{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U3GUI3TCSG2XAAI5INHNH3ZBXG","short_pith_number":"pith:U3GUI3TC","schema_version":"1.0","canonical_sha256":"a6cd446e6291b570011d434ed3ef21b99c05a505b045e07ce5e018401d773f90","source":{"kind":"arxiv","id":"1802.05751","version":3},"attestation_state":"computed","paper":{"title":"Image Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Ku, Ashish Vaswani, Dustin Tran, Jakob Uszkoreit, {\\L}ukasz Kaiser, Niki Parmar, Noam Shazeer","submitted_at":"2018-02-15T20:37:15Z","abstract_excerpt":"Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a recently proposed model architecture based on self-attention, the Transformer, to a sequence modeling formulation of image generation with a tractable likelihood. By restricting the self-attention mechanism to attend to local neighborhoods we significantly increase the size of images the model can process in practice, despite maintaining significantly larger rece"},"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":"1802.05751","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-15T20:37:15Z","cross_cats_sorted":[],"title_canon_sha256":"affb78fdae2d2bdfe0b4050efef4cd915e50f0b02b3c59376608b2ac9471388a","abstract_canon_sha256":"cf909327ef6585fe1648ba04e6dac039620f5fdea814a1e20b4bdcab2aa7f41d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:04.636795Z","signature_b64":"PJZF6LNJFg1Ke29fMA/Dr1LoQTUB3cWeCcXKCHXiri5//uenqbybyjEegzMcwoGAIzGsnCVzvJvVAd7pldMwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cd446e6291b570011d434ed3ef21b99c05a505b045e07ce5e018401d773f90","last_reissued_at":"2026-05-18T00:13:04.636147Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:04.636147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Ku, Ashish Vaswani, Dustin Tran, Jakob Uszkoreit, {\\L}ukasz Kaiser, Niki Parmar, Noam Shazeer","submitted_at":"2018-02-15T20:37:15Z","abstract_excerpt":"Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a recently proposed model architecture based on self-attention, the Transformer, to a sequence modeling formulation of image generation with a tractable likelihood. By restricting the self-attention mechanism to attend to local neighborhoods we significantly increase the size of images the model can process in practice, despite maintaining significantly larger rece"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05751","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":""},"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":"1802.05751","created_at":"2026-05-18T00:13:04.636253+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05751v3","created_at":"2026-05-18T00:13:04.636253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05751","created_at":"2026-05-18T00:13:04.636253+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3GUI3TCSG2X","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3GUI3TCSG2XAAI5","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3GUI3TC","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2507.08458","citing_title":"A document is worth a structured record: Principled inductive bias design for document recognition","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2102.09672","citing_title":"Improved Denoising Diffusion Probabilistic Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"1904.10509","citing_title":"Generating Long Sequences with Sparse Transformers","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG","json":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG.json","graph_json":"https://pith.science/api/pith-number/U3GUI3TCSG2XAAI5INHNH3ZBXG/graph.json","events_json":"https://pith.science/api/pith-number/U3GUI3TCSG2XAAI5INHNH3ZBXG/events.json","paper":"https://pith.science/paper/U3GUI3TC"},"agent_actions":{"view_html":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG","download_json":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG.json","view_paper":"https://pith.science/paper/U3GUI3TC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05751&json=true","fetch_graph":"https://pith.science/api/pith-number/U3GUI3TCSG2XAAI5INHNH3ZBXG/graph.json","fetch_events":"https://pith.science/api/pith-number/U3GUI3TCSG2XAAI5INHNH3ZBXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG/action/storage_attestation","attest_author":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG/action/author_attestation","sign_citation":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG/action/citation_signature","submit_replication":"https://pith.science/pith/U3GUI3TCSG2XAAI5INHNH3ZBXG/action/replication_record"}},"created_at":"2026-05-18T00:13:04.636253+00:00","updated_at":"2026-05-18T00:13:04.636253+00:00"}