{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VSKFQMK2KU3HL6XYRDM5DVNDE6","short_pith_number":"pith:VSKFQMK2","canonical_record":{"source":{"id":"2509.08826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"23bf35f51d85c54d48dc9f5fb45f95c5eb5a7d1d6fbd5dc0a6099547595775cf","abstract_canon_sha256":"6e3e33f9973f5b6468492aa4e04534c27ebcfabb35a2c4ad77dce6f41fcc3a93"},"schema_version":"1.0"},"canonical_sha256":"ac9458315a553675faf888d9d1d5a327b400e618fd4f0e6060372923ac4f4ee9","source":{"kind":"arxiv","id":"2509.08826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08826","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08826v1","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08826","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"pith_short_12","alias_value":"VSKFQMK2KU3H","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"pith_short_16","alias_value":"VSKFQMK2KU3HL6XY","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"pith_short_8","alias_value":"VSKFQMK2","created_at":"2026-07-05T12:08:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VSKFQMK2KU3HL6XYRDM5DVNDE6","target":"record","payload":{"canonical_record":{"source":{"id":"2509.08826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"23bf35f51d85c54d48dc9f5fb45f95c5eb5a7d1d6fbd5dc0a6099547595775cf","abstract_canon_sha256":"6e3e33f9973f5b6468492aa4e04534c27ebcfabb35a2c4ad77dce6f41fcc3a93"},"schema_version":"1.0"},"canonical_sha256":"ac9458315a553675faf888d9d1d5a327b400e618fd4f0e6060372923ac4f4ee9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:37.150600Z","signature_b64":"CqMhiODIutv3q0IiZQH4ORN1YTNSPbSKVdZnlN7iWCLXR7TeQJOxixn8Mxc1cAQbkuj8QRSqeH9jSe07CsaiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac9458315a553675faf888d9d1d5a327b400e618fd4f0e6060372923ac4f4ee9","last_reissued_at":"2026-07-05T12:08:37.150040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:37.150040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.08826","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:08:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8MD5NY+Eu0thF1Wi6zFQhnVXKhpVT85PZzRLG2JKVUqKn4TP608T53cIUlp4oE5VFPX0FKKxFN6ybzCECWmTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:35:34.145522Z"},"content_sha256":"1c0d6ce640cf836fd384eb75733e5227e7573af5f21d9ea69dd1d864d496b442","schema_version":"1.0","event_id":"sha256:1c0d6ce640cf836fd384eb75733e5227e7573af5f21d9ea69dd1d864d496b442"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VSKFQMK2KU3HL6XYRDM5DVNDE6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RewardDance: Reward Scaling in Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanzhong Guo, Jie Liu, Jie Wu, Liang Li, Ming Li, Weilin Huang, Wei Liu, Xiaoxia Hou, Yan Zeng, Yu Gao, Zeyue Xue, Zilyu Ye","submitted_at":"2025-09-10T17:59:31Z","abstract_excerpt":"Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critically, the RLHF optimization process is plagued by Reward Hacking issue, where models exploit flaws in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08826","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/2509.08826/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":"2026-07-05T12:08:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSardCeb6/5JzGNArT34WmnIgBCy+nIyJ5475bxsOJC4nUcHwCZC/3qnmY1mAHncGhX/XHGr1E1dGXc8uYoXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:35:34.146519Z"},"content_sha256":"6ac599b3bc0cdd230c6394b22bac93aaadd93e0c9959936eb0dca240e5f8d922","schema_version":"1.0","event_id":"sha256:6ac599b3bc0cdd230c6394b22bac93aaadd93e0c9959936eb0dca240e5f8d922"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6/bundle.json","state_url":"https://pith.science/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6/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":"2026-08-05T14:35:34Z","links":{"resolver":"https://pith.science/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6","bundle":"https://pith.science/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6/bundle.json","state":"https://pith.science/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSKFQMK2KU3HL6XYRDM5DVNDE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VSKFQMK2KU3HL6XYRDM5DVNDE6","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":"6e3e33f9973f5b6468492aa4e04534c27ebcfabb35a2c4ad77dce6f41fcc3a93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:59:31Z","title_canon_sha256":"23bf35f51d85c54d48dc9f5fb45f95c5eb5a7d1d6fbd5dc0a6099547595775cf"},"schema_version":"1.0","source":{"id":"2509.08826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08826","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08826v1","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08826","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"pith_short_12","alias_value":"VSKFQMK2KU3H","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"pith_short_16","alias_value":"VSKFQMK2KU3HL6XY","created_at":"2026-07-05T12:08:37Z"},{"alias_kind":"pith_short_8","alias_value":"VSKFQMK2","created_at":"2026-07-05T12:08:37Z"}],"graph_snapshots":[{"event_id":"sha256:6ac599b3bc0cdd230c6394b22bac93aaadd93e0c9959936eb0dca240e5f8d922","target":"graph","created_at":"2026-07-05T12:08:37Z","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/2509.08826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward Models (RMs) are critical for improving generation models via Reinforcement Learning (RL), yet the RM scaling paradigm in visual generation remains largely unexplored. It primarily due to fundamental limitations in existing approaches: CLIP-based RMs suffer from architectural and input modality constraints, while prevalent Bradley-Terry losses are fundamentally misaligned with the next-token prediction mechanism of Vision-Language Models (VLMs), hindering effective scaling. More critically, the RLHF optimization process is plagued by Reward Hacking issue, where models exploit flaws in t","authors_text":"Hanzhong Guo, Jie Liu, Jie Wu, Liang Li, Ming Li, Weilin Huang, Wei Liu, Xiaoxia Hou, Yan Zeng, Yu Gao, Zeyue Xue, Zilyu Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:59:31Z","title":"RewardDance: Reward Scaling in Visual Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08826","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":"sha256:1c0d6ce640cf836fd384eb75733e5227e7573af5f21d9ea69dd1d864d496b442","target":"record","created_at":"2026-07-05T12:08:37Z","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":"6e3e33f9973f5b6468492aa4e04534c27ebcfabb35a2c4ad77dce6f41fcc3a93","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:59:31Z","title_canon_sha256":"23bf35f51d85c54d48dc9f5fb45f95c5eb5a7d1d6fbd5dc0a6099547595775cf"},"schema_version":"1.0","source":{"id":"2509.08826","kind":"arxiv","version":1}},"canonical_sha256":"ac9458315a553675faf888d9d1d5a327b400e618fd4f0e6060372923ac4f4ee9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac9458315a553675faf888d9d1d5a327b400e618fd4f0e6060372923ac4f4ee9","first_computed_at":"2026-07-05T12:08:37.150040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:37.150040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CqMhiODIutv3q0IiZQH4ORN1YTNSPbSKVdZnlN7iWCLXR7TeQJOxixn8Mxc1cAQbkuj8QRSqeH9jSe07CsaiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:37.150600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c0d6ce640cf836fd384eb75733e5227e7573af5f21d9ea69dd1d864d496b442","sha256:6ac599b3bc0cdd230c6394b22bac93aaadd93e0c9959936eb0dca240e5f8d922"],"state_sha256":"da53b19b05c23b52e85332a0b444517bc7ca62af23649c0617a879c238de9857"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gv8zpBYncL3PMc5pq+w9T1peBLtUK5cdNe5EOsKj5Oa50QjAndnRTzSVsLP7mKdXxaTeRuI3fx1nJbnRgOa0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:35:34.181850Z","bundle_sha256":"f272dc94c7f16fa094ec40ea685f83ffd6a92b8ff4f5e89abf701e4baf130c5a"}}