{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TXFCXWZ44FPU7CMNUG2GHD4FU2","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":"6dddb52b902ace7af4dde4df821fe7d9c19356e8a62d2baef3ec7f19d0312f4f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-11T18:57:29Z","title_canon_sha256":"7a129d967061dcf88553362ca290c5c5bd78c1650e6afbabe39c8c2ff5b63559"},"schema_version":"1.0","source":{"id":"2602.11146","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.11146","created_at":"2026-05-25T02:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"2602.11146v2","created_at":"2026-05-25T02:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11146","created_at":"2026-05-25T02:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"TXFCXWZ44FPU","created_at":"2026-05-25T02:02:13Z"},{"alias_kind":"pith_short_16","alias_value":"TXFCXWZ44FPU7CMN","created_at":"2026-05-25T02:02:13Z"},{"alias_kind":"pith_short_8","alias_value":"TXFCXWZ4","created_at":"2026-05-25T02:02:13Z"}],"graph_snapshots":[{"event_id":"sha256:5d200b153c54c09053c5b4be1ded545df1434aef60f28c22cb41a89064aebe7e","target":"graph","created_at":"2026-05-25T02:02:13Z","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/2602.11146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider, leveraging their rich multimodal priors to guide alignment. However, their computation and memory cost can be substantial, and optimizing a latent diffusion generator through a pixel-space reward introduces a domain mismatch that complicates alignment. In this paper, we propose DiNa-LRM, a diffusion-native latent reward model that formulates preference learning di","authors_text":"Bo Yang, Didan Deng, Gongye Liu, Han Gao, Hongbo Fu, Kaihao Zhang, Lei Ke, Wenhan Luo, Yida Zhi, Yongxiang Huang, Zhizhou Zhong","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-11T18:57:29Z","title":"Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11146","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:db1d9020a82d13c0588c1b515b00aa7b8f6aaff1f67e38d059020402caa3224b","target":"record","created_at":"2026-05-25T02:02:13Z","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":"6dddb52b902ace7af4dde4df821fe7d9c19356e8a62d2baef3ec7f19d0312f4f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-11T18:57:29Z","title_canon_sha256":"7a129d967061dcf88553362ca290c5c5bd78c1650e6afbabe39c8c2ff5b63559"},"schema_version":"1.0","source":{"id":"2602.11146","kind":"arxiv","version":2}},"canonical_sha256":"9dca2bdb3ce15f4f898da1b4638f85a68ddfaaecd9a41cfed266e4e466f36ffa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dca2bdb3ce15f4f898da1b4638f85a68ddfaaecd9a41cfed266e4e466f36ffa","first_computed_at":"2026-05-25T02:02:13.327522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:13.327522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GQyFf9zZ5sOcUbY+eZj1rWnzj2QK/rQDEhTPeLP63iKMCXvsfTmHBGMpgIIlnPBq76j+HCb08rT3Hy0szCv+Dg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:13.328283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.11146","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db1d9020a82d13c0588c1b515b00aa7b8f6aaff1f67e38d059020402caa3224b","sha256:5d200b153c54c09053c5b4be1ded545df1434aef60f28c22cb41a89064aebe7e"],"state_sha256":"3613da8e76da53a3b8c7ce0599f81982abb5efb203299ef27928b26f2e435f30"}