{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ULEM7OORTBX2GWADLFPRQCHGVF","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":"b09330b52e11305676840d7577cb8658d49221b6f6b4602f75e86f274078e309","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T17:56:24Z","title_canon_sha256":"468d890ac2ca152a98776ea58a1a5c980bcdd4f5c3b5eccb08e8617fc5f73596"},"schema_version":"1.0","source":{"id":"2404.19753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19753","created_at":"2026-07-05T08:13:56Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19753v1","created_at":"2026-07-05T08:13:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19753","created_at":"2026-07-05T08:13:56Z"},{"alias_kind":"pith_short_12","alias_value":"ULEM7OORTBX2","created_at":"2026-07-05T08:13:56Z"},{"alias_kind":"pith_short_16","alias_value":"ULEM7OORTBX2GWAD","created_at":"2026-07-05T08:13:56Z"},{"alias_kind":"pith_short_8","alias_value":"ULEM7OOR","created_at":"2026-07-05T08:13:56Z"}],"graph_snapshots":[{"event_id":"sha256:33e0c98224f2a913f2aeb6def101b7256e24ba62e90700f45c6197538f8d7340","target":"graph","created_at":"2026-07-05T08:13:56Z","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/2404.19753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language datasets are vital for both text-to-image (T2I) and image-to-text (I2T) research. However, current datasets lack descriptions with fine-grained detail that would allow for richer associations to be learned by models. To fill the gap, we introduce Descriptions of Connected and Contrasting Images (DOCCI), a dataset with long, human-annotated English descriptions for 15k images that were taken, curated and donated by a single researcher intent on capturing key challenges such as spatial relations, counting, text rendering, world knowledge, and more. We instruct human annotators to","authors_text":"Alexander Ku, Garrett Tanzer, Jaemin Cho, Jason Baldridge, Jordi Pont-Tuset, Roopal Garg, Sunayana Rane, Su Wang, Yasumasa Onoe, Yonatan Bitton, Zachary Berger, Zarana Parekh","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T17:56:24Z","title":"DOCCI: Descriptions of Connected and Contrasting Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19753","kind":"arxiv","version":1},"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":"sha256:12863e3327a651d66b13a65ba5bba4532ee22d94a5928f4ea63cfd7d8cdf880e","target":"record","created_at":"2026-07-05T08:13:56Z","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":"b09330b52e11305676840d7577cb8658d49221b6f6b4602f75e86f274078e309","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T17:56:24Z","title_canon_sha256":"468d890ac2ca152a98776ea58a1a5c980bcdd4f5c3b5eccb08e8617fc5f73596"},"schema_version":"1.0","source":{"id":"2404.19753","kind":"arxiv","version":1}},"canonical_sha256":"a2c8cfb9d1986fa35803595f1808e6a94b3839b544dfc485716044fc76e2c17b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2c8cfb9d1986fa35803595f1808e6a94b3839b544dfc485716044fc76e2c17b","first_computed_at":"2026-07-05T08:13:56.400652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:56.400652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCjgXcH/0ZGQrj7Ou2XtouB+4C7qDds/ttaOYCzjGRCin2HKBxF4lQU63QNoN3Zsbnhh5KFx9KmXxpAzEKGkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:56.401117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12863e3327a651d66b13a65ba5bba4532ee22d94a5928f4ea63cfd7d8cdf880e","sha256:33e0c98224f2a913f2aeb6def101b7256e24ba62e90700f45c6197538f8d7340"],"state_sha256":"fb07f682adcec54e0681d285065ee4cd199afbfc471742c4fbcd492d5c7cea98"}