{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I5AXVHDIX5FG2C3WDXIKG2W4FF","short_pith_number":"pith:I5AXVHDI","schema_version":"1.0","canonical_sha256":"47417a9c68bf4a6d0b761dd0a36adc294464b4a6ba8c0583ae3205c0a256777c","source":{"kind":"arxiv","id":"2404.08799","version":1},"attestation_state":"computed","paper":{"title":"Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brinnae Bent","submitted_at":"2024-04-12T20:16:03Z","abstract_excerpt":"In this study, we identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP (Contrastive Language-Image Pretraining) score as our semantic consistency score. We applied this metric to compare two state-of-the-art open-source image generation diffusion models, Stable Diffusion XL and PixArt-{\\alpha}, and we found statistically significant differences between the semantic consistency scores for the models. Agreement between the Semantic Consistency Score sele"},"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":"2404.08799","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-12T20:16:03Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"5c0475ce5e3e7816f74df3908450ca9191fa43a089d54d40f2b7e9f9acf36aa6","abstract_canon_sha256":"898d30981c4ae80df4eb4fd231e0004af11e6562e151eeb204360585b6915a91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:40.459495Z","signature_b64":"wYaurw2l5xjguIQSnqYvdbacXXsr4/FwfKQ1Oyi/i5abXkaucksApLaDT+2nEQ/WPq0K4kczbEf2G4aM/UDzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47417a9c68bf4a6d0b761dd0a36adc294464b4a6ba8c0583ae3205c0a256777c","last_reissued_at":"2026-07-05T08:07:40.458896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:40.458896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brinnae Bent","submitted_at":"2024-04-12T20:16:03Z","abstract_excerpt":"In this study, we identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP (Contrastive Language-Image Pretraining) score as our semantic consistency score. We applied this metric to compare two state-of-the-art open-source image generation diffusion models, Stable Diffusion XL and PixArt-{\\alpha}, and we found statistically significant differences between the semantic consistency scores for the models. Agreement between the Semantic Consistency Score sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08799","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/2404.08799/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":"2404.08799","created_at":"2026-07-05T08:07:40.458965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08799v1","created_at":"2026-07-05T08:07:40.458965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08799","created_at":"2026-07-05T08:07:40.458965+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5AXVHDIX5FG","created_at":"2026-07-05T08:07:40.458965+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5AXVHDIX5FG2C3W","created_at":"2026-07-05T08:07:40.458965+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5AXVHDI","created_at":"2026-07-05T08:07:40.458965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24211","citing_title":"Are Any-to-Any Models More Consistent Across Modality Transfers Than Specialists?","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF","json":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF.json","graph_json":"https://pith.science/api/pith-number/I5AXVHDIX5FG2C3WDXIKG2W4FF/graph.json","events_json":"https://pith.science/api/pith-number/I5AXVHDIX5FG2C3WDXIKG2W4FF/events.json","paper":"https://pith.science/paper/I5AXVHDI"},"agent_actions":{"view_html":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF","download_json":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF.json","view_paper":"https://pith.science/paper/I5AXVHDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08799&json=true","fetch_graph":"https://pith.science/api/pith-number/I5AXVHDIX5FG2C3WDXIKG2W4FF/graph.json","fetch_events":"https://pith.science/api/pith-number/I5AXVHDIX5FG2C3WDXIKG2W4FF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF/action/storage_attestation","attest_author":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF/action/author_attestation","sign_citation":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF/action/citation_signature","submit_replication":"https://pith.science/pith/I5AXVHDIX5FG2C3WDXIKG2W4FF/action/replication_record"}},"created_at":"2026-07-05T08:07:40.458965+00:00","updated_at":"2026-07-05T08:07:40.458965+00:00"}