{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VEERUTWCA4Z4K33VLCDB7NY7GY","short_pith_number":"pith:VEERUTWC","schema_version":"1.0","canonical_sha256":"a9091a4ec20733c56f7558861fb71f3616f5cf6eed5971110b4f3e03e9454985","source":{"kind":"arxiv","id":"2606.09076","version":1},"attestation_state":"computed","paper":{"title":"Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-06-08T06:20:12Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.09076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T06:20:12Z","cross_cats_sorted":[],"title_canon_sha256":"8eaf36d6d83bc2ddf08aad683416a674fdfe3056f055c1eaac2db05dda3d807b","abstract_canon_sha256":"ae069c5195611386489e63ec3cc7c1d6a488bb43e532a832085b9f8ec2d65096"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:57.431054Z","signature_b64":"DOUHJbRDW4ukotdVcrhBUfkc7LHvu6Lo+L8YXp0sMJYebuSae0q14RuhPZqjywc3g3jqpE3lzPnig/ABTUgaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9091a4ec20733c56f7558861fb71f3616f5cf6eed5971110b4f3e03e9454985","last_reissued_at":"2026-06-09T02:07:57.430141Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:57.430141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-06-08T06:20:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09076","kind":"arxiv","version":1},"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/2606.09076/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.09076","created_at":"2026-06-09T02:07:57.430278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09076v1","created_at":"2026-06-09T02:07:57.430278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09076","created_at":"2026-06-09T02:07:57.430278+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEERUTWCA4Z4","created_at":"2026-06-09T02:07:57.430278+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEERUTWCA4Z4K33V","created_at":"2026-06-09T02:07:57.430278+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEERUTWC","created_at":"2026-06-09T02:07:57.430278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY","json":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY.json","graph_json":"https://pith.science/api/pith-number/VEERUTWCA4Z4K33VLCDB7NY7GY/graph.json","events_json":"https://pith.science/api/pith-number/VEERUTWCA4Z4K33VLCDB7NY7GY/events.json","paper":"https://pith.science/paper/VEERUTWC"},"agent_actions":{"view_html":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY","download_json":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY.json","view_paper":"https://pith.science/paper/VEERUTWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09076&json=true","fetch_graph":"https://pith.science/api/pith-number/VEERUTWCA4Z4K33VLCDB7NY7GY/graph.json","fetch_events":"https://pith.science/api/pith-number/VEERUTWCA4Z4K33VLCDB7NY7GY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY/action/storage_attestation","attest_author":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY/action/author_attestation","sign_citation":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY/action/citation_signature","submit_replication":"https://pith.science/pith/VEERUTWCA4Z4K33VLCDB7NY7GY/action/replication_record"}},"created_at":"2026-06-09T02:07:57.430278+00:00","updated_at":"2026-06-09T02:07:57.430278+00:00"}