{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7CFTTSJPJUZONDUMHH353GUWRD","short_pith_number":"pith:7CFTTSJP","schema_version":"1.0","canonical_sha256":"f88b39c92f4d32e68e8c39f7dd9a9688e028e029ad573459dbcb2f0ed126b57d","source":{"kind":"arxiv","id":"2111.13333","version":2},"attestation_state":"computed","paper":{"title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Errui Ding, Fu Li, Hao Tang, Luc Van Gool, Nicu Sebe, Radu Timofte, Tianwei Lin, Zipeng Xu","submitted_at":"2021-11-26T06:49:26Z","abstract_excerpt":"To achieve disentangled image manipulation, previous works depend heavily on manual annotation. Meanwhile, the available manipulations are limited to a pre-defined set the models were trained for. We propose a novel framework, i.e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of manipulations. Our method approaches the targets by deeply exploiting the power of the large-scale pre-trained vision-language model CLIP. Concretely, we firstly Predict the possibly entangled attri"},"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":"2111.13333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-26T06:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"da7ad0cfa7c19463c2cc2cbaef8001df9b3474cb5ca0384f0116fae98adfbbb7","abstract_canon_sha256":"87455c2f43046e6fc8a74c7a7ece56cfe3abb7e7699cc0d26e4056dd8e12e023"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:17.173144Z","signature_b64":"Hp6dOhX3KrEJC9wQzSJ8LF3xucIqJjhdPf1VReMFTEEj2R+VqL7bkHrsWv2o25PZxLRQudVHus5Hg0gByhaJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f88b39c92f4d32e68e8c39f7dd9a9688e028e029ad573459dbcb2f0ed126b57d","last_reissued_at":"2026-07-05T04:08:17.172666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:17.172666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang He, Errui Ding, Fu Li, Hao Tang, Luc Van Gool, Nicu Sebe, Radu Timofte, Tianwei Lin, Zipeng Xu","submitted_at":"2021-11-26T06:49:26Z","abstract_excerpt":"To achieve disentangled image manipulation, previous works depend heavily on manual annotation. Meanwhile, the available manipulations are limited to a pre-defined set the models were trained for. We propose a novel framework, i.e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of manipulations. Our method approaches the targets by deeply exploiting the power of the large-scale pre-trained vision-language model CLIP. Concretely, we firstly Predict the possibly entangled attri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13333","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/2111.13333/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":"2111.13333","created_at":"2026-07-05T04:08:17.172724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13333v2","created_at":"2026-07-05T04:08:17.172724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13333","created_at":"2026-07-05T04:08:17.172724+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CFTTSJPJUZO","created_at":"2026-07-05T04:08:17.172724+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CFTTSJPJUZONDUM","created_at":"2026-07-05T04:08:17.172724+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CFTTSJP","created_at":"2026-07-05T04:08:17.172724+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/7CFTTSJPJUZONDUMHH353GUWRD","json":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD.json","graph_json":"https://pith.science/api/pith-number/7CFTTSJPJUZONDUMHH353GUWRD/graph.json","events_json":"https://pith.science/api/pith-number/7CFTTSJPJUZONDUMHH353GUWRD/events.json","paper":"https://pith.science/paper/7CFTTSJP"},"agent_actions":{"view_html":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD","download_json":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD.json","view_paper":"https://pith.science/paper/7CFTTSJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13333&json=true","fetch_graph":"https://pith.science/api/pith-number/7CFTTSJPJUZONDUMHH353GUWRD/graph.json","fetch_events":"https://pith.science/api/pith-number/7CFTTSJPJUZONDUMHH353GUWRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD/action/storage_attestation","attest_author":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD/action/author_attestation","sign_citation":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD/action/citation_signature","submit_replication":"https://pith.science/pith/7CFTTSJPJUZONDUMHH353GUWRD/action/replication_record"}},"created_at":"2026-07-05T04:08:17.172724+00:00","updated_at":"2026-07-05T04:08:17.172724+00:00"}