{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C345WQQW7CLEUTU3WBGBAYIXTO","short_pith_number":"pith:C345WQQW","schema_version":"1.0","canonical_sha256":"16f9db4216f8964a4e9bb04c1061179bb4668acdbfe6f673c926624095beaf4d","source":{"kind":"arxiv","id":"2208.08664","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bahjat Kawar, Michael Elad, Roy Ganz","submitted_at":"2022-08-18T06:51:23Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients from a time-dependent classifier. While the idea is theoretically sound, deep learning-based classifiers are infamously susceptible to gradient-based adversarial attacks. Therefore, while traditional classifiers may achieve good accuracy scores, their gradients are possibly unreliable and might hinder the improvement of the generation results. Recent work dis"},"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":"2208.08664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-18T06:51:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18bd29e531783a8c9d47d9c5cc3af35911d8dc8c64ef63f50bf1cc1409e153e9","abstract_canon_sha256":"8924bf4658aa9f87eab5a3c53bd2349cae15928464cafa276cc72c5376483af2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:41.387842Z","signature_b64":"GZs9Qyl/f9gwgWHtv/mE/krWfg1mvQlz67m12BfN7VQU1fGy4EtpS0n7eURJA32mw4nQ30PpHwPYOfllbXm0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16f9db4216f8964a4e9bb04c1061179bb4668acdbfe6f673c926624095beaf4d","last_reissued_at":"2026-07-05T05:51:41.387452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:41.387452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bahjat Kawar, Michael Elad, Roy Ganz","submitted_at":"2022-08-18T06:51:23Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) are a recent family of generative models that achieve state-of-the-art results. In order to obtain class-conditional generation, it was suggested to guide the diffusion process by gradients from a time-dependent classifier. While the idea is theoretically sound, deep learning-based classifiers are infamously susceptible to gradient-based adversarial attacks. Therefore, while traditional classifiers may achieve good accuracy scores, their gradients are possibly unreliable and might hinder the improvement of the generation results. Recent work dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08664","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/2208.08664/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":"2208.08664","created_at":"2026-07-05T05:51:41.387518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08664v2","created_at":"2026-07-05T05:51:41.387518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08664","created_at":"2026-07-05T05:51:41.387518+00:00"},{"alias_kind":"pith_short_12","alias_value":"C345WQQW7CLE","created_at":"2026-07-05T05:51:41.387518+00:00"},{"alias_kind":"pith_short_16","alias_value":"C345WQQW7CLEUTU3","created_at":"2026-07-05T05:51:41.387518+00:00"},{"alias_kind":"pith_short_8","alias_value":"C345WQQW","created_at":"2026-07-05T05:51:41.387518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11087","citing_title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO","json":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO.json","graph_json":"https://pith.science/api/pith-number/C345WQQW7CLEUTU3WBGBAYIXTO/graph.json","events_json":"https://pith.science/api/pith-number/C345WQQW7CLEUTU3WBGBAYIXTO/events.json","paper":"https://pith.science/paper/C345WQQW"},"agent_actions":{"view_html":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO","download_json":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO.json","view_paper":"https://pith.science/paper/C345WQQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08664&json=true","fetch_graph":"https://pith.science/api/pith-number/C345WQQW7CLEUTU3WBGBAYIXTO/graph.json","fetch_events":"https://pith.science/api/pith-number/C345WQQW7CLEUTU3WBGBAYIXTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO/action/storage_attestation","attest_author":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO/action/author_attestation","sign_citation":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO/action/citation_signature","submit_replication":"https://pith.science/pith/C345WQQW7CLEUTU3WBGBAYIXTO/action/replication_record"}},"created_at":"2026-07-05T05:51:41.387518+00:00","updated_at":"2026-07-05T05:51:41.387518+00:00"}