{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FM2WVCIMRTIHCJJZUNEKR6TUCD","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":"d15dcce9727b94646cca9d9e89f2943e7d8b2be34411aff9c6ac6503c1acd3a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T12:28:08Z","title_canon_sha256":"24c61fc22f7d6fc5c7b347f2facd1e439159d1e954d3ebf404735e58ba53ea52"},"schema_version":"1.0","source":{"id":"2508.05323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05323","created_at":"2026-07-05T11:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05323v1","created_at":"2026-07-05T11:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05323","created_at":"2026-07-05T11:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"FM2WVCIMRTIH","created_at":"2026-07-05T11:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"FM2WVCIMRTIHCJJZ","created_at":"2026-07-05T11:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"FM2WVCIM","created_at":"2026-07-05T11:50:10Z"}],"graph_snapshots":[{"event_id":"sha256:3d03590cc6cbcf2c355eb921376bbf70364907d547adb0ec3b0b72830d3acbbe","target":"graph","created_at":"2026-07-05T11:50:10Z","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/2508.05323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in large pre-trained vision language models (VLMs) has reached state-of-the-art performance on several object detection benchmarks and boasts strong zero-shot capabilities, but for optimal performance on specific targets some form of finetuning is still necessary. While the initial VLM weights allow for great few-shot transfer learning, this usually involves the loss of the original natural language querying and zero-shot capabilities. Inspired by the success of Textual Inversion (TI) in personalizing text-to-image diffusion models, we propose a similar formulation for open-voc","authors_text":"Frank Ruis, Gertjan Burghouts, Hugo Kuijf","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T12:28:08Z","title":"Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without Forgetting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05323","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":"sha256:8058f44fd4789158a777020bc7972814ec1a1cef176c72bffc605677dd7a797c","target":"record","created_at":"2026-07-05T11:50:10Z","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":"d15dcce9727b94646cca9d9e89f2943e7d8b2be34411aff9c6ac6503c1acd3a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T12:28:08Z","title_canon_sha256":"24c61fc22f7d6fc5c7b347f2facd1e439159d1e954d3ebf404735e58ba53ea52"},"schema_version":"1.0","source":{"id":"2508.05323","kind":"arxiv","version":1}},"canonical_sha256":"2b356a890c8cd0712539a348a8fa7410e4a914e1ab25750c3b52c7081df03c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b356a890c8cd0712539a348a8fa7410e4a914e1ab25750c3b52c7081df03c2d","first_computed_at":"2026-07-05T11:50:10.772771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:10.772771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bCPg0dvfPSpfb/TvkcNeq5hBFxdV6Tau1gT8OL3fGxaTbhzCih13IJydb+zf+qsEVC1e+IzzP2S1OVK7bm9BAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:10.773284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8058f44fd4789158a777020bc7972814ec1a1cef176c72bffc605677dd7a797c","sha256:3d03590cc6cbcf2c355eb921376bbf70364907d547adb0ec3b0b72830d3acbbe"],"state_sha256":"03a24fec3e62c53f6d9872899660de8af93f10a24ba520db12bdc4e8424ea627"}