{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OUSEDRBYQJKIIUHTK3OEP2UIZ5","short_pith_number":"pith:OUSEDRBY","schema_version":"1.0","canonical_sha256":"752441c43882548450f356dc47ea88cf4052d99f82c6bed45dcc2e59d18faf94","source":{"kind":"arxiv","id":"2210.14670","version":3},"attestation_state":"computed","paper":{"title":"Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqi Wang, Chang Xu, Chong Fu, Haoyu Xie, Mingkai Zheng, Minjing Dong, Shan You","submitted_at":"2022-10-26T12:47:29Z","abstract_excerpt":"Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space. However, there exist inaccurate pseudo-labels which map the ambiguous representations of pixels to the wrong classes due to the limited cognitive ability of the model. In this paper, we define pixel-wise representations from a new perspective of probability theory and propose a Probabilistic Representation Contrastive Learning (PRCL)"},"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":"2210.14670","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T12:47:29Z","cross_cats_sorted":[],"title_canon_sha256":"698ddd4b28068884053af3efa14b674f3709e12693f29866596d76c48f9fc3c9","abstract_canon_sha256":"87b4314362d3f1efc3ae81b687abbea2b73ba1de2ee3c4c01d82ee11bc262827"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:51.417879Z","signature_b64":"OgUP8xdeExFh9gr1mZgpUuKjB2hG4KZGqHtEe8ksKnxxTCooRk6SzrajJ4OW74l2l60HiUgrkmC1W9OgRIb4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752441c43882548450f356dc47ea88cf4052d99f82c6bed45dcc2e59d18faf94","last_reissued_at":"2026-07-05T05:25:51.417359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:51.417359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqi Wang, Chang Xu, Chong Fu, Haoyu Xie, Mingkai Zheng, Minjing Dong, Shan You","submitted_at":"2022-10-26T12:47:29Z","abstract_excerpt":"Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space. However, there exist inaccurate pseudo-labels which map the ambiguous representations of pixels to the wrong classes due to the limited cognitive ability of the model. In this paper, we define pixel-wise representations from a new perspective of probability theory and propose a Probabilistic Representation Contrastive Learning (PRCL)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14670","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/2210.14670/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":"2210.14670","created_at":"2026-07-05T05:25:51.417412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14670v3","created_at":"2026-07-05T05:25:51.417412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14670","created_at":"2026-07-05T05:25:51.417412+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUSEDRBYQJKI","created_at":"2026-07-05T05:25:51.417412+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUSEDRBYQJKIIUHT","created_at":"2026-07-05T05:25:51.417412+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUSEDRBY","created_at":"2026-07-05T05:25:51.417412+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/OUSEDRBYQJKIIUHTK3OEP2UIZ5","json":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5.json","graph_json":"https://pith.science/api/pith-number/OUSEDRBYQJKIIUHTK3OEP2UIZ5/graph.json","events_json":"https://pith.science/api/pith-number/OUSEDRBYQJKIIUHTK3OEP2UIZ5/events.json","paper":"https://pith.science/paper/OUSEDRBY"},"agent_actions":{"view_html":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5","download_json":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5.json","view_paper":"https://pith.science/paper/OUSEDRBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14670&json=true","fetch_graph":"https://pith.science/api/pith-number/OUSEDRBYQJKIIUHTK3OEP2UIZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/OUSEDRBYQJKIIUHTK3OEP2UIZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5/action/storage_attestation","attest_author":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5/action/author_attestation","sign_citation":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5/action/citation_signature","submit_replication":"https://pith.science/pith/OUSEDRBYQJKIIUHTK3OEP2UIZ5/action/replication_record"}},"created_at":"2026-07-05T05:25:51.417412+00:00","updated_at":"2026-07-05T05:25:51.417412+00:00"}