{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5PPBTYQRARIUBSD3DKHPCG3T6E","short_pith_number":"pith:5PPBTYQR","schema_version":"1.0","canonical_sha256":"ebde19e211045140c87b1a8ef11b73f12c5acda8e9323471510248c42a8e3fc1","source":{"kind":"arxiv","id":"2210.09919","version":1},"attestation_state":"computed","paper":{"title":"Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Pieropan, Atsuto Maki, Hossein Azizpour, Miquel Mart\\'i i Rabad\\'an","submitted_at":"2022-10-18T15:02:51Z","abstract_excerpt":"We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled"},"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":"2210.09919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-18T15:02:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63563fb5c807cd53bf13fbd6489de8a18047f597c08e4a17153f81b0cf627ec5","abstract_canon_sha256":"5342932f94c3e6baef6ad186cd7a467c5cecf96643c1c8f181378535778665e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:00.815804Z","signature_b64":"LxpzM8qwULQah/sYI7MurNsckEauLGgz110FcrfmHA5kQvkLCh6yL3e9SjTS4Oi6dGIHzCtjgPeGbnNvDwQvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebde19e211045140c87b1a8ef11b73f12c5acda8e9323471510248c42a8e3fc1","last_reissued_at":"2026-07-05T05:08:00.815383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:00.815383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Pieropan, Atsuto Maki, Hossein Azizpour, Miquel Mart\\'i i Rabad\\'an","submitted_at":"2022-10-18T15:02:51Z","abstract_excerpt":"We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via strong data augmentation. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. This allows us to still use the full strength of data augmentation pipelines, including geometric transformations. We evaluate it on semi-supervised semantic segmentation on Cityscapes and Pascal VOC with different percentages of labeled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09919","kind":"arxiv","version":1},"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/2210.09919/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":"2210.09919","created_at":"2026-07-05T05:08:00.815449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09919v1","created_at":"2026-07-05T05:08:00.815449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09919","created_at":"2026-07-05T05:08:00.815449+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PPBTYQRARIU","created_at":"2026-07-05T05:08:00.815449+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PPBTYQRARIUBSD3","created_at":"2026-07-05T05:08:00.815449+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PPBTYQR","created_at":"2026-07-05T05:08:00.815449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18823","citing_title":"Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E","json":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E.json","graph_json":"https://pith.science/api/pith-number/5PPBTYQRARIUBSD3DKHPCG3T6E/graph.json","events_json":"https://pith.science/api/pith-number/5PPBTYQRARIUBSD3DKHPCG3T6E/events.json","paper":"https://pith.science/paper/5PPBTYQR"},"agent_actions":{"view_html":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E","download_json":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E.json","view_paper":"https://pith.science/paper/5PPBTYQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09919&json=true","fetch_graph":"https://pith.science/api/pith-number/5PPBTYQRARIUBSD3DKHPCG3T6E/graph.json","fetch_events":"https://pith.science/api/pith-number/5PPBTYQRARIUBSD3DKHPCG3T6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E/action/storage_attestation","attest_author":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E/action/author_attestation","sign_citation":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E/action/citation_signature","submit_replication":"https://pith.science/pith/5PPBTYQRARIUBSD3DKHPCG3T6E/action/replication_record"}},"created_at":"2026-07-05T05:08:00.815449+00:00","updated_at":"2026-07-05T05:08:00.815449+00:00"}