{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7RLKJOOIJLZ3264GK2BYJQRJHG","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":"3a8c251d4671df903f3ccc5b0bb531eccb54a07e0e2b0415c2a0adb3e085b695","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T01:13:49Z","title_canon_sha256":"05a465bf4e7f989435c80b608ccb3400502a8ee641d86f2d51c67544f8482b5e"},"schema_version":"1.0","source":{"id":"2606.11546","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11546","created_at":"2026-06-11T01:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11546v1","created_at":"2026-06-11T01:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11546","created_at":"2026-06-11T01:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"7RLKJOOIJLZ3","created_at":"2026-06-11T01:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"7RLKJOOIJLZ3264G","created_at":"2026-06-11T01:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"7RLKJOOI","created_at":"2026-06-11T01:09:55Z"}],"graph_snapshots":[{"event_id":"sha256:a74ef4d0c6d8d285f1e628b1eacda446d8e38c8fb88efd6ead3a40b2a4c5f4ef","target":"graph","created_at":"2026-06-11T01:09:55Z","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/2606.11546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection. However, jointly integrating both textual and visual knowledge into detection architectures remains challenging. In this paper, we propose VL-DINO, an open-vocabulary detector that enhances DINO through more effective exploitation of CLIP's vision-language knowledge. Specifically, a Query-guided Positive Sample Construction (QPSC) module is first developed to construct additional high-quality positive samples, enabling the vanilla DINO framework to better accommodate mixed training across he","authors_text":"Hao Zhang, Linqi Song, Qinran Lin, Yong Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T01:13:49Z","title":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11546","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":"sha256:3b3b2db671e0433f03b321c90d238c5669f3110e99cf75a2570db50636ed34b5","target":"record","created_at":"2026-06-11T01:09:55Z","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":"3a8c251d4671df903f3ccc5b0bb531eccb54a07e0e2b0415c2a0adb3e085b695","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T01:13:49Z","title_canon_sha256":"05a465bf4e7f989435c80b608ccb3400502a8ee641d86f2d51c67544f8482b5e"},"schema_version":"1.0","source":{"id":"2606.11546","kind":"arxiv","version":1}},"canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","first_computed_at":"2026-06-11T01:09:55.408859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:55.408859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15iS+ui4c04EaBiibiY142nlcAX0+/G/EBDHgTEviNAcEhhtCO0Tl8/cmsbe+k/ZyFdyBqs4uksOLuWP2IeaDw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:55.409655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11546","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b3b2db671e0433f03b321c90d238c5669f3110e99cf75a2570db50636ed34b5","sha256:a74ef4d0c6d8d285f1e628b1eacda446d8e38c8fb88efd6ead3a40b2a4c5f4ef"],"state_sha256":"93ce216abe8b4e538b43f5b18ea47aea8fc5ff0cdcf62fa497444bd1ab804186"}