{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6YMNR76WWJELSRPYFUOUZ4MYBM","short_pith_number":"pith:6YMNR76W","schema_version":"1.0","canonical_sha256":"f618d8ffd6b248b945f82d1d4cf1980b095cf89908f6e56c275f9c0d4464fadd","source":{"kind":"arxiv","id":"2008.04556","version":4},"attestation_state":"computed","paper":{"title":"Text as Neural Operator: Image Manipulation by Text Instruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honglak Lee, Hung-Yu Tseng, Irfan Essa, Lu Jiang, Tianhao Zhang, Weilong Yang","submitted_at":"2020-08-11T07:07:10Z","abstract_excerpt":"In recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We propose a GAN-based method to tackle this problem. The"},"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":"2008.04556","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-11T07:07:10Z","cross_cats_sorted":[],"title_canon_sha256":"cbe7cc17e534429557022a8652f71d0acee4217e157e76a9b07d6e3dff7c5a49","abstract_canon_sha256":"7aaf47d8620cdcc5488fdf4e9c893675da98ee9fd5e3ebaaae2d56ec83e16b07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:48.176589Z","signature_b64":"S0yOIkTCzqdnS2ZckZg0yAvYrh6R+L7gVjN0Gq3jq47kBNAa22V6y/01I2l++Ava+kxcvEC2cuWoHmrixOp/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f618d8ffd6b248b945f82d1d4cf1980b095cf89908f6e56c275f9c0d4464fadd","last_reissued_at":"2026-07-05T03:35:48.176160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:48.176160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text as Neural Operator: Image Manipulation by Text Instruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honglak Lee, Hung-Yu Tseng, Irfan Essa, Lu Jiang, Tianhao Zhang, Weilong Yang","submitted_at":"2020-08-11T07:07:10Z","abstract_excerpt":"In recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We propose a GAN-based method to tackle this problem. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04556","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/2008.04556/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":"2008.04556","created_at":"2026-07-05T03:35:48.176215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04556v4","created_at":"2026-07-05T03:35:48.176215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04556","created_at":"2026-07-05T03:35:48.176215+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YMNR76WWJEL","created_at":"2026-07-05T03:35:48.176215+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YMNR76WWJELSRPY","created_at":"2026-07-05T03:35:48.176215+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YMNR76W","created_at":"2026-07-05T03:35:48.176215+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/6YMNR76WWJELSRPYFUOUZ4MYBM","json":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM.json","graph_json":"https://pith.science/api/pith-number/6YMNR76WWJELSRPYFUOUZ4MYBM/graph.json","events_json":"https://pith.science/api/pith-number/6YMNR76WWJELSRPYFUOUZ4MYBM/events.json","paper":"https://pith.science/paper/6YMNR76W"},"agent_actions":{"view_html":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM","download_json":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM.json","view_paper":"https://pith.science/paper/6YMNR76W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04556&json=true","fetch_graph":"https://pith.science/api/pith-number/6YMNR76WWJELSRPYFUOUZ4MYBM/graph.json","fetch_events":"https://pith.science/api/pith-number/6YMNR76WWJELSRPYFUOUZ4MYBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM/action/storage_attestation","attest_author":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM/action/author_attestation","sign_citation":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM/action/citation_signature","submit_replication":"https://pith.science/pith/6YMNR76WWJELSRPYFUOUZ4MYBM/action/replication_record"}},"created_at":"2026-07-05T03:35:48.176215+00:00","updated_at":"2026-07-05T03:35:48.176215+00:00"}