{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5PWVQPLNDQA2EPOGXDJC6KYS7V","short_pith_number":"pith:5PWVQPLN","schema_version":"1.0","canonical_sha256":"ebed583d6d1c01a23dc6b8d22f2b12fd4902557dd503a414e2641f37eb5ca58a","source":{"kind":"arxiv","id":"1902.00159","version":1},"attestation_state":"computed","paper":{"title":"Compressing GANs using Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Gain, Ameya Patil, Angeline Aguinaldo, Kolten Pearson, Ping-yeh Chiang, Soheil Feizi","submitted_at":"2019-02-01T03:24:26Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have been used in several machine learning tasks such as domain transfer, super resolution, and synthetic data generation. State-of-the-art GANs often use tens of millions of parameters, making them expensive to deploy for applications in low SWAP (size, weight, and power) hardware, such as mobile devices, and for applications with real time capabilities. There has been no work found to reduce the number of parameters used in GANs. Therefore, we propose a method to compress GANs using knowledge distillation techniques, in which a smaller \"student\" GAN lea"},"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":"1902.00159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-01T03:24:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e28047377cf5208a9cbbf8c922d29cfabf97611b9dca96f3775f82e96d9da99f","abstract_canon_sha256":"12cb0e8c9803794970d34bcf01bba64581f416f60cd68e9410e73deeb89e778e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:58.142337Z","signature_b64":"TbRyMMtvm9CoISZClEINK8vpubBGJG+XAIrvOLogXYzDWfvo+A453bflsv3FJYsRvYXA6KMYZKEJ6LYQUbG3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebed583d6d1c01a23dc6b8d22f2b12fd4902557dd503a414e2641f37eb5ca58a","last_reissued_at":"2026-05-17T23:54:58.141731Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:58.141731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressing GANs using Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Gain, Ameya Patil, Angeline Aguinaldo, Kolten Pearson, Ping-yeh Chiang, Soheil Feizi","submitted_at":"2019-02-01T03:24:26Z","abstract_excerpt":"Generative Adversarial Networks (GANs) have been used in several machine learning tasks such as domain transfer, super resolution, and synthetic data generation. State-of-the-art GANs often use tens of millions of parameters, making them expensive to deploy for applications in low SWAP (size, weight, and power) hardware, such as mobile devices, and for applications with real time capabilities. There has been no work found to reduce the number of parameters used in GANs. Therefore, we propose a method to compress GANs using knowledge distillation techniques, in which a smaller \"student\" GAN lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00159","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":""},"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":"1902.00159","created_at":"2026-05-17T23:54:58.141827+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.00159v1","created_at":"2026-05-17T23:54:58.141827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00159","created_at":"2026-05-17T23:54:58.141827+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PWVQPLNDQA2","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PWVQPLNDQA2EPOG","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PWVQPLN","created_at":"2026-05-18T12:33:10.108867+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/5PWVQPLNDQA2EPOGXDJC6KYS7V","json":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V.json","graph_json":"https://pith.science/api/pith-number/5PWVQPLNDQA2EPOGXDJC6KYS7V/graph.json","events_json":"https://pith.science/api/pith-number/5PWVQPLNDQA2EPOGXDJC6KYS7V/events.json","paper":"https://pith.science/paper/5PWVQPLN"},"agent_actions":{"view_html":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V","download_json":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V.json","view_paper":"https://pith.science/paper/5PWVQPLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.00159&json=true","fetch_graph":"https://pith.science/api/pith-number/5PWVQPLNDQA2EPOGXDJC6KYS7V/graph.json","fetch_events":"https://pith.science/api/pith-number/5PWVQPLNDQA2EPOGXDJC6KYS7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V/action/storage_attestation","attest_author":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V/action/author_attestation","sign_citation":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V/action/citation_signature","submit_replication":"https://pith.science/pith/5PWVQPLNDQA2EPOGXDJC6KYS7V/action/replication_record"}},"created_at":"2026-05-17T23:54:58.141827+00:00","updated_at":"2026-05-17T23:54:58.141827+00:00"}