{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R6A27DVJONH2M5YEXOXVKUIXWS","short_pith_number":"pith:R6A27DVJ","schema_version":"1.0","canonical_sha256":"8f81af8ea9734fa67704bbaf555117b490031651e6f3ddef0f38ee141634eab9","source":{"kind":"arxiv","id":"2511.16527","version":2},"attestation_state":"computed","paper":{"title":"Contrastive vision-language learning with paraphrasing and negation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Artur d'Avila Garcez, Joe Townsend, Kwun Ho Ngan, Saman Sadeghi Afgeh","submitted_at":"2025-11-20T16:41:36Z","abstract_excerpt":"Contrastive vision-language models continue to be the dominant approach for image-text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks to align their image and text embeddings in a shared latent space. As a challenging case-study for neurosymbolic AI, recent results evaluating CLIP on negated or paraphrased text have shown mixed performance as these are difficult to define formally for text data. Negation produces the opposite meaning using various possible but small lexical changes. Paraphrasing may use very different textual expressions to denote essentia"},"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":"2511.16527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-20T16:41:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66c5cecf472b72274305054d556fad2e030a42deba92e0dddf1c0338d7f754e8","abstract_canon_sha256":"53757e7245d4c2e6008cb0b01ae77f28302a0614f137e9f60194b1a2a4e653b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:11.744978Z","signature_b64":"SKvYLtnvngf427XSEmkbh4rxZSOp5A03XZHWd8mLplRiNpgBr6J9UKqkRuvM5+23XgHpVnnQZim9TkZChJ+AAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f81af8ea9734fa67704bbaf555117b490031651e6f3ddef0f38ee141634eab9","last_reissued_at":"2026-06-30T02:17:11.744336Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:11.744336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive vision-language learning with paraphrasing and negation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Artur d'Avila Garcez, Joe Townsend, Kwun Ho Ngan, Saman Sadeghi Afgeh","submitted_at":"2025-11-20T16:41:36Z","abstract_excerpt":"Contrastive vision-language models continue to be the dominant approach for image-text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks to align their image and text embeddings in a shared latent space. As a challenging case-study for neurosymbolic AI, recent results evaluating CLIP on negated or paraphrased text have shown mixed performance as these are difficult to define formally for text data. Negation produces the opposite meaning using various possible but small lexical changes. Paraphrasing may use very different textual expressions to denote essentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16527","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/2511.16527/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":"2511.16527","created_at":"2026-06-30T02:17:11.744412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.16527v2","created_at":"2026-06-30T02:17:11.744412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16527","created_at":"2026-06-30T02:17:11.744412+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6A27DVJONH2","created_at":"2026-06-30T02:17:11.744412+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6A27DVJONH2M5YE","created_at":"2026-06-30T02:17:11.744412+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6A27DVJ","created_at":"2026-06-30T02:17:11.744412+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/R6A27DVJONH2M5YEXOXVKUIXWS","json":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS.json","graph_json":"https://pith.science/api/pith-number/R6A27DVJONH2M5YEXOXVKUIXWS/graph.json","events_json":"https://pith.science/api/pith-number/R6A27DVJONH2M5YEXOXVKUIXWS/events.json","paper":"https://pith.science/paper/R6A27DVJ"},"agent_actions":{"view_html":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS","download_json":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS.json","view_paper":"https://pith.science/paper/R6A27DVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.16527&json=true","fetch_graph":"https://pith.science/api/pith-number/R6A27DVJONH2M5YEXOXVKUIXWS/graph.json","fetch_events":"https://pith.science/api/pith-number/R6A27DVJONH2M5YEXOXVKUIXWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS/action/storage_attestation","attest_author":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS/action/author_attestation","sign_citation":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS/action/citation_signature","submit_replication":"https://pith.science/pith/R6A27DVJONH2M5YEXOXVKUIXWS/action/replication_record"}},"created_at":"2026-06-30T02:17:11.744412+00:00","updated_at":"2026-06-30T02:17:11.744412+00:00"}