{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FMTGIPTUAU57VRKGNXKY6DSP3J","short_pith_number":"pith:FMTGIPTU","schema_version":"1.0","canonical_sha256":"2b26643e74053bfac5466dd58f0e4fda5681fba6e32c93a6149cb97ef64e7ad9","source":{"kind":"arxiv","id":"2406.16855","version":2},"attestation_state":"computed","paper":{"title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunrui Han, Haomiao Tang, Jing Bai, Runpei Dong, Shu-Tao Xia, Xiangyu Zhang, Yuang Peng, Yuxin Cui, Zekun Qi, Zheng Ge","submitted_at":"2024-06-24T17:58:47Z","abstract_excerpt":"Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive ability to creatively generate personalized content across various contexts. However, current evaluations either are automated but misalign with humans or require human evaluations that are time-consuming and expensive. In this work, we present DreamBench++, a human-aligned benchmark that advanced multimodal GPT models automate. Specifically, we systematically design the prompts to let GPT be both human-aligned and self-aligned, empowered with task reinforcement. Further, we co"},"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":"2406.16855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T17:58:47Z","cross_cats_sorted":[],"title_canon_sha256":"212d31db73155d28a55fd70f82d8542c5031fcca5523065ba7b9ac6438b15df1","abstract_canon_sha256":"a0ec888f47466675631cbfea48b7af1a5e2fb7380a31ca0df65c72c1ca2afb7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:11.600151Z","signature_b64":"awECm2rZEqrFMybIq/dnReO8JQCNnfRMD3xc9YEvsYS0m4MFpDd4lS3o1rNNQ7x7rQHZute9zHYGxUnX2fJ4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b26643e74053bfac5466dd58f0e4fda5681fba6e32c93a6149cb97ef64e7ad9","last_reissued_at":"2026-07-05T10:27:11.599622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:11.599622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunrui Han, Haomiao Tang, Jing Bai, Runpei Dong, Shu-Tao Xia, Xiangyu Zhang, Yuang Peng, Yuxin Cui, Zekun Qi, Zheng Ge","submitted_at":"2024-06-24T17:58:47Z","abstract_excerpt":"Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive ability to creatively generate personalized content across various contexts. However, current evaluations either are automated but misalign with humans or require human evaluations that are time-consuming and expensive. In this work, we present DreamBench++, a human-aligned benchmark that advanced multimodal GPT models automate. Specifically, we systematically design the prompts to let GPT be both human-aligned and self-aligned, empowered with task reinforcement. Further, we co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16855","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/2406.16855/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":"2406.16855","created_at":"2026-07-05T10:27:11.599684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16855v2","created_at":"2026-07-05T10:27:11.599684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16855","created_at":"2026-07-05T10:27:11.599684+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMTGIPTUAU57","created_at":"2026-07-05T10:27:11.599684+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMTGIPTUAU57VRKG","created_at":"2026-07-05T10:27:11.599684+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMTGIPTU","created_at":"2026-07-05T10:27:11.599684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01383","citing_title":"MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03715","citing_title":"Text-to-Image Models Need Less from Text Encoders Than You Think","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00351","citing_title":"UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28806","citing_title":"Personal Visual Memory from Explicit and Implicit Evidence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00931","citing_title":"CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01079","citing_title":"Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04300","citing_title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10955","citing_title":"Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12675","citing_title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23951","citing_title":"HunyuanImage 3.0 Technical Report","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12305","citing_title":"Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05039","citing_title":"ID-Sim: An Identity-Focused Similarity Metric","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15742","citing_title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J","json":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J.json","graph_json":"https://pith.science/api/pith-number/FMTGIPTUAU57VRKGNXKY6DSP3J/graph.json","events_json":"https://pith.science/api/pith-number/FMTGIPTUAU57VRKGNXKY6DSP3J/events.json","paper":"https://pith.science/paper/FMTGIPTU"},"agent_actions":{"view_html":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J","download_json":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J.json","view_paper":"https://pith.science/paper/FMTGIPTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16855&json=true","fetch_graph":"https://pith.science/api/pith-number/FMTGIPTUAU57VRKGNXKY6DSP3J/graph.json","fetch_events":"https://pith.science/api/pith-number/FMTGIPTUAU57VRKGNXKY6DSP3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J/action/storage_attestation","attest_author":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J/action/author_attestation","sign_citation":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J/action/citation_signature","submit_replication":"https://pith.science/pith/FMTGIPTUAU57VRKGNXKY6DSP3J/action/replication_record"}},"created_at":"2026-07-05T10:27:11.599684+00:00","updated_at":"2026-07-05T10:27:11.599684+00:00"}