{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FO4JFUCVLLGY2I7DXBLM5FAXDL","short_pith_number":"pith:FO4JFUCV","schema_version":"1.0","canonical_sha256":"2bb892d0555acd8d23e3b856ce94171ae0e4168484780f7a3ff56b73be53407b","source":{"kind":"arxiv","id":"2109.10613","version":1},"attestation_state":"computed","paper":{"title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Bogin, Jonathan Berant, Matt Gardner, Shivanshu Gupta","submitted_at":"2021-09-22T09:25:41Z","abstract_excerpt":"While interest in models that generalize at test time to new compositions has risen in recent years, benchmarks in the visually-grounded domain have thus far been restricted to synthetic images. In this work, we propose COVR, a new test-bed for visually-grounded compositional generalization with real images. To create COVR, we use real images annotated with scene graphs, and propose an almost fully automatic procedure for generating question-answer pairs along with a set of context images. COVR focuses on questions that require complex reasoning, including higher-order operations such as quant"},"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":"2109.10613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-22T09:25:41Z","cross_cats_sorted":[],"title_canon_sha256":"8fe7e747f47ac2f96661baddeb269136800e2946c3e50e15928467f2bc61de9a","abstract_canon_sha256":"608cd7b6901138f4ad0913aa09fb8c833cab6ce8b4546ea348380fc264747a3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:38.212204Z","signature_b64":"IpufNzHOiv7TRYyoylBMnLKzXdVXu5wsOvN5Yl4JhYM8H+EQ4+SA+yWmeVZClj8YzL9i6ZzqniZ5+1Gg7VL4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bb892d0555acd8d23e3b856ce94171ae0e4168484780f7a3ff56b73be53407b","last_reissued_at":"2026-07-05T03:16:38.211736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:38.211736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Bogin, Jonathan Berant, Matt Gardner, Shivanshu Gupta","submitted_at":"2021-09-22T09:25:41Z","abstract_excerpt":"While interest in models that generalize at test time to new compositions has risen in recent years, benchmarks in the visually-grounded domain have thus far been restricted to synthetic images. In this work, we propose COVR, a new test-bed for visually-grounded compositional generalization with real images. To create COVR, we use real images annotated with scene graphs, and propose an almost fully automatic procedure for generating question-answer pairs along with a set of context images. COVR focuses on questions that require complex reasoning, including higher-order operations such as quant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10613","kind":"arxiv","version":1},"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/2109.10613/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":"2109.10613","created_at":"2026-07-05T03:16:38.211794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10613v1","created_at":"2026-07-05T03:16:38.211794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10613","created_at":"2026-07-05T03:16:38.211794+00:00"},{"alias_kind":"pith_short_12","alias_value":"FO4JFUCVLLGY","created_at":"2026-07-05T03:16:38.211794+00:00"},{"alias_kind":"pith_short_16","alias_value":"FO4JFUCVLLGY2I7D","created_at":"2026-07-05T03:16:38.211794+00:00"},{"alias_kind":"pith_short_8","alias_value":"FO4JFUCV","created_at":"2026-07-05T03:16:38.211794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06157","citing_title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL","json":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL.json","graph_json":"https://pith.science/api/pith-number/FO4JFUCVLLGY2I7DXBLM5FAXDL/graph.json","events_json":"https://pith.science/api/pith-number/FO4JFUCVLLGY2I7DXBLM5FAXDL/events.json","paper":"https://pith.science/paper/FO4JFUCV"},"agent_actions":{"view_html":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL","download_json":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL.json","view_paper":"https://pith.science/paper/FO4JFUCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10613&json=true","fetch_graph":"https://pith.science/api/pith-number/FO4JFUCVLLGY2I7DXBLM5FAXDL/graph.json","fetch_events":"https://pith.science/api/pith-number/FO4JFUCVLLGY2I7DXBLM5FAXDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL/action/storage_attestation","attest_author":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL/action/author_attestation","sign_citation":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL/action/citation_signature","submit_replication":"https://pith.science/pith/FO4JFUCVLLGY2I7DXBLM5FAXDL/action/replication_record"}},"created_at":"2026-07-05T03:16:38.211794+00:00","updated_at":"2026-07-05T03:16:38.211794+00:00"}