{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5AV55TM7M2RN2NV32U63HCKOT5","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":"b04a0d252c7a10153e601848282ae57cf08e3e1800bc024f7310964ac59e9f63","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T17:00:16Z","title_canon_sha256":"e8009795a46ed2c80cccf6208ce0cf813be8f4b374a5cb221ed6a97fded5c410"},"schema_version":"1.0","source":{"id":"2305.03689","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03689","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03689v3","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03689","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"5AV55TM7M2RN","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"5AV55TM7M2RN2NV3","created_at":"2026-07-05T07:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"5AV55TM7","created_at":"2026-07-05T07:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:9f9e7edcedabd3ce8254f391973867324bc986412001a04c1e5b9deb9f2dffc4","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/2305.03689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of compositional capability, we design Cola, a text-to-image retrieval benchmark to Compose Objects Localized with Attributes. To solve Cola, a model must retrieve images with the correct configuration of attributes and objects and avoid choosing a distractor image with the same objects and attributes but in the wrong configuration. Cola contains about 1.2k compo","authors_text":"Abhimanyu Dubey, Arijit Ray, Bryan A. Plummer, Filip Radenovic, Kate Saenko, Ranjay Krishna","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T17:00:16Z","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03689","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:f72f463f2efdfae084dc41e0549e0a70cc15e01cf0b4b1dd705f18ea6434b3ca","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":"b04a0d252c7a10153e601848282ae57cf08e3e1800bc024f7310964ac59e9f63","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T17:00:16Z","title_canon_sha256":"e8009795a46ed2c80cccf6208ce0cf813be8f4b374a5cb221ed6a97fded5c410"},"schema_version":"1.0","source":{"id":"2305.03689","kind":"arxiv","version":3}},"canonical_sha256":"e82bdecd9f66a2dd36bbd53db3894e9f7a11dadb1d8ea25db7cf5320914158e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e82bdecd9f66a2dd36bbd53db3894e9f7a11dadb1d8ea25db7cf5320914158e2","first_computed_at":"2026-07-05T07:08:28.260287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:28.260287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YLm2EmYWjns7oKMM0N65Zza3CkG323/rC0236b94GwE64nFmrU76iekBiHix3VxRQoKdszc+tIlL++igp+r/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:28.260733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03689","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f72f463f2efdfae084dc41e0549e0a70cc15e01cf0b4b1dd705f18ea6434b3ca","sha256:9f9e7edcedabd3ce8254f391973867324bc986412001a04c1e5b9deb9f2dffc4"],"state_sha256":"01f57e0917be7034b46a87e3c25a0a230f4d737a296a59babad63ca2f0edd42e"}