{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7RLKJOOIJLZ3264GK2BYJQRJHG","short_pith_number":"pith:7RLKJOOI","canonical_record":{"source":{"id":"2606.11546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T01:13:49Z","cross_cats_sorted":[],"title_canon_sha256":"05a465bf4e7f989435c80b608ccb3400502a8ee641d86f2d51c67544f8482b5e","abstract_canon_sha256":"3a8c251d4671df903f3ccc5b0bb531eccb54a07e0e2b0415c2a0adb3e085b695"},"schema_version":"1.0"},"canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","source":{"kind":"arxiv","id":"2606.11546","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7RLKJOOIJLZ3264GK2BYJQRJHG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.11546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T01:13:49Z","cross_cats_sorted":[],"title_canon_sha256":"05a465bf4e7f989435c80b608ccb3400502a8ee641d86f2d51c67544f8482b5e","abstract_canon_sha256":"3a8c251d4671df903f3ccc5b0bb531eccb54a07e0e2b0415c2a0adb3e085b695"},"schema_version":"1.0"},"canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:55.409655Z","signature_b64":"15iS+ui4c04EaBiibiY142nlcAX0+/G/EBDHgTEviNAcEhhtCO0Tl8/cmsbe+k/ZyFdyBqs4uksOLuWP2IeaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc56a4b9c84af3bd7b86568384c229398ac250da4efed88e94a12f4974eb7863","last_reissued_at":"2026-06-11T01:09:55.408859Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:55.408859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.11546","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQ94+pf+OIBGrycrnJ9aiZ0iFosC1W8UINRItLMWylA2uochLYFLJTw4FNua7pbO7ItmbNQQgzOaCtLoq2xcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T12:55:29.547508Z"},"content_sha256":"3b3b2db671e0433f03b321c90d238c5669f3110e99cf75a2570db50636ed34b5","schema_version":"1.0","event_id":"sha256:3b3b2db671e0433f03b321c90d238c5669f3110e99cf75a2570db50636ed34b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7RLKJOOIJLZ3264GK2BYJQRJHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Linqi Song, Qinran Lin, Yong Li","submitted_at":"2026-06-10T01:13:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11546","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11546/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7S0J5YvgN6MUFen60UMldHXluUKMQtRQd5FMrM/oWumuxor+hcbGEgESHKFnCME0/WWC2AbDDOpW034pK7XmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T12:55:29.547880Z"},"content_sha256":"a74ef4d0c6d8d285f1e628b1eacda446d8e38c8fb88efd6ead3a40b2a4c5f4ef","schema_version":"1.0","event_id":"sha256:a74ef4d0c6d8d285f1e628b1eacda446d8e38c8fb88efd6ead3a40b2a4c5f4ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/bundle.json","state_url":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-03T12:55:29Z","links":{"resolver":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG","bundle":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/bundle.json","state":"https://pith.science/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7RLKJOOIJLZ3264GK2BYJQRJHG/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pf3KcvJimSWVrE0f7+M7iQ31/BK8XNdlaCqoyGepRQJOpn52Nj5TSoSAdkxPLQjWYcPu5ydURT89CH5b/SEZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T12:55:29.549850Z","bundle_sha256":"305289367204aeb32d7a2065b92c380fecf5375761ee57ee538fd1b6da987f0f"}}