{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7VCN6UPUP37CJP6EV6TJYSV2TL","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":"9fc8b8a93ef61713949c8531576181b99c7d97af3bd48297203ad0fe31878ca1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:55Z","title_canon_sha256":"ab53405f6b98f444ac18d43eb3ad5346eaf42c7907313f67e535f537b51b9afd"},"schema_version":"1.0","source":{"id":"2511.20651","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.20651","created_at":"2026-06-23T03:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2511.20651v2","created_at":"2026-06-23T03:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.20651","created_at":"2026-06-23T03:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"7VCN6UPUP37C","created_at":"2026-06-23T03:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"7VCN6UPUP37CJP6E","created_at":"2026-06-23T03:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"7VCN6UPU","created_at":"2026-06-23T03:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:cfff272ceb6e611cdf82167bedee48e33980705f33de08bccb92cf30a640bc35","target":"graph","created_at":"2026-06-23T03:14:27Z","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/2511.20651/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has recently emerged as a promising approach for aligning text-to-image generative models with human preferences. A key challenge, however, lies in designing effective and interpretable rewards. Existing methods often rely on either composite metrics (e.g., CLIP, OCR, and realism scores) with fixed weights or a single scalar reward distilled from human preference models, which can limit interpretability and flexibility. We propose RubricRL, a simple and general framework for rubric-based reward design that offers greater interpretability, composability, and user con","authors_text":"Chunming Qiao, Dongdong Chen, Junsong Yuan, Xuelu Feng, Yunsheng Li, Zixuan Gao, Ziyu Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:55Z","title":"RubricRL: Simple Generalizable Rewards for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20651","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":"sha256:6cbcdaa38cade8cac00516446e5fa1fbba928c2cd11f00168f7ecc9d2a8b83dd","target":"record","created_at":"2026-06-23T03:14:27Z","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":"9fc8b8a93ef61713949c8531576181b99c7d97af3bd48297203ad0fe31878ca1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:55Z","title_canon_sha256":"ab53405f6b98f444ac18d43eb3ad5346eaf42c7907313f67e535f537b51b9afd"},"schema_version":"1.0","source":{"id":"2511.20651","kind":"arxiv","version":2}},"canonical_sha256":"fd44df51f47efe24bfc4afa69c4aba9af25070ac41d2f9a52980155398ee26c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd44df51f47efe24bfc4afa69c4aba9af25070ac41d2f9a52980155398ee26c9","first_computed_at":"2026-06-23T03:14:27.683579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:27.683579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9b9WKDT5qcmO0dT8fpAg8a7jDTnz6zZ9PTCXt8iwv7jQ4rIK7jrqwHiXopjRCxDE6Rqf2NkLWH3RgB+Xo6myAA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:27.684078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.20651","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cbcdaa38cade8cac00516446e5fa1fbba928c2cd11f00168f7ecc9d2a8b83dd","sha256:cfff272ceb6e611cdf82167bedee48e33980705f33de08bccb92cf30a640bc35"],"state_sha256":"2e887379401132980ae719ae7b1175c638288f594f2ab04c5317d3bb2a28fdb3"}