{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UKXVM6GZAX5CGTS2BABJTA4KTU","short_pith_number":"pith:UKXVM6GZ","canonical_record":{"source":{"id":"2404.01291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:58:06Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"4cd073d29a2790c1b795053c5ea9c08a7ff9f1f50f7bd23a82a73167a7c8af5b","abstract_canon_sha256":"7225e4e0bf457b5c9b8fbd5dee38e05774a32211de5f7d42ac2416b6103978ba"},"schema_version":"1.0"},"canonical_sha256":"a2af5678d905fa234e5a080299838a9d212a4d569ce1a9b470dcb6e907ee3e72","source":{"kind":"arxiv","id":"2404.01291","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01291","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01291v2","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01291","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"UKXVM6GZAX5C","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"UKXVM6GZAX5CGTS2","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"UKXVM6GZ","created_at":"2026-07-05T08:33:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UKXVM6GZAX5CGTS2BABJTA4KTU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:58:06Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"4cd073d29a2790c1b795053c5ea9c08a7ff9f1f50f7bd23a82a73167a7c8af5b","abstract_canon_sha256":"7225e4e0bf457b5c9b8fbd5dee38e05774a32211de5f7d42ac2416b6103978ba"},"schema_version":"1.0"},"canonical_sha256":"a2af5678d905fa234e5a080299838a9d212a4d569ce1a9b470dcb6e907ee3e72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:38.318642Z","signature_b64":"2jeRBZ46J6+X+kLwURVug+jTk6SEOSLiBYkA6FYBOwhbCaQlzbl6fINTgR42Rzo06/hxT+zmY/QotQFU9J4oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2af5678d905fa234e5a080299838a9d212a4d569ce1a9b470dcb6e907ee3e72","last_reissued_at":"2026-07-05T08:33:38.318130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:38.318130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01291","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:33:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2VSjQS2FCy2f7H663fTb+rd9kFa0CTFuUcOgdh6/hB9mswSkawRHyu9cInxEB9DXzM1DBxUOrcY95xCazXoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T08:26:36.082761Z"},"content_sha256":"a65ab6e5f4f4ebdb14daf7a6467919e4d5c656f63e7d75e150613495334324a0","schema_version":"1.0","event_id":"sha256:a65ab6e5f4f4ebdb14daf7a6467919e4d5c656f63e7d75e150613495334324a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UKXVM6GZAX5CGTS2BABJTA4KTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Baiqi Li, Deepak Pathak, Deva Ramanan, Graham Neubig, Jiayao Li, Pengchuan Zhang, Xide Xia, Zhiqiu Lin","submitted_at":"2024-04-01T17:58:06Z","abstract_excerpt":"Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a (generated) image and text prompt, but it fails to produce reliable scores for complex prompts involving compositions of objects, attributes, and relations. One reason is that text encoders of CLIP can notoriously act as a \"bag of words\", conflating prompts such as \"the horse is eating the grass\" with \"the grass is eating the horse\". To address this, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01291","kind":"arxiv","version":2},"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/2404.01291/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:33:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0z4viVY8VYKd32KPVScBc24raqe/1zKTHbp4KCvd0ohDXsFXkv3rtaH4ZLzyzErUJSuMzi4aKbHLqxhN3j01BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T08:26:36.083138Z"},"content_sha256":"233f2d1f7b4ebae251ac3d17338578c862a2e818be5e9c3003a0fcd88a5a801e","schema_version":"1.0","event_id":"sha256:233f2d1f7b4ebae251ac3d17338578c862a2e818be5e9c3003a0fcd88a5a801e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UKXVM6GZAX5CGTS2BABJTA4KTU/bundle.json","state_url":"https://pith.science/pith/UKXVM6GZAX5CGTS2BABJTA4KTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UKXVM6GZAX5CGTS2BABJTA4KTU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-25T08:26:36Z","links":{"resolver":"https://pith.science/pith/UKXVM6GZAX5CGTS2BABJTA4KTU","bundle":"https://pith.science/pith/UKXVM6GZAX5CGTS2BABJTA4KTU/bundle.json","state":"https://pith.science/pith/UKXVM6GZAX5CGTS2BABJTA4KTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UKXVM6GZAX5CGTS2BABJTA4KTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UKXVM6GZAX5CGTS2BABJTA4KTU","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":"7225e4e0bf457b5c9b8fbd5dee38e05774a32211de5f7d42ac2416b6103978ba","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:58:06Z","title_canon_sha256":"4cd073d29a2790c1b795053c5ea9c08a7ff9f1f50f7bd23a82a73167a7c8af5b"},"schema_version":"1.0","source":{"id":"2404.01291","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01291","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01291v2","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01291","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"UKXVM6GZAX5C","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"UKXVM6GZAX5CGTS2","created_at":"2026-07-05T08:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"UKXVM6GZ","created_at":"2026-07-05T08:33:38Z"}],"graph_snapshots":[{"event_id":"sha256:233f2d1f7b4ebae251ac3d17338578c862a2e818be5e9c3003a0fcd88a5a801e","target":"graph","created_at":"2026-07-05T08:33:38Z","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/2404.01291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a (generated) image and text prompt, but it fails to produce reliable scores for complex prompts involving compositions of objects, attributes, and relations. One reason is that text encoders of CLIP can notoriously act as a \"bag of words\", conflating prompts such as \"the horse is eating the grass\" with \"the grass is eating the horse\". To address this, we introduce","authors_text":"Baiqi Li, Deepak Pathak, Deva Ramanan, Graham Neubig, Jiayao Li, Pengchuan Zhang, Xide Xia, Zhiqiu Lin","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:58:06Z","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01291","kind":"arxiv","version":2},"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:a65ab6e5f4f4ebdb14daf7a6467919e4d5c656f63e7d75e150613495334324a0","target":"record","created_at":"2026-07-05T08:33:38Z","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":"7225e4e0bf457b5c9b8fbd5dee38e05774a32211de5f7d42ac2416b6103978ba","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T17:58:06Z","title_canon_sha256":"4cd073d29a2790c1b795053c5ea9c08a7ff9f1f50f7bd23a82a73167a7c8af5b"},"schema_version":"1.0","source":{"id":"2404.01291","kind":"arxiv","version":2}},"canonical_sha256":"a2af5678d905fa234e5a080299838a9d212a4d569ce1a9b470dcb6e907ee3e72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2af5678d905fa234e5a080299838a9d212a4d569ce1a9b470dcb6e907ee3e72","first_computed_at":"2026-07-05T08:33:38.318130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:38.318130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2jeRBZ46J6+X+kLwURVug+jTk6SEOSLiBYkA6FYBOwhbCaQlzbl6fINTgR42Rzo06/hxT+zmY/QotQFU9J4oDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:38.318642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01291","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a65ab6e5f4f4ebdb14daf7a6467919e4d5c656f63e7d75e150613495334324a0","sha256:233f2d1f7b4ebae251ac3d17338578c862a2e818be5e9c3003a0fcd88a5a801e"],"state_sha256":"038cf665bafea42420524df10637d0fb4de367fbf593904e2adc8d5fd0649f5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zcXc6/8rtYoHj4p1eVKWZRDVHefm7Uns1/q6mPBo9o7I6iF3IQ3RccHUjXCuTw6gXYWLDBzz/ti2GPQp/+m5AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T08:26:36.085285Z","bundle_sha256":"6a81e4cadbdf621d6cbf3966e572839a28b0c9f75818a4befe97bb7224153c9a"}}