{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FRTDBCI4QZPET6RI5COCRIHVAA","short_pith_number":"pith:FRTDBCI4","schema_version":"1.0","canonical_sha256":"2c6630891c865e49fa28e89c28a0f500224e6b1ce79d851189c9b9c370ab791b","source":{"kind":"arxiv","id":"2505.12274","version":1},"attestation_state":"computed","paper":{"title":"Context-Aware Autoregressive Models for Multi-Conditional Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhou, Che Jiang, Guoli Jia, Jianjun Li, Yixiao Chen, Zhiyuan Ma","submitted_at":"2025-05-18T07:27:02Z","abstract_excerpt":"Autoregressive transformers have recently shown impressive image generation quality and efficiency on par with state-of-the-art diffusion models. Unlike diffusion architectures, autoregressive models can naturally incorporate arbitrary modalities into a single, unified token sequence--offering a concise solution for multi-conditional image generation tasks. In this work, we propose $\\textbf{ContextAR}$, a flexible and effective framework for multi-conditional image generation. ContextAR embeds diverse conditions (e.g., canny edges, depth maps, poses) directly into the token sequence, preservin"},"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":"2505.12274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-18T07:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"d1deb331b5c5a09ed4892b113a6873dc6de4fe6286eb3adc5218986581941f05","abstract_canon_sha256":"882b98cb16be60c2706e665acba97ff5883b30de779bd8b7f5408d9e94bd6bf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:01.355072Z","signature_b64":"6TgcRwVPr0yGFsJNmuOSf+hTV/Xl7mQkZ5+OhIBrzqjStsBE76hGnIwgfn4fpdSSpgOudYJmXhmvYn7yJkf6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6630891c865e49fa28e89c28a0f500224e6b1ce79d851189c9b9c370ab791b","last_reissued_at":"2026-07-05T11:05:01.354592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:01.354592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Autoregressive Models for Multi-Conditional Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Zhou, Che Jiang, Guoli Jia, Jianjun Li, Yixiao Chen, Zhiyuan Ma","submitted_at":"2025-05-18T07:27:02Z","abstract_excerpt":"Autoregressive transformers have recently shown impressive image generation quality and efficiency on par with state-of-the-art diffusion models. Unlike diffusion architectures, autoregressive models can naturally incorporate arbitrary modalities into a single, unified token sequence--offering a concise solution for multi-conditional image generation tasks. In this work, we propose $\\textbf{ContextAR}$, a flexible and effective framework for multi-conditional image generation. ContextAR embeds diverse conditions (e.g., canny edges, depth maps, poses) directly into the token sequence, preservin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12274","kind":"arxiv","version":1},"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/2505.12274/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":"2505.12274","created_at":"2026-07-05T11:05:01.354651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12274v1","created_at":"2026-07-05T11:05:01.354651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12274","created_at":"2026-07-05T11:05:01.354651+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRTDBCI4QZPE","created_at":"2026-07-05T11:05:01.354651+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRTDBCI4QZPET6RI","created_at":"2026-07-05T11:05:01.354651+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRTDBCI4","created_at":"2026-07-05T11:05:01.354651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12138","citing_title":"Design Your Ad: Personalized Advertising Image and Text Generation with Unified Autoregressive Models","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA","json":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA.json","graph_json":"https://pith.science/api/pith-number/FRTDBCI4QZPET6RI5COCRIHVAA/graph.json","events_json":"https://pith.science/api/pith-number/FRTDBCI4QZPET6RI5COCRIHVAA/events.json","paper":"https://pith.science/paper/FRTDBCI4"},"agent_actions":{"view_html":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA","download_json":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA.json","view_paper":"https://pith.science/paper/FRTDBCI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12274&json=true","fetch_graph":"https://pith.science/api/pith-number/FRTDBCI4QZPET6RI5COCRIHVAA/graph.json","fetch_events":"https://pith.science/api/pith-number/FRTDBCI4QZPET6RI5COCRIHVAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA/action/storage_attestation","attest_author":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA/action/author_attestation","sign_citation":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA/action/citation_signature","submit_replication":"https://pith.science/pith/FRTDBCI4QZPET6RI5COCRIHVAA/action/replication_record"}},"created_at":"2026-07-05T11:05:01.354651+00:00","updated_at":"2026-07-05T11:05:01.354651+00:00"}