{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7MOJFQSGUZS5INDMRIMD43S4PZ","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":"395d1d64461ca27651f3eb39d2397ae281d19e741d0bb7822834e5a3d1c1caf8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T10:37:26Z","title_canon_sha256":"3b94ae56d4d125c07275acb006ed073e930d437d8098530ccef0361860b56d08"},"schema_version":"1.0","source":{"id":"2508.06924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06924","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06924v1","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06924","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"pith_short_12","alias_value":"7MOJFQSGUZS5","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"pith_short_16","alias_value":"7MOJFQSGUZS5INDM","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"pith_short_8","alias_value":"7MOJFQSG","created_at":"2026-07-05T11:51:37Z"}],"graph_snapshots":[{"event_id":"sha256:00449c8e4a6880ac311fa64191e411ab22363809faa15e2b5c0b9d81c3142845","target":"graph","created_at":"2026-07-05T11:51:37Z","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/2508.06924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models. We adapt the Group Relative Policy Optimization (GRPO) algorithm to refine the vanilla autoregressive models' outputs by carefully designed reward functions that evaluate generated images across multiple quality dimensions, including perceptual quality, realism, and semantic fidelity. We conduct comprehensive experiments on both class-conditional (i.e., class-to-image) and text-conditio","authors_text":"Fuzheng Zhang, Guorui Zhou, Jingyuan Zhang, Qi Wang, Shihao Yuan, Wangmeng Zuo, Yahui Liu, Yang Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T10:37:26Z","title":"AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06924","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":"sha256:4630db1f387e507dc8b6950705a1746b7d5f454cfb6515f9c826f78cb19b92dc","target":"record","created_at":"2026-07-05T11:51:37Z","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":"395d1d64461ca27651f3eb39d2397ae281d19e741d0bb7822834e5a3d1c1caf8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T10:37:26Z","title_canon_sha256":"3b94ae56d4d125c07275acb006ed073e930d437d8098530ccef0361860b56d08"},"schema_version":"1.0","source":{"id":"2508.06924","kind":"arxiv","version":1}},"canonical_sha256":"fb1c92c246a665d4346c8a183e6e5c7e7f0a8d0998d49fe359c42a8e658258af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb1c92c246a665d4346c8a183e6e5c7e7f0a8d0998d49fe359c42a8e658258af","first_computed_at":"2026-07-05T11:51:37.701734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:37.701734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZiUdJZBC9lwnGTibQBCRblJY1Re86l5RS/LECyGA8jrZ2eH+1dfDUKL9Zk6BQT08GHin27/Z52Nt1WrTMoIIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:37.702222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4630db1f387e507dc8b6950705a1746b7d5f454cfb6515f9c826f78cb19b92dc","sha256:00449c8e4a6880ac311fa64191e411ab22363809faa15e2b5c0b9d81c3142845"],"state_sha256":"3d5e5a27cb40c649ef9b99d2580c36ee4eee9bcec82469f4426b06f84953e447"}