{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MLFV2KWQJU3J5GKQQ4QGPV3VJ4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9c27fd4ade2d4c9b223b5aed550b8d1c7c7a97ea6c1b770a6207a4fae2d7af42","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T18:02:22Z","title_canon_sha256":"8110e68ff9803ec2a201e1c65ec01e6073f199b3f736e27c7869eff8c56fe0e2"},"schema_version":"1.0","source":{"id":"2305.16397","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16397","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16397v3","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16397","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"MLFV2KWQJU3J","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"MLFV2KWQJU3J5GKQ","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"MLFV2KWQ","created_at":"2026-07-05T07:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:d5873391a6b7db48fdfb967fdca72f1a3781ea6df5fb8324a3e5c712a6370065","target":"graph","created_at":"2026-07-05T07:08:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.16397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Benno Krojer, Christopher Pal, Elinor Poole-Dayan, Siva Reddy, Vikram Voleti","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T18:02:22Z","title":"Are Diffusion Models Vision-And-Language Reasoners?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16397","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:65335a192eebb70bf260ee04ac6be7fc8cc041e53ec4765138e30a0970399339","target":"record","created_at":"2026-07-05T07:08:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9c27fd4ade2d4c9b223b5aed550b8d1c7c7a97ea6c1b770a6207a4fae2d7af42","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T18:02:22Z","title_canon_sha256":"8110e68ff9803ec2a201e1c65ec01e6073f199b3f736e27c7869eff8c56fe0e2"},"schema_version":"1.0","source":{"id":"2305.16397","kind":"arxiv","version":3}},"canonical_sha256":"62cb5d2ad04d369e9950872067d7754f0d291ba3c5ae34bc0755e801b63e479b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62cb5d2ad04d369e9950872067d7754f0d291ba3c5ae34bc0755e801b63e479b","first_computed_at":"2026-07-05T07:08:28.593836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:28.593836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JjUsmczFNiQ2lkCBUgVLM/dmT5R4+lOmbgeEFlxG1oyoPzijbmMDs/h8+JP5/liGF7mpMZwpb006wnC2n/zXCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:28.594330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16397","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65335a192eebb70bf260ee04ac6be7fc8cc041e53ec4765138e30a0970399339","sha256:d5873391a6b7db48fdfb967fdca72f1a3781ea6df5fb8324a3e5c712a6370065"],"state_sha256":"406da8acb9be50ebd65d057347df3dd5e96d8cc477d02881ff1668e420f545ea"}