{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MLFV2KWQJU3J5GKQQ4QGPV3VJ4","short_pith_number":"pith:MLFV2KWQ","schema_version":"1.0","canonical_sha256":"62cb5d2ad04d369e9950872067d7754f0d291ba3c5ae34bc0755e801b63e479b","source":{"kind":"arxiv","id":"2305.16397","version":3},"attestation_state":"computed","paper":{"title":"Are Diffusion Models Vision-And-Language Reasoners?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Benno Krojer, Christopher Pal, Elinor Poole-Dayan, Siva Reddy, Vikram Voleti","submitted_at":"2023-05-25T18:02:22Z","abstract_excerpt":"Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-"},"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":"2305.16397","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T18:02:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8110e68ff9803ec2a201e1c65ec01e6073f199b3f736e27c7869eff8c56fe0e2","abstract_canon_sha256":"9c27fd4ade2d4c9b223b5aed550b8d1c7c7a97ea6c1b770a6207a4fae2d7af42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:28.594330Z","signature_b64":"JjUsmczFNiQ2lkCBUgVLM/dmT5R4+lOmbgeEFlxG1oyoPzijbmMDs/h8+JP5/liGF7mpMZwpb006wnC2n/zXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62cb5d2ad04d369e9950872067d7754f0d291ba3c5ae34bc0755e801b63e479b","last_reissued_at":"2026-07-05T07:08:28.593836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:28.593836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Diffusion Models Vision-And-Language Reasoners?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Benno Krojer, Christopher Pal, Elinor Poole-Dayan, Siva Reddy, Vikram Voleti","submitted_at":"2023-05-25T18:02:22Z","abstract_excerpt":"Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16397","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/2305.16397/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":"2305.16397","created_at":"2026-07-05T07:08:28.593898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16397v3","created_at":"2026-07-05T07:08:28.593898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16397","created_at":"2026-07-05T07:08:28.593898+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLFV2KWQJU3J","created_at":"2026-07-05T07:08:28.593898+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLFV2KWQJU3J5GKQ","created_at":"2026-07-05T07:08:28.593898+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLFV2KWQ","created_at":"2026-07-05T07:08:28.593898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01084","citing_title":"Kernel-Based LMI Approaches to Solving the Hamilton-Jacobi-Bellman Equation and Nonlinear Optimal Control","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4","json":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4.json","graph_json":"https://pith.science/api/pith-number/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/graph.json","events_json":"https://pith.science/api/pith-number/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/events.json","paper":"https://pith.science/paper/MLFV2KWQ"},"agent_actions":{"view_html":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4","download_json":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4.json","view_paper":"https://pith.science/paper/MLFV2KWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16397&json=true","fetch_graph":"https://pith.science/api/pith-number/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/action/storage_attestation","attest_author":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/action/author_attestation","sign_citation":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/action/citation_signature","submit_replication":"https://pith.science/pith/MLFV2KWQJU3J5GKQQ4QGPV3VJ4/action/replication_record"}},"created_at":"2026-07-05T07:08:28.593898+00:00","updated_at":"2026-07-05T07:08:28.593898+00:00"}