{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZKS3BGUDN7JNF2MUW3762WADDU","short_pith_number":"pith:ZKS3BGUD","schema_version":"1.0","canonical_sha256":"caa5b09a836fd2d2e994b6ffed58031d36617524f54f100246bd6836943dc648","source":{"kind":"arxiv","id":"2108.00968","version":2},"attestation_state":"computed","paper":{"title":"Robust Semantic Segmentation with Superpixel-Mix","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Angela Yao, Gianni Franchi, Mai Lan Ha, Nacim Belkhir, Volker Blanz, Yufei Hu","submitted_at":"2021-08-02T15:13:52Z","abstract_excerpt":"Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce Superpixel-mix, a new superpixel-based data augmentation method with teacher-student consistency training. Unlike other mixing-based augmentation techniques, mixing superpixels between images is aware of object boundaries, while yielding consistent gains in segmentation accuracy. Our proposed technique achieves state-of-the-art results in semi-supervised seman"},"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":"2108.00968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-02T15:13:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6c43a5aeb9a95227c2e4bf3949d3e817dc354c1ca86a5c1eea465baec6e90c4f","abstract_canon_sha256":"2d6ca11490721ccf2f6ee33d42e1068e3556ea76e5c629da451c2840a1ad1532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:30.828218Z","signature_b64":"lH6wsVZDdn1insTVCKbZyQBG90cUkZ7WM7E636NQtFXbvBR5Zh9BjhToLWsVSK6CR8+Paw0ux7VJHbOz2/zlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa5b09a836fd2d2e994b6ffed58031d36617524f54f100246bd6836943dc648","last_reissued_at":"2026-07-05T03:24:30.827787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:30.827787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Semantic Segmentation with Superpixel-Mix","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Angela Yao, Gianni Franchi, Mai Lan Ha, Nacim Belkhir, Volker Blanz, Yufei Hu","submitted_at":"2021-08-02T15:13:52Z","abstract_excerpt":"Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce Superpixel-mix, a new superpixel-based data augmentation method with teacher-student consistency training. Unlike other mixing-based augmentation techniques, mixing superpixels between images is aware of object boundaries, while yielding consistent gains in segmentation accuracy. Our proposed technique achieves state-of-the-art results in semi-supervised seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00968","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/2108.00968/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":"2108.00968","created_at":"2026-07-05T03:24:30.827841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00968v2","created_at":"2026-07-05T03:24:30.827841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00968","created_at":"2026-07-05T03:24:30.827841+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKS3BGUDN7JN","created_at":"2026-07-05T03:24:30.827841+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKS3BGUDN7JNF2MU","created_at":"2026-07-05T03:24:30.827841+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKS3BGUD","created_at":"2026-07-05T03:24:30.827841+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/ZKS3BGUDN7JNF2MUW3762WADDU","json":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU.json","graph_json":"https://pith.science/api/pith-number/ZKS3BGUDN7JNF2MUW3762WADDU/graph.json","events_json":"https://pith.science/api/pith-number/ZKS3BGUDN7JNF2MUW3762WADDU/events.json","paper":"https://pith.science/paper/ZKS3BGUD"},"agent_actions":{"view_html":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU","download_json":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU.json","view_paper":"https://pith.science/paper/ZKS3BGUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00968&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKS3BGUDN7JNF2MUW3762WADDU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKS3BGUDN7JNF2MUW3762WADDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU/action/storage_attestation","attest_author":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU/action/author_attestation","sign_citation":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU/action/citation_signature","submit_replication":"https://pith.science/pith/ZKS3BGUDN7JNF2MUW3762WADDU/action/replication_record"}},"created_at":"2026-07-05T03:24:30.827841+00:00","updated_at":"2026-07-05T03:24:30.827841+00:00"}