{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T7LH63CDE4HALS74NURSAX74XW","short_pith_number":"pith:T7LH63CD","schema_version":"1.0","canonical_sha256":"9fd67f6c43270e05cbfc6d23205ffcbdb3968090deb34550183e96011e91e758","source":{"kind":"arxiv","id":"1805.08318","version":2},"attestation_state":"computed","paper":{"title":"Self-Attention Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Augustus Odena, Dimitris Metaxas, Han Zhang, Ian Goodfellow","submitted_at":"2018-05-21T23:10:35Z","abstract_excerpt":"In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other. Furthermore, recent work has shown that generator conditioning affects GAN p"},"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":"1805.08318","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-21T23:10:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5eb5e10eb0cadef1ba2517aece1d1ea5997e826a871039c5f6574c9f28559823","abstract_canon_sha256":"65d76e76dc1f384e3d2b6f2c180e9294f18da6a98cf7e84b4193d385e3cfa56f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:17.999975Z","signature_b64":"Hiq8aBhEW/SuOGY9ZgXoBE3ojH9VPwa1RwJmykuzZuad+creeMoYUvVCLd8hYRLftJOlgTOyQD5vO+cZlJd3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fd67f6c43270e05cbfc6d23205ffcbdb3968090deb34550183e96011e91e758","last_reissued_at":"2026-05-17T23:43:17.999296Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:17.999296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Attention Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Augustus Odena, Dimitris Metaxas, Han Zhang, Ian Goodfellow","submitted_at":"2018-05-21T23:10:35Z","abstract_excerpt":"In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other. Furthermore, recent work has shown that generator conditioning affects GAN p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08318","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":""},"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":"1805.08318","created_at":"2026-05-17T23:43:17.999406+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08318v2","created_at":"2026-05-17T23:43:17.999406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08318","created_at":"2026-05-17T23:43:17.999406+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7LH63CDE4HA","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7LH63CDE4HALS74","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7LH63CD","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1906.09909","citing_title":"Deep Exemplar-based Video Colorization","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11080","citing_title":"AGAN: Towards Automated Design of Generative Adversarial Networks","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11118","citing_title":"DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02788","citing_title":"Incremental Concept Learning via Online Generative Memory Recall","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07001","citing_title":"Latent Adversarial Defence with Boundary-guided Generation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16476","citing_title":"Deep Learning for MRI Slice Interpolation: The Critical Role of Problem Formulation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15895","citing_title":"Layer Selection in Feature-Based Losses Affects Image Quality and Microstructural Consistency in Deep Learning Super-Resolution of Brain Diffusion MRI","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13842","citing_title":"From DES to KiDS: Domain adaptation for cross-survey detection of low-surface-brightness galaxies","ref_index":283,"is_internal_anchor":true},{"citing_arxiv_id":"1809.11096","citing_title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW","json":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW.json","graph_json":"https://pith.science/api/pith-number/T7LH63CDE4HALS74NURSAX74XW/graph.json","events_json":"https://pith.science/api/pith-number/T7LH63CDE4HALS74NURSAX74XW/events.json","paper":"https://pith.science/paper/T7LH63CD"},"agent_actions":{"view_html":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW","download_json":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW.json","view_paper":"https://pith.science/paper/T7LH63CD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08318&json=true","fetch_graph":"https://pith.science/api/pith-number/T7LH63CDE4HALS74NURSAX74XW/graph.json","fetch_events":"https://pith.science/api/pith-number/T7LH63CDE4HALS74NURSAX74XW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW/action/storage_attestation","attest_author":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW/action/author_attestation","sign_citation":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW/action/citation_signature","submit_replication":"https://pith.science/pith/T7LH63CDE4HALS74NURSAX74XW/action/replication_record"}},"created_at":"2026-05-17T23:43:17.999406+00:00","updated_at":"2026-05-17T23:43:17.999406+00:00"}