submit_replication":"https://pith.science/pith/3D2ECFM4Z4BBAET2C5AZJ3QTPS/action/replication_record"}},"created_at":"2026-07-05T04:12:18.375488+00:00","updated_at":"2026-07-05T04:12:18.375488+00:00"}