{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RZHP5ROYQWADALEC6IVNSPAGEA","short_pith_number":"pith:RZHP5ROY","schema_version":"1.0","canonical_sha256":"8e4efec5d88580302c82f22ad93c06203fb2047a3e6e2a28e49f816d47949343","source":{"kind":"arxiv","id":"2006.08198","version":3},"attestation_state":"computed","paper":{"title":"AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Haoran Li, Haotao Wang, Wuyang Chen, Yingyan Celine Lin, Yonggan Fu, Zhangyang Wang","submitted_at":"2020-06-15T07:56:24Z","abstract_excerpt":"The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement and editing. However, compared to the substantial efforts to compressing other deep models, the research on compressing GANs (usually the generators) remains at its infancy stage. Existing GAN compression algorithms are limited to handling specific GAN architectures and losses. Inspired by the recent success of AutoML in deep compression, we introduce AutoML to GAN compression a"},"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":"2006.08198","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-15T07:56:24Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"9e4f28dfd4e77139275c8c70122ae820501b4a68bfed1d6fecbeb8288de46eb8","abstract_canon_sha256":"cdc931507a60604245a79dd86be24f49043eeece840f80dffbe4a9adc7635a5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:44.565108Z","signature_b64":"06BtIPa6a9oTzzoHa/s685gzzKdhH9cVVGb2Pu5slppg1LGaI1E0m5CY0fLm8YhBPWp6YJiRt42Nmon4F3FwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e4efec5d88580302c82f22ad93c06203fb2047a3e6e2a28e49f816d47949343","last_reissued_at":"2026-07-05T09:56:44.564587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:44.564587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Haoran Li, Haotao Wang, Wuyang Chen, Yingyan Celine Lin, Yonggan Fu, Zhangyang Wang","submitted_at":"2020-06-15T07:56:24Z","abstract_excerpt":"The compression of Generative Adversarial Networks (GANs) has lately drawn attention, due to the increasing demand for deploying GANs into mobile devices for numerous applications such as image translation, enhancement and editing. However, compared to the substantial efforts to compressing other deep models, the research on compressing GANs (usually the generators) remains at its infancy stage. Existing GAN compression algorithms are limited to handling specific GAN architectures and losses. Inspired by the recent success of AutoML in deep compression, we introduce AutoML to GAN compression a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.08198","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/2006.08198/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":"2006.08198","created_at":"2026-07-05T09:56:44.564670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.08198v3","created_at":"2026-07-05T09:56:44.564670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.08198","created_at":"2026-07-05T09:56:44.564670+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZHP5ROYQWAD","created_at":"2026-07-05T09:56:44.564670+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZHP5ROYQWADALEC","created_at":"2026-07-05T09:56:44.564670+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZHP5ROY","created_at":"2026-07-05T09:56:44.564670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04850","citing_title":"Uncertainty-Aware End-to-End Co-Design of Neural Network Processors: From Training and Mapping to Fabrication","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":172,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA","json":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA.json","graph_json":"https://pith.science/api/pith-number/RZHP5ROYQWADALEC6IVNSPAGEA/graph.json","events_json":"https://pith.science/api/pith-number/RZHP5ROYQWADALEC6IVNSPAGEA/events.json","paper":"https://pith.science/paper/RZHP5ROY"},"agent_actions":{"view_html":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA","download_json":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA.json","view_paper":"https://pith.science/paper/RZHP5ROY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.08198&json=true","fetch_graph":"https://pith.science/api/pith-number/RZHP5ROYQWADALEC6IVNSPAGEA/graph.json","fetch_events":"https://pith.science/api/pith-number/RZHP5ROYQWADALEC6IVNSPAGEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA/action/storage_attestation","attest_author":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA/action/author_attestation","sign_citation":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA/action/citation_signature","submit_replication":"https://pith.science/pith/RZHP5ROYQWADALEC6IVNSPAGEA/action/replication_record"}},"created_at":"2026-07-05T09:56:44.564670+00:00","updated_at":"2026-07-05T09:56:44.564670+00:00"}