{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N7U5TSVOIND3LCLIFULSN7Y46K","short_pith_number":"pith:N7U5TSVO","schema_version":"1.0","canonical_sha256":"6fe9d9caae4347b589682d1726ff1cf29042d9bfff0c2f48cb5ce5481c232b64","source":{"kind":"arxiv","id":"2404.01292","version":1},"attestation_state":"computed","paper":{"title":"Measuring Style Similarity in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Anubhav Gupta, Gowthami Somepalli, Jonas Geiping, Kamal Gupta, Micah Goldblum, Shramay Palta, Tom Goldstein","submitted_at":"2024-04-01T17:58:30Z","abstract_excerpt":"Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine whether the properties of the image are attributable to specific training data, every time before a generated image is used for professional purposes. Existing tools for this purpose focus on retrieving images of similar semantic content. Meanwhile, many artists are concerned with style replication "},"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":"2404.01292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:58:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2595ca1194c3409e243489585a731a6b41218e4fa2e663322db5696646d4c7a0","abstract_canon_sha256":"bb2a161ac0bb754419b141ae81c12054102226538088a22bb56ce8ad1d7e530a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:04.075391Z","signature_b64":"MvPdH9NeuIA7aJqs6Wx8wsj4+r+LQtXiiflwvLbeOiRq/eGsLC+XyLsm9U4o4GAydqsJvILO/XTVdloGRi5vAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe9d9caae4347b589682d1726ff1cf29042d9bfff0c2f48cb5ce5481c232b64","last_reissued_at":"2026-07-05T08:03:04.074874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:04.074874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Style Similarity in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Anubhav Gupta, Gowthami Somepalli, Jonas Geiping, Kamal Gupta, Micah Goldblum, Shramay Palta, Tom Goldstein","submitted_at":"2024-04-01T17:58:30Z","abstract_excerpt":"Generative models are now widely used by graphic designers and artists. Prior works have shown that these models remember and often replicate content from their training data during generation. Hence as their proliferation increases, it has become important to perform a database search to determine whether the properties of the image are attributable to specific training data, every time before a generated image is used for professional purposes. Existing tools for this purpose focus on retrieving images of similar semantic content. Meanwhile, many artists are concerned with style replication "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01292","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/2404.01292/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":"2404.01292","created_at":"2026-07-05T08:03:04.074940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01292v1","created_at":"2026-07-05T08:03:04.074940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01292","created_at":"2026-07-05T08:03:04.074940+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7U5TSVOIND3","created_at":"2026-07-05T08:03:04.074940+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7U5TSVOIND3LCLI","created_at":"2026-07-05T08:03:04.074940+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7U5TSVO","created_at":"2026-07-05T08:03:04.074940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25465","citing_title":"EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26947","citing_title":"Scaling Multi-Reference Image Generation with Dynamic Reward Optimization","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26668","citing_title":"Disco-LoRA: Disentangled Composition of Content, Style, and Motion for Multi-concept Video Customization","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20506","citing_title":"FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14746","citing_title":"Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02144","citing_title":"Taxing Artificial Intelligence","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23657","citing_title":"OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01079","citing_title":"Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23657","citing_title":"OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12242","citing_title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23313","citing_title":"The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07561","citing_title":"PureCC: Pure Learning for Text-to-Image Concept Customization","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17500","citing_title":"The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20183","citing_title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19019","citing_title":"TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09030","citing_title":"When Style Similarity Scores Fail: Diagnosing Raw CSD Cosine in Artist-Style Evaluation","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08364","citing_title":"MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13509","citing_title":"DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17850","citing_title":"UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16114","citing_title":"Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K","json":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K.json","graph_json":"https://pith.science/api/pith-number/N7U5TSVOIND3LCLIFULSN7Y46K/graph.json","events_json":"https://pith.science/api/pith-number/N7U5TSVOIND3LCLIFULSN7Y46K/events.json","paper":"https://pith.science/paper/N7U5TSVO"},"agent_actions":{"view_html":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K","download_json":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K.json","view_paper":"https://pith.science/paper/N7U5TSVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01292&json=true","fetch_graph":"https://pith.science/api/pith-number/N7U5TSVOIND3LCLIFULSN7Y46K/graph.json","fetch_events":"https://pith.science/api/pith-number/N7U5TSVOIND3LCLIFULSN7Y46K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K/action/storage_attestation","attest_author":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K/action/author_attestation","sign_citation":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K/action/citation_signature","submit_replication":"https://pith.science/pith/N7U5TSVOIND3LCLIFULSN7Y46K/action/replication_record"}},"created_at":"2026-07-05T08:03:04.074940+00:00","updated_at":"2026-07-05T08:03:04.074940+00:00"}