{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5XRLKM66BK2GYFD2PGDZLZBIB3","short_pith_number":"pith:5XRLKM66","schema_version":"1.0","canonical_sha256":"ede2b533de0ab46c147a798795e4280efc1a5099325e786754708adad89f9b79","source":{"kind":"arxiv","id":"2303.11606","version":1},"attestation_state":"computed","paper":{"title":"CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong-Geol Choi, Hyeoncheol Noh, Jingi Ju, Minseok Seo, Yooseung Wang","submitted_at":"2023-03-21T05:56:53Z","abstract_excerpt":"Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with pseudo-labeling pixels having high confidences for unlabeled images. However, using only highconfidence pixels for self-training may result in losing much of the information in the unlabeled datasets due to poor confidence calibration of modern deep learning networks. In this paper, we propose a class-adaptive semisupervision framework for semi-supervised semant"},"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":"2303.11606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-21T05:56:53Z","cross_cats_sorted":[],"title_canon_sha256":"eff9c1388173af828f8cb5144d0d91245faf25b1fc098e7ef741f0e7dbf67fb9","abstract_canon_sha256":"29000d0fd16b65bfceddead7fbd5c496787cfc545062b3efc7310dfe00f8badf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:20.095105Z","signature_b64":"+DKrZKDDE7d2O8sCenA/SKgIILDMAS9waZDSKTmqNCAbJ3b4FFNQolJPrumbQXyG/X/2N9DNhVD+ooWcD+IMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ede2b533de0ab46c147a798795e4280efc1a5099325e786754708adad89f9b79","last_reissued_at":"2026-07-05T05:53:20.094722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:20.094722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong-Geol Choi, Hyeoncheol Noh, Jingi Ju, Minseok Seo, Yooseung Wang","submitted_at":"2023-03-21T05:56:53Z","abstract_excerpt":"Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with pseudo-labeling pixels having high confidences for unlabeled images. However, using only highconfidence pixels for self-training may result in losing much of the information in the unlabeled datasets due to poor confidence calibration of modern deep learning networks. In this paper, we propose a class-adaptive semisupervision framework for semi-supervised semant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11606","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/2303.11606/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":"2303.11606","created_at":"2026-07-05T05:53:20.094778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11606v1","created_at":"2026-07-05T05:53:20.094778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11606","created_at":"2026-07-05T05:53:20.094778+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XRLKM66BK2G","created_at":"2026-07-05T05:53:20.094778+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XRLKM66BK2GYFD2","created_at":"2026-07-05T05:53:20.094778+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XRLKM66","created_at":"2026-07-05T05:53:20.094778+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.12773","citing_title":"CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3","json":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3.json","graph_json":"https://pith.science/api/pith-number/5XRLKM66BK2GYFD2PGDZLZBIB3/graph.json","events_json":"https://pith.science/api/pith-number/5XRLKM66BK2GYFD2PGDZLZBIB3/events.json","paper":"https://pith.science/paper/5XRLKM66"},"agent_actions":{"view_html":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3","download_json":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3.json","view_paper":"https://pith.science/paper/5XRLKM66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11606&json=true","fetch_graph":"https://pith.science/api/pith-number/5XRLKM66BK2GYFD2PGDZLZBIB3/graph.json","fetch_events":"https://pith.science/api/pith-number/5XRLKM66BK2GYFD2PGDZLZBIB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3/action/storage_attestation","attest_author":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3/action/author_attestation","sign_citation":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3/action/citation_signature","submit_replication":"https://pith.science/pith/5XRLKM66BK2GYFD2PGDZLZBIB3/action/replication_record"}},"created_at":"2026-07-05T05:53:20.094778+00:00","updated_at":"2026-07-05T05:53:20.094778+00:00"}