{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:55MDH3DSCREIG5AYX5IY67VLKU","short_pith_number":"pith:55MDH3DS","schema_version":"1.0","canonical_sha256":"ef5833ec721448837418bf518f7eab5534aae664d401bb09cdc983fdbf605321","source":{"kind":"arxiv","id":"1907.02544","version":2},"attestation_state":"computed","paper":{"title":"Large Scale Adversarial Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Karen Simonyan","submitted_at":"2019-07-04T18:00:17Z","abstract_excerpt":"Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches based on self-supervision. In this work we show that progress in image generation quality translates to substantially improved representation learning performance. Our approach, BigBiGAN, builds upon the state-of-the-art BigGAN model, extending it to representation learning by adding an encoder and modifying the discriminator. We extensively evaluate the represe"},"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":"1907.02544","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-04T18:00:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bab8c6076cc4ca0105e278aa8307ccd576e892c1177823763019d0ddb20e5919","abstract_canon_sha256":"c3dd605981b44999873b4751fa44bcf01f49e0745f6de0cae8fe927ac74c4058"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:07.859954Z","signature_b64":"Q6iihp8VzmgwtPaY2Zo21CABDWDGdbdIPERFW015aYepai4SzzhhGxXEjWTGOp+QBmdNSNDEyjTIInJhiPlZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef5833ec721448837418bf518f7eab5534aae664d401bb09cdc983fdbf605321","last_reissued_at":"2026-07-05T00:17:07.859527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:07.859527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Scale Adversarial Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Karen Simonyan","submitted_at":"2019-07-04T18:00:17Z","abstract_excerpt":"Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches based on self-supervision. In this work we show that progress in image generation quality translates to substantially improved representation learning performance. Our approach, BigBiGAN, builds upon the state-of-the-art BigGAN model, extending it to representation learning by adding an encoder and modifying the discriminator. We extensively evaluate the represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02544","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/1907.02544/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":"1907.02544","created_at":"2026-07-05T00:17:07.859580+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02544v2","created_at":"2026-07-05T00:17:07.859580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02544","created_at":"2026-07-05T00:17:07.859580+00:00"},{"alias_kind":"pith_short_12","alias_value":"55MDH3DSCREI","created_at":"2026-07-05T00:17:07.859580+00:00"},{"alias_kind":"pith_short_16","alias_value":"55MDH3DSCREIG5AY","created_at":"2026-07-05T00:17:07.859580+00:00"},{"alias_kind":"pith_short_8","alias_value":"55MDH3DS","created_at":"2026-07-05T00:17:07.859580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02305","citing_title":"Mapping Whisper Representations to Human ECoG Responses with Interpretable Time-Resolved Neural Encoding","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"1910.04867","citing_title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2110.04627","citing_title":"Vector-quantized Image Modeling with Improved VQGAN","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU","json":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU.json","graph_json":"https://pith.science/api/pith-number/55MDH3DSCREIG5AYX5IY67VLKU/graph.json","events_json":"https://pith.science/api/pith-number/55MDH3DSCREIG5AYX5IY67VLKU/events.json","paper":"https://pith.science/paper/55MDH3DS"},"agent_actions":{"view_html":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU","download_json":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU.json","view_paper":"https://pith.science/paper/55MDH3DS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02544&json=true","fetch_graph":"https://pith.science/api/pith-number/55MDH3DSCREIG5AYX5IY67VLKU/graph.json","fetch_events":"https://pith.science/api/pith-number/55MDH3DSCREIG5AYX5IY67VLKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU/action/storage_attestation","attest_author":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU/action/author_attestation","sign_citation":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU/action/citation_signature","submit_replication":"https://pith.science/pith/55MDH3DSCREIG5AYX5IY67VLKU/action/replication_record"}},"created_at":"2026-07-05T00:17:07.859580+00:00","updated_at":"2026-07-05T00:17:07.859580+00:00"}