{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GT2KW7ARBFPO3VXRFW5WNCFEEL","short_pith_number":"pith:GT2KW7AR","schema_version":"1.0","canonical_sha256":"34f4ab7c11095eedd6f12dbb6688a422e3c8b4aba5508a53ae984221cab3e999","source":{"kind":"arxiv","id":"1906.01916","version":5},"attestation_state":"computed","paper":{"title":"Semi-supervised semantic segmentation needs strong, varied perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geoff French, Graham Finlayson, Michal Mackiewicz, Samuli Laine, Timo Aila","submitted_at":"2019-06-05T10:09:27Z","abstract_excerpt":"Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists of uniform class clusters of samples separated by low density regions - as important to its success. We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of "},"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":"1906.01916","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-05T10:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"d457d04a0abdbee2b43bfb10fc5c7dd76f89400eba4fda33a65385fa8164c678","abstract_canon_sha256":"d5333581afb75eb0e605d5f4ebe257b4b27007f33b78f00ca0d39755d8b49243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:04.688821Z","signature_b64":"YTtyYr4rEYYrg8lIDLqHvfNWWLFSX3j7GSoPmDq1VH/pyiq1KdhCkY9DcNMJZtagWinog/wJFe3G/cQvUwLOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f4ab7c11095eedd6f12dbb6688a422e3c8b4aba5508a53ae984221cab3e999","last_reissued_at":"2026-07-05T01:26:04.688349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:04.688349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised semantic segmentation needs strong, varied perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geoff French, Graham Finlayson, Michal Mackiewicz, Samuli Laine, Timo Aila","submitted_at":"2019-06-05T10:09:27Z","abstract_excerpt":"Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data distribution consists of uniform class clusters of samples separated by low density regions - as important to its success. We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01916","kind":"arxiv","version":5},"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/1906.01916/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":"1906.01916","created_at":"2026-07-05T01:26:04.688407+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01916v5","created_at":"2026-07-05T01:26:04.688407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01916","created_at":"2026-07-05T01:26:04.688407+00:00"},{"alias_kind":"pith_short_12","alias_value":"GT2KW7ARBFPO","created_at":"2026-07-05T01:26:04.688407+00:00"},{"alias_kind":"pith_short_16","alias_value":"GT2KW7ARBFPO3VXR","created_at":"2026-07-05T01:26:04.688407+00:00"},{"alias_kind":"pith_short_8","alias_value":"GT2KW7AR","created_at":"2026-07-05T01:26:04.688407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04427","citing_title":"Implicit Fuzzification via Bounded Noise Injection for Robust Medical Image Segmentation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL","json":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL.json","graph_json":"https://pith.science/api/pith-number/GT2KW7ARBFPO3VXRFW5WNCFEEL/graph.json","events_json":"https://pith.science/api/pith-number/GT2KW7ARBFPO3VXRFW5WNCFEEL/events.json","paper":"https://pith.science/paper/GT2KW7AR"},"agent_actions":{"view_html":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL","download_json":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL.json","view_paper":"https://pith.science/paper/GT2KW7AR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01916&json=true","fetch_graph":"https://pith.science/api/pith-number/GT2KW7ARBFPO3VXRFW5WNCFEEL/graph.json","fetch_events":"https://pith.science/api/pith-number/GT2KW7ARBFPO3VXRFW5WNCFEEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL/action/storage_attestation","attest_author":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL/action/author_attestation","sign_citation":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL/action/citation_signature","submit_replication":"https://pith.science/pith/GT2KW7ARBFPO3VXRFW5WNCFEEL/action/replication_record"}},"created_at":"2026-07-05T01:26:04.688407+00:00","updated_at":"2026-07-05T01:26:04.688407+00:00"}