{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:THMYKFTQKF7BSKXGM6DFPHS5OS","short_pith_number":"pith:THMYKFTQ","schema_version":"1.0","canonical_sha256":"99d9851670517e192ae66786579e5d74a3905c414ac2861e87f00756f8c04af4","source":{"kind":"arxiv","id":"2007.03844","version":2},"attestation_state":"computed","paper":{"title":"Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bharathkumar Ramachandra, Ranga Raju Vatsavai, Zexi Chen","submitted_at":"2020-07-08T01:47:10Z","abstract_excerpt":"Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However, their performance still lags behind the state-of-the-art non-GAN based SSL approaches. We identify that the main reason for this is the lack of consistency in class probability predictions on the same image under local perturbations. Following the general literature, we address this issue via label consistency regularization, which enforces the class probabili"},"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":"2007.03844","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-08T01:47:10Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"595a2c9eaacdf7e0262bba518add0467d2f85dbcf9ee0fbb584a055fe17edb80","abstract_canon_sha256":"469a42bf508257eb55e352ac2870525e7e7c7500c3e40c49ff2605c5fad7286a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:36.367552Z","signature_b64":"y0pC3oBLbhPrnG3jLOjlpnUaJj98k/JwfemwfSX/Tkfup//y48DUcUSk4HsyTxQDQYpVOm3h0xgjIUTMCH2TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99d9851670517e192ae66786579e5d74a3905c414ac2861e87f00756f8c04af4","last_reissued_at":"2026-07-05T01:35:36.366987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:36.366987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Regularization with Generative Adversarial Networks for Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bharathkumar Ramachandra, Ranga Raju Vatsavai, Zexi Chen","submitted_at":"2020-07-08T01:47:10Z","abstract_excerpt":"Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However, their performance still lags behind the state-of-the-art non-GAN based SSL approaches. We identify that the main reason for this is the lack of consistency in class probability predictions on the same image under local perturbations. Following the general literature, we address this issue via label consistency regularization, which enforces the class probabili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03844","kind":"arxiv","version":2},"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/2007.03844/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":"2007.03844","created_at":"2026-07-05T01:35:36.367052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03844v2","created_at":"2026-07-05T01:35:36.367052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03844","created_at":"2026-07-05T01:35:36.367052+00:00"},{"alias_kind":"pith_short_12","alias_value":"THMYKFTQKF7B","created_at":"2026-07-05T01:35:36.367052+00:00"},{"alias_kind":"pith_short_16","alias_value":"THMYKFTQKF7BSKXG","created_at":"2026-07-05T01:35:36.367052+00:00"},{"alias_kind":"pith_short_8","alias_value":"THMYKFTQ","created_at":"2026-07-05T01:35:36.367052+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/THMYKFTQKF7BSKXGM6DFPHS5OS","json":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS.json","graph_json":"https://pith.science/api/pith-number/THMYKFTQKF7BSKXGM6DFPHS5OS/graph.json","events_json":"https://pith.science/api/pith-number/THMYKFTQKF7BSKXGM6DFPHS5OS/events.json","paper":"https://pith.science/paper/THMYKFTQ"},"agent_actions":{"view_html":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS","download_json":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS.json","view_paper":"https://pith.science/paper/THMYKFTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03844&json=true","fetch_graph":"https://pith.science/api/pith-number/THMYKFTQKF7BSKXGM6DFPHS5OS/graph.json","fetch_events":"https://pith.science/api/pith-number/THMYKFTQKF7BSKXGM6DFPHS5OS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS/action/storage_attestation","attest_author":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS/action/author_attestation","sign_citation":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS/action/citation_signature","submit_replication":"https://pith.science/pith/THMYKFTQKF7BSKXGM6DFPHS5OS/action/replication_record"}},"created_at":"2026-07-05T01:35:36.367052+00:00","updated_at":"2026-07-05T01:35:36.367052+00:00"}