{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ODFV7MT5QCAQ4U7GM5CLQI2CXT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e195f8e9ea611aa152c74ed1f0dcf44c98d551d89192584c018c20a13ad835dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T15:52:02Z","title_canon_sha256":"e5e58c37e4baa09c828b6d04dd285760f8e6fc3043d7771401257ccc7dbfc4f7"},"schema_version":"1.0","source":{"id":"2306.07196","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07196","created_at":"2026-07-05T07:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07196v2","created_at":"2026-07-05T07:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07196","created_at":"2026-07-05T07:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"ODFV7MT5QCAQ","created_at":"2026-07-05T07:47:43Z"},{"alias_kind":"pith_short_16","alias_value":"ODFV7MT5QCAQ4U7G","created_at":"2026-07-05T07:47:43Z"},{"alias_kind":"pith_short_8","alias_value":"ODFV7MT5","created_at":"2026-07-05T07:47:43Z"}],"graph_snapshots":[{"event_id":"sha256:0d42cb4e0c95bcabb45c64c66d62d8d12e19134a9dd446e575a4d1a44634e052","target":"graph","created_at":"2026-07-05T07:47:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.07196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ahmet Iscen, Alireza Fathi, Cordelia Schmid, Mathilde Caron","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T15:52:02Z","title":"Retrieval-Enhanced Contrastive Vision-Text Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07196","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3e8556a6a9ac04ea52694d3ef21b004f52a1436fc2d558c9253ec2db5e5ee153","target":"record","created_at":"2026-07-05T07:47:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e195f8e9ea611aa152c74ed1f0dcf44c98d551d89192584c018c20a13ad835dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T15:52:02Z","title_canon_sha256":"e5e58c37e4baa09c828b6d04dd285760f8e6fc3043d7771401257ccc7dbfc4f7"},"schema_version":"1.0","source":{"id":"2306.07196","kind":"arxiv","version":2}},"canonical_sha256":"70cb5fb27d80810e53e66744b82342bcf7e93c2812291e41eae1580142059c89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70cb5fb27d80810e53e66744b82342bcf7e93c2812291e41eae1580142059c89","first_computed_at":"2026-07-05T07:47:43.405887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:43.405887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0P8eeRr7XAVswnNIn9BQj1J5aJ7yNNxaPsS88+hpzyihf/AV1nvwIxTxpOO4fzSFTZlgQkapgAqVfl7VSXNDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:43.406433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07196","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e8556a6a9ac04ea52694d3ef21b004f52a1436fc2d558c9253ec2db5e5ee153","sha256:0d42cb4e0c95bcabb45c64c66d62d8d12e19134a9dd446e575a4d1a44634e052"],"state_sha256":"c389ef3f7e95d2f23f8a38abf132493e80d42a61d90a499132780d157e1e3d41"}