{"id":"9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d","title":"EmoReward adapts reward weights for emotional video generation","argument":"The authors of EmoReward argue that fixed rewards can miss emotional intent in generated video, where visual quality, motion quality and text alignment do not provide a uniquely correct target. They propose a self-evolving mechanism that uses reward traces from one training run to adjust how different emotional cues are weighted in the next, without updating the reward models.\n\nThe method plans grounding cues from an emotional prompt, scores video using different signal primitives, and uses Reflective Reward Gating to adjust their contributions for each sample. RewardMemory estimates each primitive’s reliability within an emotional regime from rollout scores and outcomes, then sets bounded multipliers for the next run. The authors report improvements on HunyuanVideo 1.5 across multiple RL algorithms, and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration. These are the paper’s reported experimental results; the abstract does not give their magnitude or evaluation details. The proposal’s central idea is to treat evidence about which cues were useful during training as a basis for calibrating later rewards, rather than relying only on fixed weights.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the arXiv abstract, which gives no numerical improvement sizes or detailed evaluation results. The abstract describes transfer experiments on SD 3.5 and FLUX but does not report their specific outcomes.","speaker":{"name":"Zheng, Mingzhe, Wu, Yue, Tan, Jing, Zou, Chang, Jiang, Dengyang, Tian, Zeyue, He, Xuanhua, Xu, Ryan, Ge, Yunyang, Ji, Sihui, Lin, Yunlong, Pan, Kaihang, Yan, Hongru, Chen, Sixiang, Wang, Dianyi, Zhang, Julian, Kong, Weijie, Li, Changlin, Guo, Lanqing, Zhong, Zhao, Chen, Qifeng, Yang, Harry","roleAtSource":"Article author"},"source":{"title":"EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.06518","publishedAt":"2026-11-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors say existing fixed rewards for visual quality, motion quality and text alignment can poorly capture emotional intent and may invite reward hacking.","excerpt":"Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking","url":"https://arxiv.org/abs/2611.06518","relationship":"Source-stated"},{"text":"EmoReward uses reward traces from a completed training run to adapt multi-reward weights in a subsequent run, without updating reward models.","excerpt":"RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models.","url":"https://arxiv.org/abs/2611.06518","relationship":"Source-stated"},{"text":"The authors report improvements on HunyuanVideo 1.5 and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration.","excerpt":"Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration","url":"https://arxiv.org/abs/2611.06518","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06518","checkedAt":"2026-11-10T01:54:11.445Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How large were the reported improvements, and what evaluation details show how they varied across the tested RL algorithms and models?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"EmoReward adapts reward weights for emotional video generation","summary":"The authors of EmoReward argue that fixed rewards can miss emotional intent in generated video, where visual quality, motion quality and text alignment do not provide a uniquely correct target. They propose a self-evolving mechanism that uses reward traces from one training run to adjust how different emotional cues are weighted in the next, without updating the reward models.\n\nThe method plans grounding cues from an emotional prompt, scores video using different signal primitives, and uses Reflective Reward Gating to adjust their contributions for each sample. RewardMemory estimates each primitive’s reliability within an emotional regime from rollout scores and outcomes, then sets bounded multipliers for the next run. The authors report improvements on HunyuanVideo 1.5 across multiple RL algorithms, and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration. These are the paper’s reported experimental results; the abstract does not give their magnitude or evaluation details. The proposal’s central idea is to treat evidence about which cues were useful during training as a basis for calibrating later rewards, rather than relying only on fixed weights.","question":"How large were the reported improvements, and what evaluation details show how they varied across the tested RL algorithms and models?","claims":[{"text":"The authors say existing fixed rewards for visual quality, motion quality and text alignment can poorly capture emotional intent and may invite reward hacking.","excerpt":"Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking","support":"source-stated"},{"text":"EmoReward uses reward traces from a completed training run to adapt multi-reward weights in a subsequent run, without updating reward models.","excerpt":"RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models.","support":"source-stated"},{"text":"The authors report improvements on HunyuanVideo 1.5 and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration.","excerpt":"Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration","support":"source-stated"}],"limitations":["The supplied evidence is the arXiv abstract, which gives no numerical improvement sizes or detailed evaluation results.","The abstract describes transfer experiments on SD 3.5 and FLUX but does not report their specific