{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2HW2O4MDVBS64AOTSX4NEZRMTK","short_pith_number":"pith:2HW2O4MD","schema_version":"1.0","canonical_sha256":"d1eda77183a865ee01d395f8d2662c9a8e9df29e48cbce4bfcd70f8a1d4ccfdf","source":{"kind":"arxiv","id":"2408.00760","version":2},"attestation_state":"computed","paper":{"title":"Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Susung Hong","submitted_at":"2024-08-01T17:59:09Z","abstract_excerpt":"Conditional diffusion models have shown remarkable success in visual content generation, producing high-quality samples across various domains, largely due to classifier-free guidance (CFG). Recent attempts to extend guidance to unconditional models have relied on heuristic techniques, resulting in suboptimal generation quality and unintended effects. In this work, we propose Smoothed Energy Guidance (SEG), a novel training- and condition-free approach that leverages the energy-based perspective of the self-attention mechanism to enhance image generation. By defining the energy of self-attenti"},"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":"2408.00760","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:59:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d6542c489ed55afdaa5ae973c8c63442967cc34b5a80ee4f0222548b7b4155af","abstract_canon_sha256":"639a2d1defebcccd7fb0e03c09e9d62e02cb23dc642205a6b4ff84508efe622c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:55.424363Z","signature_b64":"Ll/eXhG70eY+5CPVxUl0Co7Aqgfa/Hbuj1JxCCyqD9we0sUCzLJRLQFAMK5SwZtYzLJtxoOaQkq31dtccj+uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1eda77183a865ee01d395f8d2662c9a8e9df29e48cbce4bfcd70f8a1d4ccfdf","last_reissued_at":"2026-07-05T09:13:55.423789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:55.423789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Susung Hong","submitted_at":"2024-08-01T17:59:09Z","abstract_excerpt":"Conditional diffusion models have shown remarkable success in visual content generation, producing high-quality samples across various domains, largely due to classifier-free guidance (CFG). Recent attempts to extend guidance to unconditional models have relied on heuristic techniques, resulting in suboptimal generation quality and unintended effects. In this work, we propose Smoothed Energy Guidance (SEG), a novel training- and condition-free approach that leverages the energy-based perspective of the self-attention mechanism to enhance image generation. By defining the energy of self-attenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00760","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/2408.00760/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":"2408.00760","created_at":"2026-07-05T09:13:55.423852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00760v2","created_at":"2026-07-05T09:13:55.423852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00760","created_at":"2026-07-05T09:13:55.423852+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HW2O4MDVBS6","created_at":"2026-07-05T09:13:55.423852+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HW2O4MDVBS64AOT","created_at":"2026-07-05T09:13:55.423852+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HW2O4MD","created_at":"2026-07-05T09:13:55.423852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31162","citing_title":"Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.13419","citing_title":"Diffusion Models Memorize in Training -- and Generalize in Inference","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23536","citing_title":"$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK","json":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK.json","graph_json":"https://pith.science/api/pith-number/2HW2O4MDVBS64AOTSX4NEZRMTK/graph.json","events_json":"https://pith.science/api/pith-number/2HW2O4MDVBS64AOTSX4NEZRMTK/events.json","paper":"https://pith.science/paper/2HW2O4MD"},"agent_actions":{"view_html":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK","download_json":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK.json","view_paper":"https://pith.science/paper/2HW2O4MD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00760&json=true","fetch_graph":"https://pith.science/api/pith-number/2HW2O4MDVBS64AOTSX4NEZRMTK/graph.json","fetch_events":"https://pith.science/api/pith-number/2HW2O4MDVBS64AOTSX4NEZRMTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK/action/storage_attestation","attest_author":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK/action/author_attestation","sign_citation":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK/action/citation_signature","submit_replication":"https://pith.science/pith/2HW2O4MDVBS64AOTSX4NEZRMTK/action/replication_record"}},"created_at":"2026-07-05T09:13:55.423852+00:00","updated_at":"2026-07-05T09:13:55.423852+00:00"}