{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GPD2VMVOWDDZAPLQZT3ZUEADT7","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":"cf1342ef5c20beb8a896f2d443bd485a3aff5c87916bbec8bc4cca3602267fb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T19:12:09Z","title_canon_sha256":"f7fdfcdc7fe8c6a85a38fcbae4c557fdb88d98a6e65cf2b6ac4cafea89e9e297"},"schema_version":"1.0","source":{"id":"2508.12137","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12137","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12137v1","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12137","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_12","alias_value":"GPD2VMVOWDDZ","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_16","alias_value":"GPD2VMVOWDDZAPLQ","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_8","alias_value":"GPD2VMVO","created_at":"2026-07-05T11:55:00Z"}],"graph_snapshots":[{"event_id":"sha256:ff1b90e3e2c54d1d615b70017949363a65a8ef26fba21ae0c72d7a1abb2c7901","target":"graph","created_at":"2026-07-05T11:55:00Z","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/2508.12137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings remain suboptimal for fine-grained open-set visual retrieval, where state-of-the-art results require fine-tuning the vision encoder using annotated domain-specific samples. Naively performing such fine-tuning typically leads to catastrophic forgetting, severely diminishing the model's general-purpose visual and cross-modal capabilities.\n  In this work, we prop","authors_text":"Andr\\'e Araujo, Kaifeng Chen, Nikolaos-Antonios Ypsilantis, Ond\\v{r}ej Chum","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T19:12:09Z","title":"Infusing fine-grained visual knowledge to Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12137","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":"sha256:545c3dc3e350db6d6812d593fd271a97ef0a55e381b9336e355bb6e9c9f1ee32","target":"record","created_at":"2026-07-05T11:55:00Z","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":"cf1342ef5c20beb8a896f2d443bd485a3aff5c87916bbec8bc4cca3602267fb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T19:12:09Z","title_canon_sha256":"f7fdfcdc7fe8c6a85a38fcbae4c557fdb88d98a6e65cf2b6ac4cafea89e9e297"},"schema_version":"1.0","source":{"id":"2508.12137","kind":"arxiv","version":1}},"canonical_sha256":"33c7aab2aeb0c7903d70ccf79a10039fcee00886d6db6ea78af6eae61519ef37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33c7aab2aeb0c7903d70ccf79a10039fcee00886d6db6ea78af6eae61519ef37","first_computed_at":"2026-07-05T11:55:00.721589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:00.721589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KL/GCSsiJz+SEnFj6CdUJksr0AgxyvNcrnyEkNwG7mdTcagH2lU4ykwtz80GqQ/JPehSqF6tXyNQEKR4zFLVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:00.722053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12137","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:545c3dc3e350db6d6812d593fd271a97ef0a55e381b9336e355bb6e9c9f1ee32","sha256:ff1b90e3e2c54d1d615b70017949363a65a8ef26fba21ae0c72d7a1abb2c7901"],"state_sha256":"e76d02ff1d513304fd967ef901a9dffe82e756de6f5cdbd368692803f066ca39"}