{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JBUWOOUAVABPVIYMQYAFGN2BOA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e0d0934c860b4e698e11a1d2da3b06125154b1d694e48bfbe2f26c24c9ac1495","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-15T17:59:46Z","title_canon_sha256":"7cd75869ff0274ca10078f650e5626a2632944b32e3804cb75ce15b8870e4833"},"schema_version":"1.0","source":{"id":"2504.11455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11455","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11455v1","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11455","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"JBUWOOUAVABP","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_16","alias_value":"JBUWOOUAVABPVIYM","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_8","alias_value":"JBUWOOUA","created_at":"2026-07-05T10:49:34Z"}],"graph_snapshots":[{"event_id":"sha256:09f584e8bd5a00abe1eb7ad89760fd65eab82a9643ac3b8111e996efa66267cf","target":"graph","created_at":"2026-07-05T10:49:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.11455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B parameters, our model can generate 1024x1024 resolution images with high fidelity, and achieve competitive results on challenging text-to-image benchmarks, e.g., 0.59 on GenEval and 79.66 on DPG; 2) both supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) training could lead to significant improvements on generation aesthectics and prompt alig","authors_text":"Junke Wang, Weilin Huang, Xinyu Zhang, Xun Wang, Yu-Gang Jiang, Zhi Tian, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-15T17:59:46Z","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11455","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e80c75a7ec60c36c2a89ab7bd86f0bb894e0b6228352f2914910b3882f24113d","target":"record","created_at":"2026-07-05T10:49:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e0d0934c860b4e698e11a1d2da3b06125154b1d694e48bfbe2f26c24c9ac1495","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-15T17:59:46Z","title_canon_sha256":"7cd75869ff0274ca10078f650e5626a2632944b32e3804cb75ce15b8870e4833"},"schema_version":"1.0","source":{"id":"2504.11455","kind":"arxiv","version":1}},"canonical_sha256":"4869673a80a802faa30c860053374170261a6e4b192f59f66ac9e363304a2389","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4869673a80a802faa30c860053374170261a6e4b192f59f66ac9e363304a2389","first_computed_at":"2026-07-05T10:49:34.178708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:34.178708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zQxNstesQS98u4QYRkiDjtelbBlX1+8MOzf336qKQQm3+2XbeV7iJFAVgAmtfeF/Vi3O0J47+Fu1Xsp29PjGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:34.179177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e80c75a7ec60c36c2a89ab7bd86f0bb894e0b6228352f2914910b3882f24113d","sha256:09f584e8bd5a00abe1eb7ad89760fd65eab82a9643ac3b8111e996efa66267cf"],"state_sha256":"bbbdd1f51908cab9921f8e7c66efe54ad797ba4d853753e7f0746bc62aef73a1"}