{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GPZDT5FJSQPKGNT5U4AP7M2WE5","short_pith_number":"pith:GPZDT5FJ","schema_version":"1.0","canonical_sha256":"33f239f4a9941ea3367da700ffb356277791c760759b7a4847e1927a40a93e8b","source":{"kind":"arxiv","id":"2411.15738","version":3},"attestation_state":"computed","paper":{"title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Juncheng Li, Kaihang Pan, Qifan Yu, Siliang Tang, Wei Chow, Xiaoyang Wan, Yang Wu, Yueting Zhuang, Zhongqi Yue","submitted_at":"2024-11-24T07:02:56Z","abstract_excerpt":"Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execute complex user instructions, as they are trained on low-quality data with limited editing types. We present AnyEdit, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains. We ensure the diversity and quality of the AnyEdit collection through three aspects: initial data diversity, adaptive editing process, and automat"},"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":"2411.15738","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T07:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"5dde771fee91ab20125dfb3f7ed34b1507d2573c5940d2cd4790b0d3eb6be176","abstract_canon_sha256":"9cacb875de1ea041b81739fb6748b5eed7c9cb936d7a77b82079cbd9205f93b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:17.544094Z","signature_b64":"L0zpGbsxaEfBIAP5eIRsuHaI0xo4Cg+VJyTZPX25Gtgxfs6NayqIxLvYELCOQdhzN4K2Y9+LeClv6R484Q2BCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f239f4a9941ea3367da700ffb356277791c760759b7a4847e1927a40a93e8b","last_reissued_at":"2026-07-05T10:41:17.543609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:17.543609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Juncheng Li, Kaihang Pan, Qifan Yu, Siliang Tang, Wei Chow, Xiaoyang Wan, Yang Wu, Yueting Zhuang, Zhongqi Yue","submitted_at":"2024-11-24T07:02:56Z","abstract_excerpt":"Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execute complex user instructions, as they are trained on low-quality data with limited editing types. We present AnyEdit, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains. We ensure the diversity and quality of the AnyEdit collection through three aspects: initial data diversity, adaptive editing process, and automat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15738","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/2411.15738/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":"2411.15738","created_at":"2026-07-05T10:41:17.543670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15738v3","created_at":"2026-07-05T10:41:17.543670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15738","created_at":"2026-07-05T10:41:17.543670+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPZDT5FJSQPK","created_at":"2026-07-05T10:41:17.543670+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPZDT5FJSQPKGNT5","created_at":"2026-07-05T10:41:17.543670+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPZDT5FJ","created_at":"2026-07-05T10:41:17.543670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09233","citing_title":"Towards Robust Sequential Decomposition for Complex Image Editing","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23622","citing_title":"DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01908","citing_title":"Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20360","citing_title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03147","citing_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09233","citing_title":"Towards Robust Sequential Decomposition for Complex Image Editing","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5","json":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5.json","graph_json":"https://pith.science/api/pith-number/GPZDT5FJSQPKGNT5U4AP7M2WE5/graph.json","events_json":"https://pith.science/api/pith-number/GPZDT5FJSQPKGNT5U4AP7M2WE5/events.json","paper":"https://pith.science/paper/GPZDT5FJ"},"agent_actions":{"view_html":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5","download_json":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5.json","view_paper":"https://pith.science/paper/GPZDT5FJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15738&json=true","fetch_graph":"https://pith.science/api/pith-number/GPZDT5FJSQPKGNT5U4AP7M2WE5/graph.json","fetch_events":"https://pith.science/api/pith-number/GPZDT5FJSQPKGNT5U4AP7M2WE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5/action/storage_attestation","attest_author":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5/action/author_attestation","sign_citation":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5/action/citation_signature","submit_replication":"https://pith.science/pith/GPZDT5FJSQPKGNT5U4AP7M2WE5/action/replication_record"}},"created_at":"2026-07-05T10:41:17.543670+00:00","updated_at":"2026-07-05T10:41:17.543670+00:00"}