{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NZB3PPXUPI5IIA5DT3CAZ3NFDA","short_pith_number":"pith:NZB3PPXU","schema_version":"1.0","canonical_sha256":"6e43b7bef47a3a8403a39ec40ceda5183870b0a469e832884db33f2df2845082","source":{"kind":"arxiv","id":"2310.01596","version":4},"attestation_state":"computed","paper":{"title":"ImagenHub: Standardizing the evaluation of conditional image generation models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Kai Zhang, Max Ku, Tianle Li, Wenhu Chen, Wenwen Zhuang, Xingyu Fu, Yujie Lu","submitted_at":"2023-10-02T19:41:42Z","abstract_excerpt":"Recently, a myriad of conditional image generation and editing models have been developed to serve different downstream tasks, including text-to-image generation, text-guided image editing, subject-driven image generation, control-guided image generation, etc. However, we observe huge inconsistencies in experimental conditions: datasets, inference, and evaluation metrics - render fair comparisons difficult. This paper proposes ImagenHub, which is a one-stop library to standardize the inference and evaluation of all the conditional image generation models. Firstly, we define seven prominent tas"},"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":"2310.01596","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-02T19:41:42Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"315be9fb3bd74ecbc93d40f84afe53bed54388892f2e5c40135a0b704078a3cc","abstract_canon_sha256":"53d3d120e53fb6074ff6cc58a6c85f45316111d2ddccf2fd40e5bc5eff29f261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:04.210382Z","signature_b64":"2ixo0Ig0cTjhnchIr3viDDr9HQDhPVsjZgtA7SNr5/geYb4kHsWfr23rvCvzU/k30CmHSo0AL5ZhH7c+PZtyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e43b7bef47a3a8403a39ec40ceda5183870b0a469e832884db33f2df2845082","last_reissued_at":"2026-07-05T07:54:04.209894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:04.209894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImagenHub: Standardizing the evaluation of conditional image generation models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Kai Zhang, Max Ku, Tianle Li, Wenhu Chen, Wenwen Zhuang, Xingyu Fu, Yujie Lu","submitted_at":"2023-10-02T19:41:42Z","abstract_excerpt":"Recently, a myriad of conditional image generation and editing models have been developed to serve different downstream tasks, including text-to-image generation, text-guided image editing, subject-driven image generation, control-guided image generation, etc. However, we observe huge inconsistencies in experimental conditions: datasets, inference, and evaluation metrics - render fair comparisons difficult. This paper proposes ImagenHub, which is a one-stop library to standardize the inference and evaluation of all the conditional image generation models. Firstly, we define seven prominent tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01596","kind":"arxiv","version":4},"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/2310.01596/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":"2310.01596","created_at":"2026-07-05T07:54:04.209957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01596v4","created_at":"2026-07-05T07:54:04.209957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01596","created_at":"2026-07-05T07:54:04.209957+00:00"},{"alias_kind":"pith_short_12","alias_value":"NZB3PPXUPI5I","created_at":"2026-07-05T07:54:04.209957+00:00"},{"alias_kind":"pith_short_16","alias_value":"NZB3PPXUPI5IIA5D","created_at":"2026-07-05T07:54:04.209957+00:00"},{"alias_kind":"pith_short_8","alias_value":"NZB3PPXU","created_at":"2026-07-05T07:54:04.209957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06875","citing_title":"Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows","ref_index":5,"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":36,"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":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA","json":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA.json","graph_json":"https://pith.science/api/pith-number/NZB3PPXUPI5IIA5DT3CAZ3NFDA/graph.json","events_json":"https://pith.science/api/pith-number/NZB3PPXUPI5IIA5DT3CAZ3NFDA/events.json","paper":"https://pith.science/paper/NZB3PPXU"},"agent_actions":{"view_html":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA","download_json":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA.json","view_paper":"https://pith.science/paper/NZB3PPXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01596&json=true","fetch_graph":"https://pith.science/api/pith-number/NZB3PPXUPI5IIA5DT3CAZ3NFDA/graph.json","fetch_events":"https://pith.science/api/pith-number/NZB3PPXUPI5IIA5DT3CAZ3NFDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA/action/storage_attestation","attest_author":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA/action/author_attestation","sign_citation":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA/action/citation_signature","submit_replication":"https://pith.science/pith/NZB3PPXUPI5IIA5DT3CAZ3NFDA/action/replication_record"}},"created_at":"2026-07-05T07:54:04.209957+00:00","updated_at":"2026-07-05T07:54:04.209957+00:00"}