{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ODFV7MT5QCAQ4U7GM5CLQI2CXT","short_pith_number":"pith:ODFV7MT5","schema_version":"1.0","canonical_sha256":"70cb5fb27d80810e53e66744b82342bcf7e93c2812291e41eae1580142059c89","source":{"kind":"arxiv","id":"2306.07196","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Enhanced Contrastive Vision-Text Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Alireza Fathi, Cordelia Schmid, Mathilde Caron","submitted_at":"2023-06-12T15:52:02Z","abstract_excerpt":"Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from the pre-training dataset. Hence, a key ingredient to their success has been the use of large-scale curated pre-training data aiming at expanding the set of concepts that they can memorize during the pre-training stage. In this work, we explore an alternative to encoding fine-grained knowledge directly into the model's parameters: we instead train the model t"},"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":"2306.07196","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T15:52:02Z","cross_cats_sorted":[],"title_canon_sha256":"e5e58c37e4baa09c828b6d04dd285760f8e6fc3043d7771401257ccc7dbfc4f7","abstract_canon_sha256":"e195f8e9ea611aa152c74ed1f0dcf44c98d551d89192584c018c20a13ad835dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:43.406433Z","signature_b64":"0P8eeRr7XAVswnNIn9BQj1J5aJ7yNNxaPsS88+hpzyihf/AV1nvwIxTxpOO4fzSFTZlgQkapgAqVfl7VSXNDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70cb5fb27d80810e53e66744b82342bcf7e93c2812291e41eae1580142059c89","last_reissued_at":"2026-07-05T07:47:43.405887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:43.405887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Enhanced Contrastive Vision-Text Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ahmet Iscen, Alireza Fathi, Cordelia Schmid, Mathilde Caron","submitted_at":"2023-06-12T15:52:02Z","abstract_excerpt":"Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from the pre-training dataset. Hence, a key ingredient to their success has been the use of large-scale curated pre-training data aiming at expanding the set of concepts that they can memorize during the pre-training stage. In this work, we explore an alternative to encoding fine-grained knowledge directly into the model's parameters: we instead train the model t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07196","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/2306.07196/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":"2306.07196","created_at":"2026-07-05T07:47:43.405949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07196v2","created_at":"2026-07-05T07:47:43.405949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07196","created_at":"2026-07-05T07:47:43.405949+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODFV7MT5QCAQ","created_at":"2026-07-05T07:47:43.405949+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODFV7MT5QCAQ4U7G","created_at":"2026-07-05T07:47:43.405949+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODFV7MT5","created_at":"2026-07-05T07:47:43.405949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT","json":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT.json","graph_json":"https://pith.science/api/pith-number/ODFV7MT5QCAQ4U7GM5CLQI2CXT/graph.json","events_json":"https://pith.science/api/pith-number/ODFV7MT5QCAQ4U7GM5CLQI2CXT/events.json","paper":"https://pith.science/paper/ODFV7MT5"},"agent_actions":{"view_html":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT","download_json":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT.json","view_paper":"https://pith.science/paper/ODFV7MT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07196&json=true","fetch_graph":"https://pith.science/api/pith-number/ODFV7MT5QCAQ4U7GM5CLQI2CXT/graph.json","fetch_events":"https://pith.science/api/pith-number/ODFV7MT5QCAQ4U7GM5CLQI2CXT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT/action/storage_attestation","attest_author":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT/action/author_attestation","sign_citation":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT/action/citation_signature","submit_replication":"https://pith.science/pith/ODFV7MT5QCAQ4U7GM5CLQI2CXT/action/replication_record"}},"created_at":"2026-07-05T07:47:43.405949+00:00","updated_at":"2026-07-05T07:47:43.405949+00:00"}