{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7VCN6UPUP37CJP6EV6TJYSV2TL","short_pith_number":"pith:7VCN6UPU","canonical_record":{"source":{"id":"2511.20651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"ab53405f6b98f444ac18d43eb3ad5346eaf42c7907313f67e535f537b51b9afd","abstract_canon_sha256":"9fc8b8a93ef61713949c8531576181b99c7d97af3bd48297203ad0fe31878ca1"},"schema_version":"1.0"},"canonical_sha256":"fd44df51f47efe24bfc4afa69c4aba9af25070ac41d2f9a52980155398ee26c9","source":{"kind":"arxiv","id":"2511.20651","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7VCN6UPUP37CJP6EV6TJYSV2TL","target":"record","payload":{"canonical_record":{"source":{"id":"2511.20651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T18:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"ab53405f6b98f444ac18d43eb3ad5346eaf42c7907313f67e535f537b51b9afd","abstract_canon_sha256":"9fc8b8a93ef61713949c8531576181b99c7d97af3bd48297203ad0fe31878ca1"},"schema_version":"1.0"},"canonical_sha256":"fd44df51f47efe24bfc4afa69c4aba9af25070ac41d2f9a52980155398ee26c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:27.684078Z","signature_b64":"9b9WKDT5qcmO0dT8fpAg8a7jDTnz6zZ9PTCXt8iwv7jQ4rIK7jrqwHiXopjRCxDE6Rqf2NkLWH3RgB+Xo6myAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd44df51f47efe24bfc4afa69c4aba9af25070ac41d2f9a52980155398ee26c9","last_reissued_at":"2026-06-23T03:14:27.683579Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:27.683579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.20651","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":"2026-06-23T03:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3vrHA0XDsOhJprT5pGdkhOK/jCinqtIQdB/C2Om2IPVPocTQqJgelVSh5wgV501R7LWvsTPiN2jKKSJTXFfVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:59:53.178669Z"},"content_sha256":"6cbcdaa38cade8cac00516446e5fa1fbba928c2cd11f00168f7ecc9d2a8b83dd","schema_version":"1.0","event_id":"sha256:6cbcdaa38cade8cac00516446e5fa1fbba928c2cd11f00168f7ecc9d2a8b83dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7VCN6UPUP37CJP6EV6TJYSV2TL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RubricRL: Simple Generalizable Rewards for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunming Qiao, Dongdong Chen, Junsong Yuan, Xuelu Feng, Yunsheng Li, Zixuan Gao, Ziyu Wan","submitted_at":"2025-11-25T18:59:55Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.20651","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/2511.20651/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":"2026-06-23T03:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pY5M4edSsrfZh+D7YirPBK4ERK+LnUQxtF8heRZ2+aHi+aTW8SzpYolb1OyTh0afAyvyaTtCBeeINTNcdOzABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:59:53.179045Z"},"content_sha256":"cfff272ceb6e611cdf82167bedee48e33980705f33de08bccb92cf30a640bc35","schema_version":"1.0","event_id":"sha256:cfff272ceb6e611cdf82167bedee48e33980705f33de08bccb92cf30a640bc35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VCN6UPUP37CJP6EV6TJYSV2TL/bundle.json","state_url":"https://pith.science/pith/7VCN6UPUP37CJP6EV6TJYSV2TL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VCN6UPUP37CJP6EV6TJYSV2TL/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":"2026-06-30T18:59:53Z","links":{"resolver":"https://pith.science/pith/7VCN6UPUP37CJP6EV6TJYSV2TL","bundle":"https://pith.science/pith/7VCN6UPUP37CJP6EV6TJYSV2TL/bundle.json","state":"https://pith.science/pith/7VCN6UPUP37CJP6EV6TJYSV2TL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VCN6UPUP37CJP6EV6TJYSV2TL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrBhlybGoB5Jnkc5JoeIobFItIpyQzlzYiLkJxbz3v0VJA5z8lkTthgaFRUQaZCOCs+ippr4K3M0n6RI/y9bBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T18:59:53.181139Z","bundle_sha256":"cb30577b84be4d07c46f81657c1e012abf2725ce305009631907bec95bf6f585"}}