{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YQPJVUXCX3YG75YZ7EFR3LXIWT","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":"95841116a673536a8d6773a4de64230a47e9f616c90c265764ee2e6f027d61da","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:56:04Z","title_canon_sha256":"ccad5bce95b500c83ccccba8f1940aa0afb0e151eac56442886e979f6ffac97b"},"schema_version":"1.0","source":{"id":"2412.03561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03561","created_at":"2026-07-05T09:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03561v1","created_at":"2026-07-05T09:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03561","created_at":"2026-07-05T09:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"YQPJVUXCX3YG","created_at":"2026-07-05T09:44:31Z"},{"alias_kind":"pith_short_16","alias_value":"YQPJVUXCX3YG75YZ","created_at":"2026-07-05T09:44:31Z"},{"alias_kind":"pith_short_8","alias_value":"YQPJVUXC","created_at":"2026-07-05T09:44:31Z"}],"graph_snapshots":[{"event_id":"sha256:f474148d72cb3a477aa2374ef5f648ab5c02227ec99100f7b6eee404e77c3efc","target":"graph","created_at":"2026-07-05T09:44:31Z","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/2412.03561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose FLAIR, Fine-grained Language-informed Image Representations, an approach that utilizes long and detailed image descriptions to learn localized image embeddings. By sampling diverse sub-captions that describe fine-grained details about an image, we train our vision-language model to produce not only global embeddings but also text-specific image representations.","authors_text":"Mariana-Iuliana Georgescu, Rui Xiao, Sanghwan Kim, Stephan Alaniz, Zeynep Akata","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:56:04Z","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03561","kind":"arxiv","version":1},"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:cfc196118f298e368d6decc74513f7a8695868872cc5584a961e26e2d96c991d","target":"record","created_at":"2026-07-05T09:44:31Z","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":"95841116a673536a8d6773a4de64230a47e9f616c90c265764ee2e6f027d61da","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:56:04Z","title_canon_sha256":"ccad5bce95b500c83ccccba8f1940aa0afb0e151eac56442886e979f6ffac97b"},"schema_version":"1.0","source":{"id":"2412.03561","kind":"arxiv","version":1}},"canonical_sha256":"c41e9ad2e2bef06ff719f90b1daee8b4c3d6d4495827a256668e959e9ee43239","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c41e9ad2e2bef06ff719f90b1daee8b4c3d6d4495827a256668e959e9ee43239","first_computed_at":"2026-07-05T09:44:31.317778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:31.317778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9M3nhAbF3X6m778puJ+gXfmt+eHO+UhmgXAKKIdeO/EofkfHisefeA6tnoqaT096lxC6vcQG86drVLyZ/p2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:31.318357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfc196118f298e368d6decc74513f7a8695868872cc5584a961e26e2d96c991d","sha256:f474148d72cb3a477aa2374ef5f648ab5c02227ec99100f7b6eee404e77c3efc"],"state_sha256":"1b2a9aa68daab9b9dc68955342f02bab639bd36764a07aaa3370796d63776639"}