{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CG76JTO7KIOWE7L4XI5MMOWC76","short_pith_number":"pith:CG76JTO7","canonical_record":{"source":{"id":"2505.17017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"62e56fa00ca118add57fbf09fa74effb61fad663d0963aab9fd8f552dd69db61","abstract_canon_sha256":"0f58350da6ad3065e35b14fe08fd91f4ee1aea10f409b5debe3cb8e387232275"},"schema_version":"1.0"},"canonical_sha256":"11bfe4cddf521d627d7cba3ac63ac2ffa9b4de95176707ad25c2c9dbcd13831f","source":{"kind":"arxiv","id":"2505.17017","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17017","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17017v2","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17017","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"CG76JTO7KIOW","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"CG76JTO7KIOWE7L4","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"CG76JTO7","created_at":"2026-07-05T11:19:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CG76JTO7KIOWE7L4XI5MMOWC76","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:49Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"62e56fa00ca118add57fbf09fa74effb61fad663d0963aab9fd8f552dd69db61","abstract_canon_sha256":"0f58350da6ad3065e35b14fe08fd91f4ee1aea10f409b5debe3cb8e387232275"},"schema_version":"1.0"},"canonical_sha256":"11bfe4cddf521d627d7cba3ac63ac2ffa9b4de95176707ad25c2c9dbcd13831f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:07.430600Z","signature_b64":"hOCyJMg5HHVPa18KwUl7p51LCCI59m9l1GqoOGg/YKsorNSMhjf/Vss5kgQMCJh6quBjspqfFY/xyBIswsy+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11bfe4cddf521d627d7cba3ac63ac2ffa9b4de95176707ad25c2c9dbcd13831f","last_reissued_at":"2026-07-05T11:19:07.430106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:07.430106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17017","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KvShAwMMwhjQN6lwNP3ZoSElb+VEV9rgNdcozjRbpONvyvNAjUK5kmaI8ma0ZozhJxZV8/7l1VIjFN4Iz25eCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:53:33.394010Z"},"content_sha256":"0de256fc5777de9c25bc952f2812707dccea52697ba0f95e4ecb02d6cc0206fa","schema_version":"1.0","event_id":"sha256:0de256fc5777de9c25bc952f2812707dccea52697ba0f95e4ecb02d6cc0206fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CG76JTO7KIOWE7L4XI5MMOWC76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengzhuo Tong, Hongsheng Li, Pheng-Ann Heng, Renrui Zhang, Wenyu Shan, Xinyu Wei, Zhenghao Xing, Ziyu Guo","submitted_at":"2025-05-22T17:59:49Z","abstract_excerpt":"Recent advancements underscore the significant role of Reinforcement Learning (RL) in enhancing the Chain-of-Thought (CoT) reasoning capabilities of large language models (LLMs). Two prominent RL algorithms, Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO), are central to these developments, showcasing different pros and cons. Autoregressive image generation, also interpretable as a sequential CoT reasoning process, presents unique challenges distinct from LLM-based CoT reasoning. These encompass ensuring text-image consistency, improving image aesthetic quali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17017","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/2505.17017/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ByM9qce+pzep8vdmZoa3qwdtSSawnnDljh24Vv04HiRaqbdF8i7jnKt62eL300PqIZ6dAtskMPcp2s3qAlA7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:53:33.395325Z"},"content_sha256":"5b121a503a1cf9ef0f6cd8f506e395ff5e34e487246c8a4a50f632bed3efb929","schema_version":"1.0","event_id":"sha256:5b121a503a1cf9ef0f6cd8f506e395ff5e34e487246c8a4a50f632bed3efb929"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CG76JTO7KIOWE7L4XI5MMOWC76/bundle.json","state_url":"https://pith.science/pith/CG76JTO7KIOWE7L4XI5MMOWC76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CG76JTO7KIOWE7L4XI5MMOWC76/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T18:53:33Z","links":{"resolver":"https://pith.science/pith/CG76JTO7KIOWE7L4XI5MMOWC76","bundle":"https://pith.science/pith/CG76JTO7KIOWE7L4XI5MMOWC76/bundle.json","state":"https://pith.science/pith/CG76JTO7KIOWE7L4XI5MMOWC76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CG76JTO7KIOWE7L4XI5MMOWC76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CG76JTO7KIOWE7L4XI5MMOWC76","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":"0f58350da6ad3065e35b14fe08fd91f4ee1aea10f409b5debe3cb8e387232275","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:49Z","title_canon_sha256":"62e56fa00ca118add57fbf09fa74effb61fad663d0963aab9fd8f552dd69db61"},"schema_version":"1.0","source":{"id":"2505.17017","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17017","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17017v2","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17017","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"CG76JTO7KIOW","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"CG76JTO7KIOWE7L4","created_at":"2026-07-05T11:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"CG76JTO7","created_at":"2026-07-05T11:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:5b121a503a1cf9ef0f6cd8f506e395ff5e34e487246c8a4a50f632bed3efb929","target":"graph","created_at":"2026-07-05T11:19:07Z","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/2505.17017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements underscore the significant role of Reinforcement Learning (RL) in enhancing the Chain-of-Thought (CoT) reasoning capabilities of large language models (LLMs). Two prominent RL algorithms, Direct Preference Optimization (DPO) and Group Relative Policy Optimization (GRPO), are central to these developments, showcasing different pros and cons. Autoregressive image generation, also interpretable as a sequential CoT reasoning process, presents unique challenges distinct from LLM-based CoT reasoning. These encompass ensuring text-image consistency, improving image aesthetic quali","authors_text":"Chengzhuo Tong, Hongsheng Li, Pheng-Ann Heng, Renrui Zhang, Wenyu Shan, Xinyu Wei, Zhenghao Xing, Ziyu Guo","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:49Z","title":"Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17017","kind":"arxiv","version":2},"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":"sha256:0de256fc5777de9c25bc952f2812707dccea52697ba0f95e4ecb02d6cc0206fa","target":"record","created_at":"2026-07-05T11:19:07Z","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":"0f58350da6ad3065e35b14fe08fd91f4ee1aea10f409b5debe3cb8e387232275","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:49Z","title_canon_sha256":"62e56fa00ca118add57fbf09fa74effb61fad663d0963aab9fd8f552dd69db61"},"schema_version":"1.0","source":{"id":"2505.17017","kind":"arxiv","version":2}},"canonical_sha256":"11bfe4cddf521d627d7cba3ac63ac2ffa9b4de95176707ad25c2c9dbcd13831f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11bfe4cddf521d627d7cba3ac63ac2ffa9b4de95176707ad25c2c9dbcd13831f","first_computed_at":"2026-07-05T11:19:07.430106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:07.430106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hOCyJMg5HHVPa18KwUl7p51LCCI59m9l1GqoOGg/YKsorNSMhjf/Vss5kgQMCJh6quBjspqfFY/xyBIswsy+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:07.430600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17017","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0de256fc5777de9c25bc952f2812707dccea52697ba0f95e4ecb02d6cc0206fa","sha256:5b121a503a1cf9ef0f6cd8f506e395ff5e34e487246c8a4a50f632bed3efb929"],"state_sha256":"376ea22f496f7e413e19291fa9636095d524b521f4b1872498061c23af462ae7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qHyXF4Bqd00DrsKfVaZNw1906tuHJZMcPFxRk2cSCulbeedy1g9FU6Pt2yebR6UpAFH5clG8Gz2EDT7r4bomBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:53:33.402492Z","bundle_sha256":"bffc4da3eef04416a82c030647e3037b39dd35e824d1fd48c1284121bbecfbd3"}}