{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IJRAUDS6BL2KS7OBMZCVRUHY2D","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":"aaeff7504c1cd32939fff8fce9e8cef622b295370de8474901b53d75601d1f0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T15:05:34Z","title_canon_sha256":"c7535fdcac8cb747aaf4c00483816c60aaf2e40a8afcbc71ec74edd625fd34a0"},"schema_version":"1.0","source":{"id":"2307.06795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06795","created_at":"2026-07-05T06:30:37Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06795v1","created_at":"2026-07-05T06:30:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06795","created_at":"2026-07-05T06:30:37Z"},{"alias_kind":"pith_short_12","alias_value":"IJRAUDS6BL2K","created_at":"2026-07-05T06:30:37Z"},{"alias_kind":"pith_short_16","alias_value":"IJRAUDS6BL2KS7OB","created_at":"2026-07-05T06:30:37Z"},{"alias_kind":"pith_short_8","alias_value":"IJRAUDS6","created_at":"2026-07-05T06:30:37Z"}],"graph_snapshots":[{"event_id":"sha256:3001d13f9dcf46b44311c8ff729a6fa4cfbbe01dca442110d2a92fa493755dbe","target":"graph","created_at":"2026-07-05T06:30:37Z","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/2307.06795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language foundation models such as CLIP have shown impressive zero-shot performance on many tasks and datasets, especially thanks to their free-text inputs. However, they struggle to handle some downstream tasks, such as fine-grained attribute detection and localization. In this paper, we propose a multitask fine-tuning strategy based on a positive/negative prompt formulation to further leverage the capacities of the vision-language foundation models. Using the CLIP architecture as baseline, we show strong improvements on bird fine-grained attribute detection and localization tasks, whi","authors_text":"Cl\\'ement Rambour, Denis Coquenet, Emanuele Dalsasso, Nicolas Thome","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T15:05:34Z","title":"Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06795","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":"sha256:10318818d1590481713352a8c7a28667a7c8797fafd3f93c9ae0a164325d2c14","target":"record","created_at":"2026-07-05T06:30:37Z","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":"aaeff7504c1cd32939fff8fce9e8cef622b295370de8474901b53d75601d1f0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-13T15:05:34Z","title_canon_sha256":"c7535fdcac8cb747aaf4c00483816c60aaf2e40a8afcbc71ec74edd625fd34a0"},"schema_version":"1.0","source":{"id":"2307.06795","kind":"arxiv","version":1}},"canonical_sha256":"42620a0e5e0af4a97dc1664558d0f8d0d746ca2913ac37e932675f86423de5cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42620a0e5e0af4a97dc1664558d0f8d0d746ca2913ac37e932675f86423de5cc","first_computed_at":"2026-07-05T06:30:37.725886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:37.725886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z2TzhYcSLbFe14QA2U3unfwTAYHUxXdyQVrZfzyQxeIv0HnQlAh29l1gFps0JBUGOYytHCtzqD+PEhB+x2QpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:37.726325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10318818d1590481713352a8c7a28667a7c8797fafd3f93c9ae0a164325d2c14","sha256:3001d13f9dcf46b44311c8ff729a6fa4cfbbe01dca442110d2a92fa493755dbe"],"state_sha256":"55e473fc86bf995988d4cc6d27acfaa13ce92ab0c3a9acdd39f8fc3315056dde"}