{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6EZUZRTRPWLRVFJYY7DGSTBNMY","short_pith_number":"pith:6EZUZRTR","schema_version":"1.0","canonical_sha256":"f1334cc6717d971a9538c7c6694c2d6621a9061e5f0af8f8a888805c7372295d","source":{"kind":"arxiv","id":"2607.10800","version":1},"attestation_state":"computed","paper":{"title":"h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changbo Wang, Junwei Shu, Long Chen, Yang Li, Zehui Guo, Zhen Wang","submitted_at":"2026-07-12T15:14:37Z","abstract_excerpt":"Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original image. Existing approaches either rely on inversion-based pipelines or heuristic source-to-target trajectory constructions, which often depend on architecture-specific designs or are sensitive to hyperparameters. In this paper, we propose h-Flow, a training-free and theoretically grounded flow-based editing framework. Inspired by Doob's $h$-Transform, we reformulate image editing as conditional generation under multip"},"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":"2607.10800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-12T15:14:37Z","cross_cats_sorted":[],"title_canon_sha256":"f8ec3837f6aac7f3f3697007c594c34b845f1fc4afbdd926a1110bf951cfdf8d","abstract_canon_sha256":"c4419d9b662159e1e5763c9c79d3fab34d7bafca3c29dcbe7859d5fa4136d88d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:40.887157Z","signature_b64":"o9g+TxDvnVCxKw/bUwjrGVMxw76R26Ix/tnGlvgWjCYiLjEIiUnk4UDupWV9Cg2hYbDrELALq3E6zlz3fbJzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1334cc6717d971a9538c7c6694c2d6621a9061e5f0af8f8a888805c7372295d","last_reissued_at":"2026-07-14T01:21:40.886328Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:40.886328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"h-Flow: Flexible Flow-based Image Editing via Doob's h-Transform","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changbo Wang, Junwei Shu, Long Chen, Yang Li, Zehui Guo, Zhen Wang","submitted_at":"2026-07-12T15:14:37Z","abstract_excerpt":"Editing images with pre-trained text-to-image flow models typically requires carefully balancing target alignment with the desired prompt and source consistency with the original image. Existing approaches either rely on inversion-based pipelines or heuristic source-to-target trajectory constructions, which often depend on architecture-specific designs or are sensitive to hyperparameters. In this paper, we propose h-Flow, a training-free and theoretically grounded flow-based editing framework. Inspired by Doob's $h$-Transform, we reformulate image editing as conditional generation under multip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10800","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/2607.10800/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":"2607.10800","created_at":"2026-07-14T01:21:40.886761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10800v1","created_at":"2026-07-14T01:21:40.886761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10800","created_at":"2026-07-14T01:21:40.886761+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EZUZRTRPWLR","created_at":"2026-07-14T01:21:40.886761+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EZUZRTRPWLRVFJY","created_at":"2026-07-14T01:21:40.886761+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EZUZRTR","created_at":"2026-07-14T01:21:40.886761+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/6EZUZRTRPWLRVFJYY7DGSTBNMY","json":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY.json","graph_json":"https://pith.science/api/pith-number/6EZUZRTRPWLRVFJYY7DGSTBNMY/graph.json","events_json":"https://pith.science/api/pith-number/6EZUZRTRPWLRVFJYY7DGSTBNMY/events.json","paper":"https://pith.science/paper/6EZUZRTR"},"agent_actions":{"view_html":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY","download_json":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY.json","view_paper":"https://pith.science/paper/6EZUZRTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10800&json=true","fetch_graph":"https://pith.science/api/pith-number/6EZUZRTRPWLRVFJYY7DGSTBNMY/graph.json","fetch_events":"https://pith.science/api/pith-number/6EZUZRTRPWLRVFJYY7DGSTBNMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY/action/storage_attestation","attest_author":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY/action/author_attestation","sign_citation":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY/action/citation_signature","submit_replication":"https://pith.science/pith/6EZUZRTRPWLRVFJYY7DGSTBNMY/action/replication_record"}},"created_at":"2026-07-14T01:21:40.886761+00:00","updated_at":"2026-07-14T01:21:40.886761+00:00"}