{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6VBHKHWPSPV35IIPW7SGT5PDPT","short_pith_number":"pith:6VBHKHWP","schema_version":"1.0","canonical_sha256":"f542751ecf93ebbea10fb7e469f5e37ce6961d2fbfd473958fa65bda56848a4e","source":{"kind":"arxiv","id":"2503.23897","version":1},"attestation_state":"computed","paper":{"title":"Training-Free Text-Guided Image Editing with Visual Autoregressive Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bihan Wen, Jian Wang, Jiaxing Huang, Lanqing Guo, Pichao Wang, Yufei Wang, Zhihao Li","submitted_at":"2025-03-31T09:46:56Z","abstract_excerpt":"Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying on inversion techniques to extract structured noise from input images. However, inaccuracies in inversion can propagate errors, leading to unintended modifications and compromising fidelity. Moreover, even with perfect inversion, the entanglement between textual prompts and image features often results in global changes when only local edits are intended. T"},"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":"2503.23897","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T09:46:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"31c2fb86e519e5bc35c7bfd550010ab0c5109aa97b7c1d66428b8a87cf58e32e","abstract_canon_sha256":"f467521778130608d71f4e958135f4483c9bf115ad672c450c4cf959dd346a60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:01.568093Z","signature_b64":"npL7lDi8L0rtSBXAg3ymHJ7xdnZTTQuuu6NMr5PLL0acYKHcLi4JsIO2nL51Kles6SmlH0sY24psXWPXPmgXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f542751ecf93ebbea10fb7e469f5e37ce6961d2fbfd473958fa65bda56848a4e","last_reissued_at":"2026-07-05T10:42:01.567639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:01.567639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Free Text-Guided Image Editing with Visual Autoregressive Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bihan Wen, Jian Wang, Jiaxing Huang, Lanqing Guo, Pichao Wang, Yufei Wang, Zhihao Li","submitted_at":"2025-03-31T09:46:56Z","abstract_excerpt":"Text-guided image editing is an essential task that enables users to modify images through natural language descriptions. Recent advances in diffusion models and rectified flows have significantly improved editing quality, primarily relying on inversion techniques to extract structured noise from input images. However, inaccuracies in inversion can propagate errors, leading to unintended modifications and compromising fidelity. Moreover, even with perfect inversion, the entanglement between textual prompts and image features often results in global changes when only local edits are intended. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23897","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/2503.23897/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":"2503.23897","created_at":"2026-07-05T10:42:01.567702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23897v1","created_at":"2026-07-05T10:42:01.567702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23897","created_at":"2026-07-05T10:42:01.567702+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VBHKHWPSPV3","created_at":"2026-07-05T10:42:01.567702+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VBHKHWPSPV35IIP","created_at":"2026-07-05T10:42:01.567702+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VBHKHWP","created_at":"2026-07-05T10:42:01.567702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14591","citing_title":"Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT","json":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT.json","graph_json":"https://pith.science/api/pith-number/6VBHKHWPSPV35IIPW7SGT5PDPT/graph.json","events_json":"https://pith.science/api/pith-number/6VBHKHWPSPV35IIPW7SGT5PDPT/events.json","paper":"https://pith.science/paper/6VBHKHWP"},"agent_actions":{"view_html":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT","download_json":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT.json","view_paper":"https://pith.science/paper/6VBHKHWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23897&json=true","fetch_graph":"https://pith.science/api/pith-number/6VBHKHWPSPV35IIPW7SGT5PDPT/graph.json","fetch_events":"https://pith.science/api/pith-number/6VBHKHWPSPV35IIPW7SGT5PDPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT/action/storage_attestation","attest_author":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT/action/author_attestation","sign_citation":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT/action/citation_signature","submit_replication":"https://pith.science/pith/6VBHKHWPSPV35IIPW7SGT5PDPT/action/replication_record"}},"created_at":"2026-07-05T10:42:01.567702+00:00","updated_at":"2026-07-05T10:42:01.567702+00:00"}