{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q3K3M73XMB2VIAHXBHP7TVZLLX","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":"08654609bc6c7e9dff523354035d43031b922b40108666db12a7210609973d52","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:43:38Z","title_canon_sha256":"c7fbdcfffbcb214aa3c47f912cf2eebac4ec6728e82d797ea07eeb1800c84f9e"},"schema_version":"1.0","source":{"id":"2305.10400","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10400","created_at":"2026-07-05T07:27:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10400v4","created_at":"2026-07-05T07:27:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10400","created_at":"2026-07-05T07:27:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q3K3M73XMB2V","created_at":"2026-07-05T07:27:45Z"},{"alias_kind":"pith_short_16","alias_value":"Q3K3M73XMB2VIAHX","created_at":"2026-07-05T07:27:45Z"},{"alias_kind":"pith_short_8","alias_value":"Q3K3M73X","created_at":"2026-07-05T07:27:45Z"}],"graph_snapshots":[{"event_id":"sha256:571df1686b0a88153355fd9a5b51c6d912720ae92c19cebe40d2ff76e29f584a","target":"graph","created_at":"2026-07-05T07:27:45Z","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/2305.10400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In this work, we study methods for automatic text-image alignment evaluation. We first introduce SeeTRUE: a comprehensive evaluation set, spanning multiple datasets from both text-to-image and image-to-text generation tasks, with human judgements for whether a given text-image pair is semantically aligned. We then describe two automatic methods to determine alignment: the first i","authors_text":"Eran Ofek, Idan Szpektor, Jonathan Herzig, Michal Yarom, Oran Lang, Roee Aharoni, Soravit Changpinyo, Yonatan Bitton","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:43:38Z","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10400","kind":"arxiv","version":4},"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":"sha256:9f5d11e9575817850c3aa4bb0b3fde35d1fc38e522f11141be908904abec8525","target":"record","created_at":"2026-07-05T07:27:45Z","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":"08654609bc6c7e9dff523354035d43031b922b40108666db12a7210609973d52","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:43:38Z","title_canon_sha256":"c7fbdcfffbcb214aa3c47f912cf2eebac4ec6728e82d797ea07eeb1800c84f9e"},"schema_version":"1.0","source":{"id":"2305.10400","kind":"arxiv","version":4}},"canonical_sha256":"86d5b67f7760755400f709dff9d72b5dfeb2313580ada2dc265a2a9abe0d4be1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86d5b67f7760755400f709dff9d72b5dfeb2313580ada2dc265a2a9abe0d4be1","first_computed_at":"2026-07-05T07:27:45.570857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:45.570857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BZxzcqepLWdKAUCSWHuEV1M95uqkWQgyI4rw2+obi7PqmU3ylnUVtm9X18Ozr5QxtJWMCGNs1Ghhd7iLc1NXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:45.571289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10400","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f5d11e9575817850c3aa4bb0b3fde35d1fc38e522f11141be908904abec8525","sha256:571df1686b0a88153355fd9a5b51c6d912720ae92c19cebe40d2ff76e29f584a"],"state_sha256":"cb895436c8c097bd9af84eb3ed149d0bf4a616309767b0a4352b32e00bd7942d"}