{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LUAPTOMQ7N45DJXPDADTW5R2A2","short_pith_number":"pith:LUAPTOMQ","schema_version":"1.0","canonical_sha256":"5d00f9b990fb79d1a6ef18073b763a06b1cf1ffda40ed28122da598eb2f1ed2a","source":{"kind":"arxiv","id":"2505.02370","version":1},"attestation_state":"computed","paper":{"title":"SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Chen, Fan Chen, Longyin Wen, Ming Li, Sijie Zhu, Xiaoying Xing, Xin Gu","submitted_at":"2025-05-05T05:19:40Z","abstract_excerpt":"Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signals caused by the mismatch between editing instructions and original-edited image pairs. Recent efforts attempt to improve editing models through generating higher-quality edited images, pre-training on recognition tasks, or introducing vision-language models (VLMs) but fail to resolve this fundamental issue. In this paper, we offer a novel solution by constructing more effective editing instructions for given image pa"},"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":"2505.02370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-05T05:19:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6ba8f72ef5dccf3b62cd560602e32a7dc95f3e0a26fc4ae07c5c8647a4da57b4","abstract_canon_sha256":"cfdb6ecfbd69c7e0ec6028700a24000be8ea0ccac4f4d454f2e32dfe84484f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:36.036262Z","signature_b64":"5SXSj7ycv+o3glcHySUGb+1nWP4qoECVkqgPUQgFFB8wIs1lO9K0yQ75lpUMhZO5ShFi4/+rAbj72qgQ6NC6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d00f9b990fb79d1a6ef18073b763a06b1cf1ffda40ed28122da598eb2f1ed2a","last_reissued_at":"2026-07-05T10:58:36.035839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:36.035839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chen Chen, Fan Chen, Longyin Wen, Ming Li, Sijie Zhu, Xiaoying Xing, Xin Gu","submitted_at":"2025-05-05T05:19:40Z","abstract_excerpt":"Due to the challenges of manually collecting accurate editing data, existing datasets are typically constructed using various automated methods, leading to noisy supervision signals caused by the mismatch between editing instructions and original-edited image pairs. Recent efforts attempt to improve editing models through generating higher-quality edited images, pre-training on recognition tasks, or introducing vision-language models (VLMs) but fail to resolve this fundamental issue. In this paper, we offer a novel solution by constructing more effective editing instructions for given image pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02370","kind":"arxiv","version":1},"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/2505.02370/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":"2505.02370","created_at":"2026-07-05T10:58:36.035904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02370v1","created_at":"2026-07-05T10:58:36.035904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02370","created_at":"2026-07-05T10:58:36.035904+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUAPTOMQ7N45","created_at":"2026-07-05T10:58:36.035904+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUAPTOMQ7N45DJXP","created_at":"2026-07-05T10:58:36.035904+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUAPTOMQ","created_at":"2026-07-05T10:58:36.035904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2","json":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2.json","graph_json":"https://pith.science/api/pith-number/LUAPTOMQ7N45DJXPDADTW5R2A2/graph.json","events_json":"https://pith.science/api/pith-number/LUAPTOMQ7N45DJXPDADTW5R2A2/events.json","paper":"https://pith.science/paper/LUAPTOMQ"},"agent_actions":{"view_html":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2","download_json":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2.json","view_paper":"https://pith.science/paper/LUAPTOMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02370&json=true","fetch_graph":"https://pith.science/api/pith-number/LUAPTOMQ7N45DJXPDADTW5R2A2/graph.json","fetch_events":"https://pith.science/api/pith-number/LUAPTOMQ7N45DJXPDADTW5R2A2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2/action/storage_attestation","attest_author":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2/action/author_attestation","sign_citation":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2/action/citation_signature","submit_replication":"https://pith.science/pith/LUAPTOMQ7N45DJXPDADTW5R2A2/action/replication_record"}},"created_at":"2026-07-05T10:58:36.035904+00:00","updated_at":"2026-07-05T10:58:36.035904+00:00"}