{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3KEEDG7652JF45WHHNHE75UKIL","short_pith_number":"pith:3KEEDG76","schema_version":"1.0","canonical_sha256":"da88419bfeee925e76c73b4e4ff68a42cdba982eb096fe7940584170301e6356","source":{"kind":"arxiv","id":"2106.07631","version":3},"attestation_state":"computed","paper":{"title":"Improved Transformer for High-Resolution GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Han Zhang, Long Zhao, Ting Chen, Zizhao Zhang","submitted_at":"2021-06-14T17:39:49Z","abstract_excerpt":"Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs). In this paper, we introduce two key ingredients to Transformer to address this challenge. First, in low-resolution stages of the generative process, standard global self-attention is replaced with the proposed multi-axis blocked self-attention which allows efficient mixing of local and global attention. Se"},"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":"2106.07631","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-14T17:39:49Z","cross_cats_sorted":[],"title_canon_sha256":"61efc5e0a764c65ef2a96440677c7a5d4966f782c9436fd871b3a04218172b7e","abstract_canon_sha256":"5425e5d5fcc2e3fc030cebc8ebf20dd5e9ec16a187b1b4be63b56fed0a738d08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:42.023903Z","signature_b64":"uKyorgVnf9KAVduickQ1gjR86t8wBmC0dxq8czrpNYpth6mJLMunGuGViJ5snX4kG9aS0XmQ7yVCXVW6QKptBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da88419bfeee925e76c73b4e4ff68a42cdba982eb096fe7940584170301e6356","last_reissued_at":"2026-07-05T03:43:42.023468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:42.023468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Transformer for High-Resolution GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris N. Metaxas, Han Zhang, Long Zhao, Ting Chen, Zizhao Zhang","submitted_at":"2021-06-14T17:39:49Z","abstract_excerpt":"Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs). In this paper, we introduce two key ingredients to Transformer to address this challenge. First, in low-resolution stages of the generative process, standard global self-attention is replaced with the proposed multi-axis blocked self-attention which allows efficient mixing of local and global attention. Se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07631","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/2106.07631/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":"2106.07631","created_at":"2026-07-05T03:43:42.023525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07631v3","created_at":"2026-07-05T03:43:42.023525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07631","created_at":"2026-07-05T03:43:42.023525+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KEEDG7652JF","created_at":"2026-07-05T03:43:42.023525+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KEEDG7652JF45WH","created_at":"2026-07-05T03:43:42.023525+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KEEDG76","created_at":"2026-07-05T03:43:42.023525+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/3KEEDG7652JF45WHHNHE75UKIL","json":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL.json","graph_json":"https://pith.science/api/pith-number/3KEEDG7652JF45WHHNHE75UKIL/graph.json","events_json":"https://pith.science/api/pith-number/3KEEDG7652JF45WHHNHE75UKIL/events.json","paper":"https://pith.science/paper/3KEEDG76"},"agent_actions":{"view_html":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL","download_json":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL.json","view_paper":"https://pith.science/paper/3KEEDG76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07631&json=true","fetch_graph":"https://pith.science/api/pith-number/3KEEDG7652JF45WHHNHE75UKIL/graph.json","fetch_events":"https://pith.science/api/pith-number/3KEEDG7652JF45WHHNHE75UKIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL/action/storage_attestation","attest_author":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL/action/author_attestation","sign_citation":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL/action/citation_signature","submit_replication":"https://pith.science/pith/3KEEDG7652JF45WHHNHE75UKIL/action/replication_record"}},"created_at":"2026-07-05T03:43:42.023525+00:00","updated_at":"2026-07-05T03:43:42.023525+00:00"}