{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6246XT57DBJTIZAXNKJJ5WYYQ7","short_pith_number":"pith:6246XT57","schema_version":"1.0","canonical_sha256":"f6b9ebcfbf18533464176a929edb1887cc767aa706a3d84e0d06c3cbebf9558d","source":{"kind":"arxiv","id":"2303.09618","version":2},"attestation_state":"computed","paper":{"title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Can Qin, Chia-Chih Chen, Huan Wang, Ning Yu, Ran Xu, Shu Zhang, Silvio Savarese, Stefano Ermon, Xinyi Yang, Yihao Feng, Zeyuan Chen","submitted_at":"2023-03-16T19:47:41Z","abstract_excerpt":"Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences. We hypothesize that state-of-the-art instructional image editing models, where outputs are generated based on an input image and an editing instruction, could similarly benefit from human feedback, as their outputs may not adhere to the correct instructions and preferences of users. In this paper, we present a novel framework to harness human feedback for instructional visual editing (HIVE). Specifically, we collect human feedback on the edited images and learn a rew"},"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":"2303.09618","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T19:47:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG"],"title_canon_sha256":"8f7f815ac865f38cecbcd518fe8a78b82cd1f50cd9e9178c60548b1d8c63bbbf","abstract_canon_sha256":"885d4300d282c93e8006a4410eb03fe215368caf9d4c7c3abb5603db706861d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:59.093509Z","signature_b64":"T38qvl55WSr+M3BpEiM/L/sXWjMcSPkZ+g+8gasHab1mZCH9qRQc1gHUpssSbjfT8gzpTvsE5hU4W1nPJMiFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6b9ebcfbf18533464176a929edb1887cc767aa706a3d84e0d06c3cbebf9558d","last_reissued_at":"2026-07-05T08:00:59.093015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:59.093015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Can Qin, Chia-Chih Chen, Huan Wang, Ning Yu, Ran Xu, Shu Zhang, Silvio Savarese, Stefano Ermon, Xinyi Yang, Yihao Feng, Zeyuan Chen","submitted_at":"2023-03-16T19:47:41Z","abstract_excerpt":"Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences. We hypothesize that state-of-the-art instructional image editing models, where outputs are generated based on an input image and an editing instruction, could similarly benefit from human feedback, as their outputs may not adhere to the correct instructions and preferences of users. In this paper, we present a novel framework to harness human feedback for instructional visual editing (HIVE). Specifically, we collect human feedback on the edited images and learn a rew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09618","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/2303.09618/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":"2303.09618","created_at":"2026-07-05T08:00:59.093075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09618v2","created_at":"2026-07-05T08:00:59.093075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09618","created_at":"2026-07-05T08:00:59.093075+00:00"},{"alias_kind":"pith_short_12","alias_value":"6246XT57DBJT","created_at":"2026-07-05T08:00:59.093075+00:00"},{"alias_kind":"pith_short_16","alias_value":"6246XT57DBJTIZAX","created_at":"2026-07-05T08:00:59.093075+00:00"},{"alias_kind":"pith_short_8","alias_value":"6246XT57","created_at":"2026-07-05T08:00:59.093075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04887","citing_title":"HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7","json":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7.json","graph_json":"https://pith.science/api/pith-number/6246XT57DBJTIZAXNKJJ5WYYQ7/graph.json","events_json":"https://pith.science/api/pith-number/6246XT57DBJTIZAXNKJJ5WYYQ7/events.json","paper":"https://pith.science/paper/6246XT57"},"agent_actions":{"view_html":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7","download_json":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7.json","view_paper":"https://pith.science/paper/6246XT57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09618&json=true","fetch_graph":"https://pith.science/api/pith-number/6246XT57DBJTIZAXNKJJ5WYYQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/6246XT57DBJTIZAXNKJJ5WYYQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7/action/storage_attestation","attest_author":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7/action/author_attestation","sign_citation":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7/action/citation_signature","submit_replication":"https://pith.science/pith/6246XT57DBJTIZAXNKJJ5WYYQ7/action/replication_record"}},"created_at":"2026-07-05T08:00:59.093075+00:00","updated_at":"2026-07-05T08:00:59.093075+00:00"}