{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENEAJLAXLQUTGVK3BMRYHE7KO5","short_pith_number":"pith:ENEAJLAX","schema_version":"1.0","canonical_sha256":"234804ac175c2933555b0b238393ea77424389f78c55817c66dee42c30c58818","source":{"kind":"arxiv","id":"2509.12046","version":2},"attestation_state":"computed","paper":{"title":"Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baolu Li, Dong Li, Dong Zhou, Emad Barsoum, Huchuan Lu, Jianbin Zhao, Mengmeng Ge, Qinghe Wang, Takashi Isobe, Tong Shen, Xiaomin Li, Xu Jia, Yunzhi Zhuge, Zirui Zheng","submitted_at":"2025-09-15T15:27:29Z","abstract_excerpt":"Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature entanglement. We present \\textbf{S}tructured \\textbf{M}asking for \\textbf{AR}-based \\textbf{L}ayout-to-\\textbf{I}mage (SMARLI), a novel framework that effectively integrates spatial layout constraints into the AR generation process. To equip AR models with layout control, a structured masking strategy is applied to the attention computation to govern the int"},"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":"2509.12046","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-15T15:27:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5edfd2348035ab57876561c7668687a449c9a0f97baca8357fc37202ff445b0a","abstract_canon_sha256":"1235f685c93576352c11e928fa55ff64ab7fbe57e5608eccdc83c02141594770"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:41.423162Z","signature_b64":"X7nT6OyukKOahxxUXa4v5pXDAWsIJnjRC7vcLtBNocR63eeLoY/YQm/xuoQ0IfJu049myJgtFZtAwQEZJrYxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"234804ac175c2933555b0b238393ea77424389f78c55817c66dee42c30c58818","last_reissued_at":"2026-07-01T01:17:41.422658Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:41.422658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baolu Li, Dong Li, Dong Zhou, Emad Barsoum, Huchuan Lu, Jianbin Zhao, Mengmeng Ge, Qinghe Wang, Takashi Isobe, Tong Shen, Xiaomin Li, Xu Jia, Yunzhi Zhuge, Zirui Zheng","submitted_at":"2025-09-15T15:27:29Z","abstract_excerpt":"Although autoregressive (AR) models have demonstrated remarkable success in image generation, extending these models to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature entanglement. We present \\textbf{S}tructured \\textbf{M}asking for \\textbf{AR}-based \\textbf{L}ayout-to-\\textbf{I}mage (SMARLI), a novel framework that effectively integrates spatial layout constraints into the AR generation process. To equip AR models with layout control, a structured masking strategy is applied to the attention computation to govern the int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.12046","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/2509.12046/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":"2509.12046","created_at":"2026-07-01T01:17:41.422719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.12046v2","created_at":"2026-07-01T01:17:41.422719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.12046","created_at":"2026-07-01T01:17:41.422719+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENEAJLAXLQUT","created_at":"2026-07-01T01:17:41.422719+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENEAJLAXLQUTGVK3","created_at":"2026-07-01T01:17:41.422719+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENEAJLAX","created_at":"2026-07-01T01:17:41.422719+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/ENEAJLAXLQUTGVK3BMRYHE7KO5","json":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5.json","graph_json":"https://pith.science/api/pith-number/ENEAJLAXLQUTGVK3BMRYHE7KO5/graph.json","events_json":"https://pith.science/api/pith-number/ENEAJLAXLQUTGVK3BMRYHE7KO5/events.json","paper":"https://pith.science/paper/ENEAJLAX"},"agent_actions":{"view_html":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5","download_json":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5.json","view_paper":"https://pith.science/paper/ENEAJLAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.12046&json=true","fetch_graph":"https://pith.science/api/pith-number/ENEAJLAXLQUTGVK3BMRYHE7KO5/graph.json","fetch_events":"https://pith.science/api/pith-number/ENEAJLAXLQUTGVK3BMRYHE7KO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5/action/storage_attestation","attest_author":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5/action/author_attestation","sign_citation":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5/action/citation_signature","submit_replication":"https://pith.science/pith/ENEAJLAXLQUTGVK3BMRYHE7KO5/action/replication_record"}},"created_at":"2026-07-01T01:17:41.422719+00:00","updated_at":"2026-07-01T01:17:41.422719+00:00"}