{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IGNJ62YKSSQGOXX7BVRIXLCXOB","short_pith_number":"pith:IGNJ62YK","schema_version":"1.0","canonical_sha256":"419a9f6b0a94a0675eff0d628bac577047e9fbe6573bcabf6c6085c6c4248e93","source":{"kind":"arxiv","id":"2406.09952","version":2},"attestation_state":"computed","paper":{"title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ander Salaberria, Eneko Agirre, Gorka Azkune, Imanol Miranda","submitted_at":"2024-06-14T11:58:49Z","abstract_excerpt":"Existing Vision-Language Compositionality (VLC) benchmarks like SugarCrepe are formulated as image-to-text retrieval problems, where, given an image, the models need to select between the correct textual description and a synthetic hard negative text. In this work, we present the Bidirectional Vision-Language Compositionality (BiVLC) dataset. The novelty of BiVLC is to add a synthetic hard negative image generated from the synthetic text, resulting in two image-to-text retrieval examples (one for each image) and, more importantly, two text-to-image retrieval examples (one for each text). Human"},"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":"2406.09952","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-14T11:58:49Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"2d2d30e2324b90326525141c565367af2e630bec72236e8c8e6a0395a01a1e46","abstract_canon_sha256":"b0fb5acdee97fe6e143ec6335408cb6d5c46f9dd93380ccae8fd386fbc4822c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:17.162773Z","signature_b64":"uAFhjOV4L4OVCC8lnBQBIeB0UtySQLeXFxvtNsAo6gPz48lsaDKAmgdSMn3w00YH4ZK/hasaGHvvsBTROsDmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"419a9f6b0a94a0675eff0d628bac577047e9fbe6573bcabf6c6085c6c4248e93","last_reissued_at":"2026-07-05T09:30:17.162305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:17.162305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ander Salaberria, Eneko Agirre, Gorka Azkune, Imanol Miranda","submitted_at":"2024-06-14T11:58:49Z","abstract_excerpt":"Existing Vision-Language Compositionality (VLC) benchmarks like SugarCrepe are formulated as image-to-text retrieval problems, where, given an image, the models need to select between the correct textual description and a synthetic hard negative text. In this work, we present the Bidirectional Vision-Language Compositionality (BiVLC) dataset. The novelty of BiVLC is to add a synthetic hard negative image generated from the synthetic text, resulting in two image-to-text retrieval examples (one for each image) and, more importantly, two text-to-image retrieval examples (one for each text). Human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09952","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/2406.09952/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":"2406.09952","created_at":"2026-07-05T09:30:17.162370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09952v2","created_at":"2026-07-05T09:30:17.162370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09952","created_at":"2026-07-05T09:30:17.162370+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGNJ62YKSSQG","created_at":"2026-07-05T09:30:17.162370+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGNJ62YKSSQGOXX7","created_at":"2026-07-05T09:30:17.162370+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGNJ62YK","created_at":"2026-07-05T09:30:17.162370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02175","citing_title":"Understanding Space Is Rocket Science -- Only Top Reasoning Models Can Solve Spatial Understanding Tasks","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB","json":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB.json","graph_json":"https://pith.science/api/pith-number/IGNJ62YKSSQGOXX7BVRIXLCXOB/graph.json","events_json":"https://pith.science/api/pith-number/IGNJ62YKSSQGOXX7BVRIXLCXOB/events.json","paper":"https://pith.science/paper/IGNJ62YK"},"agent_actions":{"view_html":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB","download_json":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB.json","view_paper":"https://pith.science/paper/IGNJ62YK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09952&json=true","fetch_graph":"https://pith.science/api/pith-number/IGNJ62YKSSQGOXX7BVRIXLCXOB/graph.json","fetch_events":"https://pith.science/api/pith-number/IGNJ62YKSSQGOXX7BVRIXLCXOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB/action/storage_attestation","attest_author":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB/action/author_attestation","sign_citation":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB/action/citation_signature","submit_replication":"https://pith.science/pith/IGNJ62YKSSQGOXX7BVRIXLCXOB/action/replication_record"}},"created_at":"2026-07-05T09:30:17.162370+00:00","updated_at":"2026-07-05T09:30:17.162370+00:00"}