{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XM67MBKQN3K4YLFMVSJWT3K3TL","short_pith_number":"pith:XM67MBKQ","schema_version":"1.0","canonical_sha256":"bb3df605506ed5cc2cacac9369ed5b9af5b5ea0cc264c140833d8a7c52dd74fe","source":{"kind":"arxiv","id":"2509.01984","version":2},"attestation_state":"computed","paper":{"title":"Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amin Heyrani Nobar, Dimitris Metaxas, Faez Ahmed, Han Zhang, Ligong Han, Ngan Hoai Nguyen, Quan Dao, Viet Anh Nguyen, Xiaoxiao He","submitted_at":"2025-09-02T06:01:52Z","abstract_excerpt":"Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation tasks. While conditional generation has been widely explored, the ability to perform prompt-guided image editing without additional training is equally critical, as it supports numerous practical real-world applications. This paper investigates the text-to-image editing capabilities of VAR by introducing Visual AutoRegressive Inverse Noise (VARIN), the first noise inversion-based editing technique designed explicitl"},"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":"2509.01984","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T06:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"4cf18c44ab94f1e41ab1b708c448168fec047106537ecfc278b5ee9e0a105ab1","abstract_canon_sha256":"f0079b713b51ca9f11f782489cb1f6228cf8e3b61be267df9466f1bc5e1c45c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:53.027716Z","signature_b64":"ZDiFX0gG+MxdXMmmhH/tnfU5V02Bkb3XGPxtTH7ckfFDn5IXsLfKjcvILQq2O+xs8SQJ45aHXuMcepajvRkeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb3df605506ed5cc2cacac9369ed5b9af5b5ea0cc264c140833d8a7c52dd74fe","last_reissued_at":"2026-07-05T12:03:53.027177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:53.027177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amin Heyrani Nobar, Dimitris Metaxas, Faez Ahmed, Han Zhang, Ligong Han, Ngan Hoai Nguyen, Quan Dao, Viet Anh Nguyen, Xiaoxiao He","submitted_at":"2025-09-02T06:01:52Z","abstract_excerpt":"Visual autoregressive models (VAR) have recently emerged as a promising class of generative models, achieving performance comparable to diffusion models in text-to-image generation tasks. While conditional generation has been widely explored, the ability to perform prompt-guided image editing without additional training is equally critical, as it supports numerous practical real-world applications. This paper investigates the text-to-image editing capabilities of VAR by introducing Visual AutoRegressive Inverse Noise (VARIN), the first noise inversion-based editing technique designed explicitl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01984","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/2509.01984/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":"2509.01984","created_at":"2026-07-05T12:03:53.027226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01984v2","created_at":"2026-07-05T12:03:53.027226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01984","created_at":"2026-07-05T12:03:53.027226+00:00"},{"alias_kind":"pith_short_12","alias_value":"XM67MBKQN3K4","created_at":"2026-07-05T12:03:53.027226+00:00"},{"alias_kind":"pith_short_16","alias_value":"XM67MBKQN3K4YLFM","created_at":"2026-07-05T12:03:53.027226+00:00"},{"alias_kind":"pith_short_8","alias_value":"XM67MBKQ","created_at":"2026-07-05T12:03:53.027226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13558","citing_title":"Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26357","citing_title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","ref_index":13,"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":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL","json":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL.json","graph_json":"https://pith.science/api/pith-number/XM67MBKQN3K4YLFMVSJWT3K3TL/graph.json","events_json":"https://pith.science/api/pith-number/XM67MBKQN3K4YLFMVSJWT3K3TL/events.json","paper":"https://pith.science/paper/XM67MBKQ"},"agent_actions":{"view_html":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL","download_json":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL.json","view_paper":"https://pith.science/paper/XM67MBKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01984&json=true","fetch_graph":"https://pith.science/api/pith-number/XM67MBKQN3K4YLFMVSJWT3K3TL/graph.json","fetch_events":"https://pith.science/api/pith-number/XM67MBKQN3K4YLFMVSJWT3K3TL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL/action/storage_attestation","attest_author":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL/action/author_attestation","sign_citation":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL/action/citation_signature","submit_replication":"https://pith.science/pith/XM67MBKQN3K4YLFMVSJWT3K3TL/action/replication_record"}},"created_at":"2026-07-05T12:03:53.027226+00:00","updated_at":"2026-07-05T12:03:53.027226+00:00"}