{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JC7G3HBZTURGA6AT7UIEEBNZCD","short_pith_number":"pith:JC7G3HBZ","schema_version":"1.0","canonical_sha256":"48be6d9c399d22607813fd104205b910d0cc34b5f910bf86605d51b6d1d7be80","source":{"kind":"arxiv","id":"2511.19982","version":3},"attestation_state":"computed","paper":{"title":"EmoFeedback$^2$: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aiping Liu, Gang Yang, Jingyang Jia, Kai Shu, Long Xing, Xun Chen","submitted_at":"2025-11-25T06:51:15Z","abstract_excerpt":"Continuous emotional image content generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emotional feedback from generated images, limiting the control of emotional continuity. Additionally, their simple emotion-text alignment fails to adaptively adjust emotional prompts according to image content, leading to insufficient emotional fidelity. To address these concerns, we propose a novel generation-understanding-feedback reinforcement paradigm (EmoFeedback$^2$) for C-EIC"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.19982","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-25T06:51:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a716d719a4c39d786a715cc6b393d7d4cdc764be14d159bf1b18faa49297516","abstract_canon_sha256":"9f7f310d24cdc10ed4119c0a70a8ff2166422378ed5ae10d27013d2e2db3c93c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48be6d9c399d22607813fd104205b910d0cc34b5f910bf86605d51b6d1d7be80","last_reissued_at":"2026-07-31T01:08:54.447836Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:08:54.447836Z"},"graph_snapshot":{"paper":{"title":"EmoFeedback$^2$: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aiping Liu, Gang Yang, Jingyang Jia, Kai Shu, Long Xing, Xun Chen","submitted_at":"2025-11-25T06:51:15Z","abstract_excerpt":"Continuous emotional image content generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emotional feedback from generated images, limiting the control of emotional continuity. Additionally, their simple emotion-text alignment fails to adaptively adjust emotional prompts according to image content, leading to insufficient emotional fidelity. To address these concerns, we propose a novel generation-understanding-feedback reinforcement paradigm (EmoFeedback$^2$) for C-EIC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19982","kind":"arxiv","version":3},"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/2511.19982/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.19982","created_at":"2026-07-31T01:08:54.450968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.19982v3","created_at":"2026-07-31T01:08:54.450968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19982","created_at":"2026-07-31T01:08:54.450968+00:00"},{"alias_kind":"pith_short_12","alias_value":"JC7G3HBZTURG","created_at":"2026-07-31T01:08:54.450968+00:00"},{"alias_kind":"pith_short_16","alias_value":"JC7G3HBZTURGA6AT","created_at":"2026-07-31T01:08:54.450968+00:00"},{"alias_kind":"pith_short_8","alias_value":"JC7G3HBZ","created_at":"2026-07-31T01:08:54.450968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.09286","citing_title":"CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD","json":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD.json","graph_json":"https://pith.science/api/pith-number/JC7G3HBZTURGA6AT7UIEEBNZCD/graph.json","events_json":"https://pith.science/api/pith-number/JC7G3HBZTURGA6AT7UIEEBNZCD/events.json","paper":"https://pith.science/paper/JC7G3HBZ"},"agent_actions":{"view_html":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD","download_json":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD.json","view_paper":"https://pith.science/paper/JC7G3HBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.19982&json=true","fetch_graph":"https://pith.science/api/pith-number/JC7G3HBZTURGA6AT7UIEEBNZCD/graph.json","fetch_events":"https://pith.science/api/pith-number/JC7G3HBZTURGA6AT7UIEEBNZCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD/action/storage_attestation","attest_author":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD/action/author_attestation","sign_citation":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD/action/citation_signature","submit_replication":"https://pith.science/pith/JC7G3HBZTURGA6AT7UIEEBNZCD/action/replication_record"}},"created_at":"2026-07-31T01:08:54.450968+00:00","updated_at":"2026-07-31T01:08:54.450968+00:00"}