{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7TDFPHWUAJRS3ZLDTZ2NM37HRN","short_pith_number":"pith:7TDFPHWU","schema_version":"1.0","canonical_sha256":"fcc6579ed402632de5639e74d66fe78b474877b509e18a17864eef9b0b4c11f5","source":{"kind":"arxiv","id":"2606.09156","version":1},"attestation_state":"computed","paper":{"title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junke Wang, Peize Sun, Qiushan Guo, Weilin Huang, Xun Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2026-06-08T07:47:53Z","abstract_excerpt":"Autoregressive (AR) models have demonstrated strong potential in visual generation, offering superior performance with simple architectures and optimization objectives. However, existing methods are typically limited to single-modality conditions, e.g., text, restricting their applicability in real-world scenarios that demand image synthesis from diverse controls. In this work, we present OmniGen-AR, a unified autoregressive framework for Any-to-Image generation. By discretizing various visual conditions through a shared visual tokenizer and text prompts with a text tokenizer, OmniGen-AR suppo"},"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":"2606.09156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T07:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"f564165a8ade219461a8c4aaa4c5a7443d1e81afdf0ae67d63dc944c87c6e9da","abstract_canon_sha256":"c4a88271d75649c22fd68146ad55ad8079bb37996bb592470cd207c079c16a63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:03.555184Z","signature_b64":"+oL4yU2MwPrf72vg2oBfdtq7whBUPGx9sB3lfEdRxRpspZmodnqiEm1ERbAgL4S+8L1qWtlD+3eBmlbPEar9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcc6579ed402632de5639e74d66fe78b474877b509e18a17864eef9b0b4c11f5","last_reissued_at":"2026-06-09T02:08:03.554356Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:03.554356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junke Wang, Peize Sun, Qiushan Guo, Weilin Huang, Xun Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2026-06-08T07:47:53Z","abstract_excerpt":"Autoregressive (AR) models have demonstrated strong potential in visual generation, offering superior performance with simple architectures and optimization objectives. However, existing methods are typically limited to single-modality conditions, e.g., text, restricting their applicability in real-world scenarios that demand image synthesis from diverse controls. In this work, we present OmniGen-AR, a unified autoregressive framework for Any-to-Image generation. By discretizing various visual conditions through a shared visual tokenizer and text prompts with a text tokenizer, OmniGen-AR suppo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09156","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/2606.09156/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":"2606.09156","created_at":"2026-06-09T02:08:03.554492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09156v1","created_at":"2026-06-09T02:08:03.554492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09156","created_at":"2026-06-09T02:08:03.554492+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TDFPHWUAJRS","created_at":"2026-06-09T02:08:03.554492+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TDFPHWUAJRS3ZLD","created_at":"2026-06-09T02:08:03.554492+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TDFPHWU","created_at":"2026-06-09T02:08:03.554492+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/7TDFPHWUAJRS3ZLDTZ2NM37HRN","json":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN.json","graph_json":"https://pith.science/api/pith-number/7TDFPHWUAJRS3ZLDTZ2NM37HRN/graph.json","events_json":"https://pith.science/api/pith-number/7TDFPHWUAJRS3ZLDTZ2NM37HRN/events.json","paper":"https://pith.science/paper/7TDFPHWU"},"agent_actions":{"view_html":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN","download_json":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN.json","view_paper":"https://pith.science/paper/7TDFPHWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09156&json=true","fetch_graph":"https://pith.science/api/pith-number/7TDFPHWUAJRS3ZLDTZ2NM37HRN/graph.json","fetch_events":"https://pith.science/api/pith-number/7TDFPHWUAJRS3ZLDTZ2NM37HRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN/action/storage_attestation","attest_author":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN/action/author_attestation","sign_citation":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN/action/citation_signature","submit_replication":"https://pith.science/pith/7TDFPHWUAJRS3ZLDTZ2NM37HRN/action/replication_record"}},"created_at":"2026-06-09T02:08:03.554492+00:00","updated_at":"2026-06-09T02:08:03.554492+00:00"}