outcomes."],"mediaId":"b17395183e61aa3f7dd2f7d7af70fbd823615878d31e2bc54d417028810301b5","correctionReason":null,"id":"9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d","publicationId":"c5d76233-d884-42fe-8b68-8aa29c0bf441","version":1,"sourceUrl":"https://arxiv.org/abs/2611.06518","sourceTitle":"EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:00:23.706Z","createdAt":"2026-11-10T01:38:55.878Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"b17395183e61aa3f7dd2f7d7af70fbd823615878d31e2bc54d417028810301b5","kind":"article","url":"https://arxiv.org/abs/2611.06518","sourceUrl":"https://arxiv.org/abs/2611.06518","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T01:38:12.335Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06518","checkedAt":"2026-11-10T01:54:11.445Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"b17395183e61aa3f7dd2f7d7af70fbd823615878d31e2bc54d417028810301b5","confidence":0.8300000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"c3150096bf5451cdd734f563ef8a5f15aa3191e95a2b0f6928e9ac8847b876ff","decidedAt":"2026-11-10T01:38:15.905Z"},"provenance":{"textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observationId":"07fddff7ca933892c70030052006f58e19615a2cabfe33f15ebaa26945cd7083","retrievedAt":"2026-11-10T01:38:12.003Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"0e12524e-b08f-4457-8d49-0ba56f6f668d"},"reviewer":{"model":"gpt-6-luna","runId":"4ceebe02-8c7a-4683-8fc3-ffb544c14eba"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T01:38:55.878Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Zheng, Mingzhe","url":null,"kind":"unknown"},{"name":"Wu, Yue","url":null,"kind":"unknown"},{"name":"Tan, Jing","url":null,"kind":"unknown"},{"name":"Zou, Chang","url":null,"kind":"unknown"},{"name":"Jiang, Dengyang","url":null,"kind":"unknown"},{"name":"Tian, Zeyue","url":null,"kind":"unknown"},{"name":"He, Xuanhua","url":null,"kind":"unknown"},{"name":"Xu, Ryan","url":null,"kind":"unknown"},{"name":"Ge, Yunyang","url":null,"kind":"unknown"},{"name":"Ji, Sihui","url":null,"kind":"unknown"},{"name":"Lin, Yunlong","url":null,"kind":"unknown"},{"name":"Pan, Kaihang","url":null,"kind":"unknown"},{"name":"Yan, Hongru","url":null,"kind":"unknown"},{"name":"Chen, Sixiang","url":null,"kind":"unknown"},{"name":"Wang, Dianyi","url":null,"kind":"unknown"},{"name":"Zhang, Julian","url":null,"kind":"unknown"},{"name":"Kong, Weijie","url":null,"kind":"unknown"},{"name":"Li, Changlin","url":null,"kind":"unknown"},{"name":"Guo, Lanqing","url":null,"kind":"unknown"},{"name":"Zhong, Zhao","url":null,"kind":"unknown"},{"name":"Chen, Qifeng","url":null,"kind":"unknown"},{"name":"Yang, Harry","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Zheng, Mingzhe","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zheng, Mingzhe","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Wu, Yue","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wu, Yue","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Tan, Jing","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Tan, Jing","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Zou, Chang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zou, Chang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Jiang, Dengyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jiang, Dengyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Tian, Zeyue","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Tian, Zeyue","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"He, Xuanhua","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"He, Xuanhua","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:6","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Xu, Ryan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Xu, Ryan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:7","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Ge, Yunyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ge, Yunyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:8","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Ji, Sihui","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ji, Sihui","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:9","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Lin, Yunlong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Lin, Yunlong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:10","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Pan, Kaihang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Pan, Kaihang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:11","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Yan, Hongru","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Yan, Hongru","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:12","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Chen, Sixiang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Sixiang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:13","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Wang, Dianyi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wang, Dianyi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:14","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Zhang, Julian","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Julian","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:15","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Kong, Weijie","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kong, Weijie","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:16","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Li, Changlin","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Li, Changlin","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:17","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Guo, Lanqing","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Guo, Lanqing","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:18","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Zhong, Zhao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhong, Zhao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:19","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Chen, Qifeng","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