{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J22SISAYUVVQ4WWVDM2JDZX2HY","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":"3211a3ae14945f7799a24ef1ce4faaf54b36f67ab54eb306e7c372353e000e28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-31T01:15:29Z","title_canon_sha256":"9dda500f2d08fb749974c7bcc99cdeef88b6c87ca698ee45697b65550188eb1d"},"schema_version":"1.0","source":{"id":"2506.00333","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00333","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00333v1","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00333","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"J22SISAYUVVQ","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"J22SISAYUVVQ4WWV","created_at":"2026-07-05T11:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"J22SISAY","created_at":"2026-07-05T11:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:7da6dfe22aa96777f2825a6254537795b687f6334e0f672e9debce7568668d64","target":"graph","created_at":"2026-07-05T11:13:32Z","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/2506.00333/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary object detection models allow users to freely specify a class vocabulary in natural language at test time, guiding the detection of desired objects. However, vocabularies can be overly broad or even mis-specified, hampering the overall performance of the detector. In this work, we propose a plug-and-play Vocabulary Adapter (VocAda) to refine the user-defined vocabulary, automatically tailoring it to categories that are relevant for a given image. VocAda does not require any training, it operates at inference time in three steps: i) it uses an image captionner to describe visibl","authors_text":"Elisa Ricci, Gabriela Csurka, Massimiliano Mancini, Mingxuan Liu, Riccardo Volpi, Tyler L. Hayes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-31T01:15:29Z","title":"Test-time Vocabulary Adaptation for Language-driven Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00333","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":"sha256:457a9c8d15581d1e7ceec6fb07e6272a75ab01f41e7017fb589922cd963fb685","target":"record","created_at":"2026-07-05T11:13:32Z","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":"3211a3ae14945f7799a24ef1ce4faaf54b36f67ab54eb306e7c372353e000e28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-31T01:15:29Z","title_canon_sha256":"9dda500f2d08fb749974c7bcc99cdeef88b6c87ca698ee45697b65550188eb1d"},"schema_version":"1.0","source":{"id":"2506.00333","kind":"arxiv","version":1}},"canonical_sha256":"4eb5244818a56b0e5ad51b3491e6fa3e32f7716f145dd3f5c4348a7ed6e0e3e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb5244818a56b0e5ad51b3491e6fa3e32f7716f145dd3f5c4348a7ed6e0e3e8","first_computed_at":"2026-07-05T11:13:32.679570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:32.679570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uf93nAwDzOMQqDhhWeJsKDAnPKk5A0SIHRdOAz8wKm5Ip/tjNSd9ktTwOKRIXO1IB7gUuOz3f/suLZWoCYjrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:32.680013Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00333","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:457a9c8d15581d1e7ceec6fb07e6272a75ab01f41e7017fb589922cd963fb685","sha256:7da6dfe22aa96777f2825a6254537795b687f6334e0f672e9debce7568668d64"],"state_sha256":"f36cd1a42d6cda0901be65950d812f2c0aefc35544ea9a1b870082cf2dbb6cfb"}