{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7RWLEY7P3LSSTO6UG7PS25NQWM","short_pith_number":"pith:7RWLEY7P","schema_version":"1.0","canonical_sha256":"fc6cb263efdae529bbd437df2d75b0b3281c19dd10da7b0b2f75fb40088fc995","source":{"kind":"arxiv","id":"2302.08357","version":3},"attestation_state":"computed","paper":{"title":"Boundary Guided Learning-Free Semantic Control with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Olga Russakovsky, Yan Yan, Ye Zhu, Yu Wu, Zhiwei Deng","submitted_at":"2023-02-16T15:21:46Z","abstract_excerpt":"Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary editing networks in the existing literature. In this work, we present our BoundaryDiffusion method for efficient, effective and light-weight semantic control with frozen pre-trained DDMs, without learning any extra networks. As one of the first learning-free diffusion editing works, we start by seeking a comprehensive understanding of the intermediate high-dimensional latent spaces by theoretically and empirically a"},"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":"2302.08357","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-16T15:21:46Z","cross_cats_sorted":[],"title_canon_sha256":"385d2cbc396302cef8c49c92ee391f2d9d629e128643dbd4e514d8c7831c794c","abstract_canon_sha256":"4e9a699e4e6281591a547f0ba31a2ab5be99fa5a00cd993ca828b6ed46a49baf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:59.075062Z","signature_b64":"xc7I/qenj8W2qGYyENa2gR6ga+QVf7JNML1N2TlXKcsDhaBMr+Sj2aIEPGY9/ehpsyx8Lkxi8lmDkSwv+8nHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc6cb263efdae529bbd437df2d75b0b3281c19dd10da7b0b2f75fb40088fc995","last_reissued_at":"2026-07-05T07:01:59.074568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:59.074568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boundary Guided Learning-Free Semantic Control with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Olga Russakovsky, Yan Yan, Ye Zhu, Yu Wu, Zhiwei Deng","submitted_at":"2023-02-16T15:21:46Z","abstract_excerpt":"Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary editing networks in the existing literature. In this work, we present our BoundaryDiffusion method for efficient, effective and light-weight semantic control with frozen pre-trained DDMs, without learning any extra networks. As one of the first learning-free diffusion editing works, we start by seeking a comprehensive understanding of the intermediate high-dimensional latent spaces by theoretically and empirically a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.08357","kind":"arxiv","version":3},"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/2302.08357/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":"2302.08357","created_at":"2026-07-05T07:01:59.074625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.08357v3","created_at":"2026-07-05T07:01:59.074625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.08357","created_at":"2026-07-05T07:01:59.074625+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RWLEY7P3LSS","created_at":"2026-07-05T07:01:59.074625+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RWLEY7P3LSSTO6U","created_at":"2026-07-05T07:01:59.074625+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RWLEY7P","created_at":"2026-07-05T07:01:59.074625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14524","citing_title":"Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusion","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM","json":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM.json","graph_json":"https://pith.science/api/pith-number/7RWLEY7P3LSSTO6UG7PS25NQWM/graph.json","events_json":"https://pith.science/api/pith-number/7RWLEY7P3LSSTO6UG7PS25NQWM/events.json","paper":"https://pith.science/paper/7RWLEY7P"},"agent_actions":{"view_html":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM","download_json":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM.json","view_paper":"https://pith.science/paper/7RWLEY7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.08357&json=true","fetch_graph":"https://pith.science/api/pith-number/7RWLEY7P3LSSTO6UG7PS25NQWM/graph.json","fetch_events":"https://pith.science/api/pith-number/7RWLEY7P3LSSTO6UG7PS25NQWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM/action/storage_attestation","attest_author":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM/action/author_attestation","sign_citation":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM/action/citation_signature","submit_replication":"https://pith.science/pith/7RWLEY7P3LSSTO6UG7PS25NQWM/action/replication_record"}},"created_at":"2026-07-05T07:01:59.074625+00:00","updated_at":"2026-07-05T07:01:59.074625+00:00"}