Qifeng","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:20","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Yang, Harry","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Yang, Harry","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:21","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}}],"participationCoverage":{"total":22,"returned":22,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.06518","snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z","basis":"publisher-page-metadata","sourceLinks":61,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d/source"}},"canonicalUrl":"https://escapemeridian.com/readings/emoreward-adapts-reward-weights-for-emotional-video-generation-9865bab0","formats":{"html":"/readings/emoreward-adapts-reward-weights-for-emotional-video-generation-9865bab0","markdown":"/readings/emoreward-adapts-reward-weights-for-emotional-video-generation-9865bab0.md","json":"/readings/emoreward-adapts-reward-weights-for-emotional-video-generation-9865bab0.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-reinforcement-learning","name":"Reinforcement learning","explanation":"Training by trial and error, in which a system is rewarded for the outcomes its designers want.","referenceUrl":"https://developers.google.com/machine-learning/glossary#reinforcement-learning-rl"}],"entities":[{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d","revision":"c5d76233-d884-42fe-8b68-8aa29c0bf441","revisionKind":"publication-id","title":"EmoReward adapts reward weights for emotional video generation","url":"https://escapemeridian.com/readings/emoreward-adapts-reward-weights-for-emotional-video-generation-9865bab0"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.06518","revision":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","revisionKind":"sha256-source-text","title":"EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL","url":"https://arxiv.org/abs/2611.06518"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d","title":"EmoReward adapts reward weights for emotional video generation","argument":"The authors of EmoReward argue that fixed rewards can miss emotional intent in generated video, where visual quality, motion quality and text alignment do not provide a uniquely correct target. They propose a self-evolving mechanism that uses reward traces from one training run to adjust how different emotional cues are weighted in the next, without updating the reward models.\n\nThe method plans grounding cues from an emotional prompt, scores video using different signal primitives, and uses Reflective Reward Gating to adjust their contributions for each sample. RewardMemory estimates each primitive’s reliability within an emotional regime from rollout scores and outcomes, then sets bounded multipliers for the next run. The authors report improvements on HunyuanVideo 1.5 across multiple RL algorithms, and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration. These are the paper’s reported experimental results; the abstract does not give their magnitude or evaluation details. The proposal’s central idea is to treat evidence about which cues were useful during training as a basis for calibrating later rewards, rather than relying only on fixed weights.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the arXiv abstract, which gives no numerical improvement sizes or detailed evaluation results. The abstract describes transfer experiments on SD 3.5 and FLUX but does not report their specific outcomes.","speaker":{"name":"Zheng, Mingzhe, Wu, Yue, Tan, Jing, Zou, Chang, Jiang, Dengyang, Tian, Zeyue, He, Xuanhua, Xu, Ryan, Ge, Yunyang, Ji, Sihui, Lin, Yunlong, Pan, Kaihang, Yan, Hongru, Chen, Sixiang, Wang, Dianyi, Zhang, Julian, Kong, Weijie, Li, Changlin, Guo, Lanqing, Zhong, Zhao, Chen, Qifeng, Yang, Harry","roleAtSource":"Article author"},"source":{"title":"EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.06518","publishedAt":"2026-11-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors say existing fixed rewards for visual quality, motion quality and text alignment can poorly capture emotional intent and may invite reward hacking.","excerpt":"Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking","url":"https://arxiv.org/abs/2611.06518","relationship":"Source-stated"},{"text":"EmoReward uses reward traces from a completed training run to adapt multi-reward weights in a subsequent run, without updating reward models.","excerpt":"RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models.","url":"https://arxiv.org/abs/2611.06518","relationship":"Source-stated"},{"text":"The authors report improvements on HunyuanVideo 1.5 and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration.","excerpt":"Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration","url":"https://arxiv.org/abs/2611.06518","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06518","checkedAt":"2026-11-10T01:54:11.445Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How large were the reported improvements, and what evaluation details show how they varied across the tested RL algorithms and models?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"EmoReward adapts reward weights for emotional video generation","summary":"The authors of EmoReward argue that fixed rewards can miss emotional intent in generated video, where visual quality, motion quality and text alignment do not provide a uniquely correct target. They propose a self-evolving mechanism that uses reward traces from one training run to adjust how different emotional cues are weighted in the next, without updating the reward models.