{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CM5VTUNYHC6FYD5LGLKLQUM5P6","short_pith_number":"pith:CM5VTUNY","schema_version":"1.0","canonical_sha256":"133b59d1b838bc5c0fab32d4b8519d7f820ab84c0aa69c60bacd9d33a642d2a5","source":{"kind":"arxiv","id":"2503.02187","version":1},"attestation_state":"computed","paper":{"title":"h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Kieu, Kien Do, Thin Nguyen, Toan Nguyen","submitted_at":"2025-03-04T01:49:59Z","abstract_excerpt":"We introduce a theoretical framework for diffusion-based image editing by formulating it as a reverse-time bridge modeling problem. This approach modifies the backward process of a pretrained diffusion model to construct a bridge that converges to an implicit distribution associated with the editing target at time 0. Building on this framework, we propose h-Edit, a novel editing method that utilizes Doob's h-transform and Langevin Monte Carlo to decompose the update of an intermediate edited sample into two components: a \"reconstruction\" term and an \"editing\" term. This decomposition provides "},"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":"2503.02187","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T01:49:59Z","cross_cats_sorted":[],"title_canon_sha256":"535ff155b0c4f4e69af74b3c7fa45923aafb7ac23a5bbc25affdd0866983c85c","abstract_canon_sha256":"d1fdaf3b10b2f353ee9c4a20e14b3a86b58cc352407382433e4b2c48fc17a841"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:38.879401Z","signature_b64":"LRvkPJkpczsmOgH1Q+WIs/APRaLvAtHWTamnfh5816TLXLLSgmQpjWbe9fRuucaME1vnTNKggIudWhaNidk6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"133b59d1b838bc5c0fab32d4b8519d7f820ab84c0aa69c60bacd9d33a642d2a5","last_reissued_at":"2026-07-05T10:23:38.878911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:38.878911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Kieu, Kien Do, Thin Nguyen, Toan Nguyen","submitted_at":"2025-03-04T01:49:59Z","abstract_excerpt":"We introduce a theoretical framework for diffusion-based image editing by formulating it as a reverse-time bridge modeling problem. This approach modifies the backward process of a pretrained diffusion model to construct a bridge that converges to an implicit distribution associated with the editing target at time 0. Building on this framework, we propose h-Edit, a novel editing method that utilizes Doob's h-transform and Langevin Monte Carlo to decompose the update of an intermediate edited sample into two components: a \"reconstruction\" term and an \"editing\" term. This decomposition provides "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02187","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/2503.02187/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":"2503.02187","created_at":"2026-07-05T10:23:38.878964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02187v1","created_at":"2026-07-05T10:23:38.878964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02187","created_at":"2026-07-05T10:23:38.878964+00:00"},{"alias_kind":"pith_short_12","alias_value":"CM5VTUNYHC6F","created_at":"2026-07-05T10:23:38.878964+00:00"},{"alias_kind":"pith_short_16","alias_value":"CM5VTUNYHC6FYD5L","created_at":"2026-07-05T10:23:38.878964+00:00"},{"alias_kind":"pith_short_8","alias_value":"CM5VTUNY","created_at":"2026-07-05T10:23:38.878964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06924","citing_title":"Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6","json":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6.json","graph_json":"https://pith.science/api/pith-number/CM5VTUNYHC6FYD5LGLKLQUM5P6/graph.json","events_json":"https://pith.science/api/pith-number/CM5VTUNYHC6FYD5LGLKLQUM5P6/events.json","paper":"https://pith.science/paper/CM5VTUNY"},"agent_actions":{"view_html":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6","download_json":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6.json","view_paper":"https://pith.science/paper/CM5VTUNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02187&json=true","fetch_graph":"https://pith.science/api/pith-number/CM5VTUNYHC6FYD5LGLKLQUM5P6/graph.json","fetch_events":"https://pith.science/api/pith-number/CM5VTUNYHC6FYD5LGLKLQUM5P6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6/action/storage_attestation","attest_author":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6/action/author_attestation","sign_citation":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6/action/citation_signature","submit_replication":"https://pith.science/pith/CM5VTUNYHC6FYD5LGLKLQUM5P6/action/replication_record"}},"created_at":"2026-07-05T10:23:38.878964+00:00","updated_at":"2026-07-05T10:23:38.878964+00:00"}