{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EWJCPPBKYZSOXZWJD5Q7KVR6BN","short_pith_number":"pith:EWJCPPBK","schema_version":"1.0","canonical_sha256":"259227bc2ac664ebe6c91f61f5563e0b696bdc92d266788f11f5ac8841ae4001","source":{"kind":"arxiv","id":"2112.03126","version":3},"attestation_state":"computed","paper":{"title":"Label-Efficient Semantic Segmentation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrey Voynov, Artem Babenko, Dmitry Baranchuk, Ivan Rubachev, Valentin Khrulkov","submitted_at":"2021-12-06T15:55:30Z","abstract_excerpt":"Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of diffusion models has made them an appealing tool in several applications, including inpainting, super-resolution, and semantic editing. In this paper, we demonstrate that diffusion models can also serve as an instrument for semantic segmentation, especially in the setup when labeled data is scarce. In particular, for several pretrained diffusion models, we in"},"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":"2112.03126","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-06T15:55:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d41fc78b55527815e492c4d11f978b7aa5364ca2dfd40f3a08df240b40555c31","abstract_canon_sha256":"274eecdc5505abefd12e9e2d8ac2b41804f3cfce7f36fc142c390e1a8577aab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:36.777589Z","signature_b64":"6Y0khn3idSem8uEDcrset9dLdZTj1QIDBtFRCP+cI9nGwg83cRSQvwAqFazra0nGWDmscM0DUkAUHoSQxANXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"259227bc2ac664ebe6c91f61f5563e0b696bdc92d266788f11f5ac8841ae4001","last_reissued_at":"2026-07-05T04:05:36.777102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:36.777102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-Efficient Semantic Segmentation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrey Voynov, Artem Babenko, Dmitry Baranchuk, Ivan Rubachev, Valentin Khrulkov","submitted_at":"2021-12-06T15:55:30Z","abstract_excerpt":"Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of diffusion models has made them an appealing tool in several applications, including inpainting, super-resolution, and semantic editing. In this paper, we demonstrate that diffusion models can also serve as an instrument for semantic segmentation, especially in the setup when labeled data is scarce. In particular, for several pretrained diffusion models, we in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03126","kind":"arxiv","version":3},"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/2112.03126/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":"2112.03126","created_at":"2026-07-05T04:05:36.777163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03126v3","created_at":"2026-07-05T04:05:36.777163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03126","created_at":"2026-07-05T04:05:36.777163+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWJCPPBKYZSO","created_at":"2026-07-05T04:05:36.777163+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWJCPPBKYZSOXZWJ","created_at":"2026-07-05T04:05:36.777163+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWJCPPBK","created_at":"2026-07-05T04:05:36.777163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.09479","citing_title":"DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15263","citing_title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16384","citing_title":"Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19289","citing_title":"What Makes Synthetic Data Effective in Image Segmentation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13013","citing_title":"JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03134","citing_title":"SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24575","citing_title":"Diffusion Model as a Generalist Segmentation Learner","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04590","citing_title":"From Diffusion to Rectified Flow: Rethinking Text-Based Segmentation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN","json":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN.json","graph_json":"https://pith.science/api/pith-number/EWJCPPBKYZSOXZWJD5Q7KVR6BN/graph.json","events_json":"https://pith.science/api/pith-number/EWJCPPBKYZSOXZWJD5Q7KVR6BN/events.json","paper":"https://pith.science/paper/EWJCPPBK"},"agent_actions":{"view_html":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN","download_json":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN.json","view_paper":"https://pith.science/paper/EWJCPPBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03126&json=true","fetch_graph":"https://pith.science/api/pith-number/EWJCPPBKYZSOXZWJD5Q7KVR6BN/graph.json","fetch_events":"https://pith.science/api/pith-number/EWJCPPBKYZSOXZWJD5Q7KVR6BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN/action/storage_attestation","attest_author":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN/action/author_attestation","sign_citation":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN/action/citation_signature","submit_replication":"https://pith.science/pith/EWJCPPBKYZSOXZWJD5Q7KVR6BN/action/replication_record"}},"created_at":"2026-07-05T04:05:36.777163+00:00","updated_at":"2026-07-05T04:05:36.777163+00:00"}