\n\nThe method plans grounding cues from an emotional prompt, scores video using different signal primitives, and uses Reflective Reward Gating to adjust their contributions for each sample. RewardMemory estimates each primitive’s reliability within an emotional regime from rollout scores and outcomes, then sets bounded multipliers for the next run. The authors report improvements on HunyuanVideo 1.5 across multiple RL algorithms, and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration. These are the paper’s reported experimental results; the abstract does not give their magnitude or evaluation details. The proposal’s central idea is to treat evidence about which cues were useful during training as a basis for calibrating later rewards, rather than relying only on fixed weights.","question":"How large were the reported improvements, and what evaluation details show how they varied across the tested RL algorithms and models?","claims":[{"text":"The authors say existing fixed rewards for visual quality, motion quality and text alignment can poorly capture emotional intent and may invite reward hacking.","excerpt":"Existing approaches typically rely on fixed rewards for visual quality, motion quality, and text alignment that poorly capture emotional intent and can invite reward hacking","support":"source-stated"},{"text":"EmoReward uses reward traces from a completed training run to adapt multi-reward weights in a subsequent run, without updating reward models.","excerpt":"RewardMemory then estimates each primitive's reliability from rollout scores and outcomes within each emotional regime in the finished training run, then fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models.","support":"source-stated"},{"text":"The authors report improvements on HunyuanVideo 1.5 and describe ablations and transfer experiments on SD 3.5 and FLUX as further support for adaptive reward calibration.","excerpt":"Experiments on HunyuanVideo 1.5 show improvements across multiple RL algorithms and compare EmoReward with other agentic reward methods under SAGE-GRPO. Ablations and transfer experiments on SD 3.5 and FLUX further support adaptive reward calibration","support":"source-stated"}],"limitations":["The supplied evidence is the arXiv abstract, which gives no numerical improvement sizes or detailed evaluation results.","The abstract describes transfer experiments on SD 3.5 and FLUX but does not report their specific outcomes."],"mediaId":"b17395183e61aa3f7dd2f7d7af70fbd823615878d31e2bc54d417028810301b5","correctionReason":null,"id":"9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d","publicationId":"c5d76233-d884-42fe-8b68-8aa29c0bf441","version":1,"sourceUrl":"https://arxiv.org/abs/2611.06518","sourceTitle":"EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:00:23.706Z","createdAt":"2026-11-10T01:38:55.878Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"b17395183e61aa3f7dd2f7d7af70fbd823615878d31e2bc54d417028810301b5","kind":"article","url":"https://arxiv.org/abs/2611.06518","sourceUrl":"https://arxiv.org/abs/2611.06518","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T01:38:12.335Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06518","checkedAt":"2026-11-10T01:54:11.445Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"b17395183e61aa3f7dd2f7d7af70fbd823615878d31e2bc54d417028810301b5","confidence":0.8300000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"c3150096bf5451cdd734f563ef8a5f15aa3191e95a2b0f6928e9ac8847b876ff","decidedAt":"2026-11-10T01:38:15.905Z"},"provenance":{"textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observationId":"07fddff7ca933892c70030052006f58e19615a2cabfe33f15ebaa26945cd7083","retrievedAt":"2026-11-10T01:38:12.003Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"0e12524e-b08f-4457-8d49-0ba56f6f668d"},"reviewer":{"model":"gpt-6-luna","runId":"4ceebe02-8c7a-4683-8fc3-ffb544c14eba"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T01:38:55.878Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Zheng, Mingzhe","url":null,"kind":"unknown"},{"name":"Wu, Yue","url":null,"kind":"unknown"},{"name":"Tan, Jing","url":null,"kind":"unknown"},{"name":"Zou, Chang","url":null,"kind":"unknown"},{"name":"Jiang, Dengyang","url":null,"kind":"unknown"},{"name":"Tian, Zeyue","url":null,"kind":"unknown"},{"name":"He, Xuanhua","url":null,"kind":"unknown"},{"name":"Xu, Ryan","url":null,"kind":"unknown"},{"name":"Ge, Yunyang","url":null,"kind":"unknown"},{"name":"Ji, Sihui","url":null,"kind":"unknown"},{"name":"Lin, Yunlong","url":null,"kind":"unknown"},{"name":"Pan, Kaihang","url":null,"kind":"unknown"},{"name":"Yan, Hongru","url":null,"kind":"unknown"},{"name":"Chen, Sixiang","url":null,"kind":"unknown"},{"name":"Wang, Dianyi","url":null,"kind":"unknown"},{"name":"Zhang, Julian","url":null,"kind":"unknown"},{"name":"Kong, Weijie","url":null,"kind":"unknown"},{"name":"Li, Changlin","url":null,"kind":"unknown"},{"name":"Guo, Lanqing","url":null,"kind":"unknown"},{"name":"Zhong, Zhao","url":null,"kind":"unknown"},{"name":"Chen, Qifeng","url":null,"kind":"unknown"},{"name":"Yang, Harry","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Zheng, Mingzhe","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zheng, Mingzhe","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Wu, Yue","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wu, Yue","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Tan, Jing","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Tan, Jing","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Zou, Chang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zou, Chang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Jiang, Dengyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Jiang, Dengyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Tian, Zeyue","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Tian, Zeyue","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:5","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"He, Xuanhua","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"He, Xuanhua","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:6","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