{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5AV55TM7M2RN2NV32U63HCKOT5","short_pith_number":"pith:5AV55TM7","schema_version":"1.0","canonical_sha256":"e82bdecd9f66a2dd36bbd53db3894e9f7a11dadb1d8ea25db7cf5320914158e2","source":{"kind":"arxiv","id":"2305.03689","version":3},"attestation_state":"computed","paper":{"title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhimanyu Dubey, Arijit Ray, Bryan A. Plummer, Filip Radenovic, Kate Saenko, Ranjay Krishna","submitted_at":"2023-05-05T17:00:16Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.03689","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-05T17:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"e8009795a46ed2c80cccf6208ce0cf813be8f4b374a5cb221ed6a97fded5c410","abstract_canon_sha256":"b04a0d252c7a10153e601848282ae57cf08e3e1800bc024f7310964ac59e9f63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:28.260733Z","signature_b64":"YLm2EmYWjns7oKMM0N65Zza3CkG323/rC0236b94GwE64nFmrU76iekBiHix3VxRQoKdszc+tIlL++igp+r/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e82bdecd9f66a2dd36bbd53db3894e9f7a11dadb1d8ea25db7cf5320914158e2","last_reissued_at":"2026-07-05T07:08:28.260287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:28.260287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhimanyu Dubey, Arijit Ray, Bryan A. Plummer, Filip Radenovic, Kate Saenko, Ranjay Krishna","submitted_at":"2023-05-05T17:00:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03689","kind":"arxiv","version":3},"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/2305.03689/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.03689","created_at":"2026-07-05T07:08:28.260350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03689v3","created_at":"2026-07-05T07:08:28.260350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03689","created_at":"2026-07-05T07:08:28.260350+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AV55TM7M2RN","created_at":"2026-07-05T07:08:28.260350+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AV55TM7M2RN2NV3","created_at":"2026-07-05T07:08:28.260350+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AV55TM7","created_at":"2026-07-05T07:08:28.260350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5","json":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5.json","graph_json":"https://pith.science/api/pith-number/5AV55TM7M2RN2NV32U63HCKOT5/graph.json","events_json":"https://pith.science/api/pith-number/5AV55TM7M2RN2NV32U63HCKOT5/events.json","paper":"https://pith.science/paper/5AV55TM7"},"agent_actions":{"view_html":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5","download_json":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5.json","view_paper":"https://pith.science/paper/5AV55TM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03689&json=true","fetch_graph":"https://pith.science/api/pith-number/5AV55TM7M2RN2NV32U63HCKOT5/graph.json","fetch_events":"https://pith.science/api/pith-number/5AV55TM7M2RN2NV32U63HCKOT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5/action/storage_attestation","attest_author":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5/action/author_attestation","sign_citation":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5/action/citation_signature","submit_replication":"https://pith.science/pith/5AV55TM7M2RN2NV32U63HCKOT5/action/replication_record"}},"created_at":"2026-07-05T07:08:28.260350+00:00","updated_at":"2026-07-05T07:08:28.260350+00:00"}