{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:43BARLPJCKSOHK7FCAGD6D3MTP","short_pith_number":"pith:43BARLPJ","schema_version":"1.0","canonical_sha256":"e6c208ade912a4e3abe5100c3f0f6c9beda7511de60c7ead8fbb001fcf9a0385","source":{"kind":"arxiv","id":"2606.00782","version":1},"attestation_state":"computed","paper":{"title":"FlowOVD: Learning Generative Latent Flows for Zero-shot Open-vocabulary Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Cavallaro, Changjae Oh, Yao Wei","submitted_at":"2026-05-30T16:01:43Z","abstract_excerpt":"Open-vocabulary object detection (OVD) has achieved remarkable progress through large-scale vision-language pre-training. Existing methods, however, typically formulate OVD as a discriminative prediction problem, where decoder queries are either static or initialized from encoder features, thus limiting their diversity and flexibility. In this paper, we introduce a generative perspective by modeling decoder query generation as a continuous transport process in latent space. We propose FlowOVD, a text-conditioned query generation framework based on rectified flow that progressively transforms t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.00782","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T16:01:43Z","cross_cats_sorted":[],"title_canon_sha256":"3c451f2c3cb3a8c6a6f28c4fa548dab3bf1f31e7e1a849ea1a0695b11633c920","abstract_canon_sha256":"66bcafc0a895c99af318fac529ce13a5f399de6fac1c7e7ef31c4a1d8934c10f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:05.576444Z","signature_b64":"19uGhqT/ySAl4ciJJ+TO+S3oIFvHBpeoyI2bbzy953NXnW66gCuwdnY98eKye4SVe3UO05G0FtInyvpb0o4kDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c208ade912a4e3abe5100c3f0f6c9beda7511de60c7ead8fbb001fcf9a0385","last_reissued_at":"2026-06-02T01:04:05.576054Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:05.576054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowOVD: Learning Generative Latent Flows for Zero-shot Open-vocabulary Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Cavallaro, Changjae Oh, Yao Wei","submitted_at":"2026-05-30T16:01:43Z","abstract_excerpt":"Open-vocabulary object detection (OVD) has achieved remarkable progress through large-scale vision-language pre-training. Existing methods, however, typically formulate OVD as a discriminative prediction problem, where decoder queries are either static or initialized from encoder features, thus limiting their diversity and flexibility. In this paper, we introduce a generative perspective by modeling decoder query generation as a continuous transport process in latent space. We propose FlowOVD, a text-conditioned query generation framework based on rectified flow that progressively transforms t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00782","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/2606.00782/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.00782","created_at":"2026-06-02T01:04:05.576116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00782v1","created_at":"2026-06-02T01:04:05.576116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00782","created_at":"2026-06-02T01:04:05.576116+00:00"},{"alias_kind":"pith_short_12","alias_value":"43BARLPJCKSO","created_at":"2026-06-02T01:04:05.576116+00:00"},{"alias_kind":"pith_short_16","alias_value":"43BARLPJCKSOHK7F","created_at":"2026-06-02T01:04:05.576116+00:00"},{"alias_kind":"pith_short_8","alias_value":"43BARLPJ","created_at":"2026-06-02T01:04:05.576116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP","json":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP.json","graph_json":"https://pith.science/api/pith-number/43BARLPJCKSOHK7FCAGD6D3MTP/graph.json","events_json":"https://pith.science/api/pith-number/43BARLPJCKSOHK7FCAGD6D3MTP/events.json","paper":"https://pith.science/paper/43BARLPJ"},"agent_actions":{"view_html":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP","download_json":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP.json","view_paper":"https://pith.science/paper/43BARLPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00782&json=true","fetch_graph":"https://pith.science/api/pith-number/43BARLPJCKSOHK7FCAGD6D3MTP/graph.json","fetch_events":"https://pith.science/api/pith-number/43BARLPJCKSOHK7FCAGD6D3MTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP/action/storage_attestation","attest_author":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP/action/author_attestation","sign_citation":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP/action/citation_signature","submit_replication":"https://pith.science/pith/43BARLPJCKSOHK7FCAGD6D3MTP/action/replication_record"}},"created_at":"2026-06-02T01:04:05.576116+00:00","updated_at":"2026-06-02T01:04:05.576116+00:00"}