Xu, Ryan","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Xu, Ryan","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:7","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Ge, Yunyang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ge, Yunyang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:8","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Ji, Sihui","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ji, Sihui","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:9","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Lin, Yunlong","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Lin, Yunlong","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:10","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Pan, Kaihang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Pan, Kaihang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:11","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Yan, Hongru","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Yan, Hongru","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:12","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Chen, Sixiang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Sixiang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:13","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Wang, Dianyi","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Wang, Dianyi","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:14","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Zhang, Julian","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhang, Julian","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:15","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Kong, Weijie","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Kong, Weijie","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:16","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Li, Changlin","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Li, Changlin","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:17","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Guo, Lanqing","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Guo, Lanqing","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:18","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Zhong, Zhao","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zhong, Zhao","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:19","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Chen, Qifeng","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Chen, Qifeng","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:20","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}},{"actor":{"name":"Yang, Harry","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Yang, Harry","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06518","locator":"head/meta[name=author|citation_author]"},"assertionId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe:participation:21","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T01:54:11.445Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","sourceUrl":"https://arxiv.org/abs/2611.06518","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z"}}],"participationCoverage":{"total":22,"returned":22,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.06518","snapshotId":"47eb384b56ba2d99cb4a5f34f18f510eb4d92dcc091fd96d2c6a8ef2966982fe","contentSha256":"18b6a95bb8a13d54789f1d4cf360745387f409f02f251ba1985a805a528d3fca","textHash":"35d4f2a5745a93bd2db0ec8a4c9600e726b77e2d92ada6dc7fead2b4df019a22","observedAt":"2026-11-10T01:54:11.445Z","basis":"publisher-page-metadata","sourceLinks":61,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/9865bab0838fd331f35833792a642649c9da5cd2c9a4a657a79029cb5f5d293d/source"}}}],"audits":[{"publicationId":"c5d76233-d884-42fe-8b68-8aa29c0bf441","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading attributes the problem framing, method and results to the paper's authors. It labels the improvements as reported results rather than established facts.","excerpt":"Authors:Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou"},{"dimension":"summary","status":"uncertain","explanation":"There are two issues. First, the opening sentence says visual quality, motion quality and text alignment have no uniquely correct target. The abstract applies that to evaluating video quality, especially emotional expression; the fixed rewards are said to poorly capture emotional intent. Smallest repair: separate the two points. Second, central terms are unexplained for non-specialists: reward, RL, reward hacking, reward traces, signal primitives, rollout, and the model names HunyuanVideo 1.5, SD 3.5 and FLUX. Tooltip definitions for these terms are needed. The reading also omits the GRPO and RLHF framing, including the abstract's point that RLHF is difficult to scale.","excerpt":"evaluating video quality, especially emotional expression, often depends on subjective aesthetics and has no uniquely correct target"},{"dimension":"date","status":"pass","explanation":"The original publication date, 2026-11-04, matches the v1 submission date. The feed date of Nov 5 is a later announcement.","excerpt":"[Submitted on 4 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"The claims about fixed-reward shortcomings, cross-run calibration without updating reward models, and the HunyuanVideo, SD 3.5 and FLUX experiments match the abstract. The reading correctly notes that the abstract gives no magnitudes. The question follows from that gap without implying an answer.","excerpt":"fixes bounded multipliers that calibrate fusion weights in the next training run without updating reward models"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct link to the arXiv abstract page of the source paper.","excerpt":null}],"createdAt":"2026-11-10T01:38:55.878Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}