{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VEERUTWCA4Z4K33VLCDB7NY7GY","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":"ae069c5195611386489e63ec3cc7c1d6a488bb43e532a832085b9f8ec2d65096","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T06:20:12Z","title_canon_sha256":"8eaf36d6d83bc2ddf08aad683416a674fdfe3056f055c1eaac2db05dda3d807b"},"schema_version":"1.0","source":{"id":"2606.09076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09076","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09076v1","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09076","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"VEERUTWCA4Z4","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"VEERUTWCA4Z4K33V","created_at":"2026-06-09T02:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"VEERUTWC","created_at":"2026-06-09T02:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:f38aec12e7bf43f25bc113cccddc52333d8f57418344d028d66f042762f502ee","target":"graph","created_at":"2026-06-09T02:07:57Z","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/2606.09076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models are central to text-to-image post-training, but visual preference is subjective and better represented as a distribution over rubric scores than as a deterministic scalar. Existing scalar, score-token, and pairwise reward models over-compress uncertainty and fine-grained score differences, while reasoning-based generative rewards provide stronger judgments but are costly to deploy and difficult to use as direct optimization signals. We propose Z-Reward, a teacher-student reward modeling framework that decouples reasoning-heavy judgment from efficient reward deployment. The teache","authors_text":"Aiming Hao, Chunle Guo, Dengyang Jiang, Huanqia Cai, Ming-Ming Cheng, Peng Gao, Steven C.H. Hoi, Xin Jin, Yuming Jiang, Zechao Zhan, Zhen Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T06:20:12Z","title":"Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09076","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":"sha256:55a1f957807439f0b22096f7cf31a1d1ff1fc16f58afcb60a19a0cf5f8b9cb11","target":"record","created_at":"2026-06-09T02:07:57Z","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":"ae069c5195611386489e63ec3cc7c1d6a488bb43e532a832085b9f8ec2d65096","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T06:20:12Z","title_canon_sha256":"8eaf36d6d83bc2ddf08aad683416a674fdfe3056f055c1eaac2db05dda3d807b"},"schema_version":"1.0","source":{"id":"2606.09076","kind":"arxiv","version":1}},"canonical_sha256":"a9091a4ec20733c56f7558861fb71f3616f5cf6eed5971110b4f3e03e9454985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9091a4ec20733c56f7558861fb71f3616f5cf6eed5971110b4f3e03e9454985","first_computed_at":"2026-06-09T02:07:57.430141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:57.430141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOUHJbRDW4ukotdVcrhBUfkc7LHvu6Lo+L8YXp0sMJYebuSae0q14RuhPZqjywc3g3jqpE3lzPnig/ABTUgaAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:57.431054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55a1f957807439f0b22096f7cf31a1d1ff1fc16f58afcb60a19a0cf5f8b9cb11","sha256:f38aec12e7bf43f25bc113cccddc52333d8f57418344d028d66f042762f502ee"],"state_sha256":"431e3cc554c4d69f4df09a5d8bcb8498658365c7af1e1b83d727235d24ae0248"}