{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I7LC7EIGP54LMHSCQQ7VZC2LGJ","short_pith_number":"pith:I7LC7EIG","schema_version":"1.0","canonical_sha256":"47d62f91067f78b61e42843f5c8b4b324b1e6e174385338a24e35f28642482bb","source":{"kind":"arxiv","id":"2505.00502","version":1},"attestation_state":"computed","paper":{"title":"Towards Scalable Human-aligned Benchmark for Text-guided Image Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsoo Shin, Eugene Baek, Joonseok Lee, Kihyun Kim, Suho Ryu","submitted_at":"2025-05-01T13:06:05Z","abstract_excerpt":"A variety of text-guided image editing models have been proposed recently. However, there is no widely-accepted standard evaluation method mainly due to the subjective nature of the task, letting researchers rely on manual user study. To address this, we introduce a novel Human-Aligned benchmark for Text-guided Image Editing (HATIE). Providing a large-scale benchmark set covering a wide range of editing tasks, it allows reliable evaluation, not limited to specific easy-to-evaluate cases. Also, HATIE provides a fully-automated and omnidirectional evaluation pipeline. Particularly, we combine mu"},"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":"2505.00502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T13:06:05Z","cross_cats_sorted":[],"title_canon_sha256":"b3650b4b7f8e2140a6b28348c21a46da6ca48207d20917b3d67d5736ce1ef178","abstract_canon_sha256":"7e76ba76593b0f3b8fc9e4fa996d0d6a96b15b1d943b11643d977d6c93d2095c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:14.600817Z","signature_b64":"7uYwFmyxRzRO/mTVbwuxE0vD8eBXUKYGALHfH06xCjfS6kxNDOW+C9Z6jJuf7yVV/oINO3Br9CGAvXK+iL5EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47d62f91067f78b61e42843f5c8b4b324b1e6e174385338a24e35f28642482bb","last_reissued_at":"2026-07-05T10:57:14.600319Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:14.600319Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Scalable Human-aligned Benchmark for Text-guided Image Editing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsoo Shin, Eugene Baek, Joonseok Lee, Kihyun Kim, Suho Ryu","submitted_at":"2025-05-01T13:06:05Z","abstract_excerpt":"A variety of text-guided image editing models have been proposed recently. However, there is no widely-accepted standard evaluation method mainly due to the subjective nature of the task, letting researchers rely on manual user study. To address this, we introduce a novel Human-Aligned benchmark for Text-guided Image Editing (HATIE). Providing a large-scale benchmark set covering a wide range of editing tasks, it allows reliable evaluation, not limited to specific easy-to-evaluate cases. Also, HATIE provides a fully-automated and omnidirectional evaluation pipeline. Particularly, we combine mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00502","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/2505.00502/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":"2505.00502","created_at":"2026-07-05T10:57:14.600385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00502v1","created_at":"2026-07-05T10:57:14.600385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00502","created_at":"2026-07-05T10:57:14.600385+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7LC7EIGP54L","created_at":"2026-07-05T10:57:14.600385+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7LC7EIGP54LMHSC","created_at":"2026-07-05T10:57:14.600385+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7LC7EIG","created_at":"2026-07-05T10:57:14.600385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ","json":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ.json","graph_json":"https://pith.science/api/pith-number/I7LC7EIGP54LMHSCQQ7VZC2LGJ/graph.json","events_json":"https://pith.science/api/pith-number/I7LC7EIGP54LMHSCQQ7VZC2LGJ/events.json","paper":"https://pith.science/paper/I7LC7EIG"},"agent_actions":{"view_html":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ","download_json":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ.json","view_paper":"https://pith.science/paper/I7LC7EIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00502&json=true","fetch_graph":"https://pith.science/api/pith-number/I7LC7EIGP54LMHSCQQ7VZC2LGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I7LC7EIGP54LMHSCQQ7VZC2LGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ/action/storage_attestation","attest_author":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ/action/author_attestation","sign_citation":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ/action/citation_signature","submit_replication":"https://pith.science/pith/I7LC7EIGP54LMHSCQQ7VZC2LGJ/action/replication_record"}},"created_at":"2026-07-05T10:57:14.600385+00:00","updated_at":"2026-07-05T10:57:14.600385+00:00"}