{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DD76S5J4M7SEOKJK6ATGV4CG6E","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":"d15108ea616a3b38e60e8cfc0003e679db8b1436054f4e8cd78b6b1eb0bee73a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T16:48:25Z","title_canon_sha256":"2dbf87f5623a53c4ac5be5703d277940242a200266de8e94adf269c2035c2944"},"schema_version":"1.0","source":{"id":"2403.06892","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06892","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06892v2","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06892","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"DD76S5J4M7SE","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"DD76S5J4M7SEOKJK","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"DD76S5J4","created_at":"2026-07-05T09:42:23Z"}],"graph_snapshots":[{"event_id":"sha256:5712416d043b82a0b8c3f832a82b72d673c141232bd6d2c1100beb53955bbc74","target":"graph","created_at":"2026-07-05T09:42:23Z","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/2403.06892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set and open-vocabulary object detection (OVD) tasks through the integration of language modalities. However, their demanding computational requirements have hindered their practical application in real-time object detection (OD) scenarios. In this paper, we scrutinize the limitations of two leading models in the OVDEval benchmark, OmDet and Grounding-DINO, and introduce OmDet-Turbo. This novel transformer-based real-time OVD model features an innovative Efficient Fusion Head (EFH) module designed ","authors_text":"Kyusong Lee, Lu Zhang, Peng Liu, Tiancheng Zhao, Xuan He","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T16:48:25Z","title":"Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06892","kind":"arxiv","version":2},"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:c16dab4f6e93a488b05d73c31c2dcb1bb1fe0bbb08090152009a5b9b29808719","target":"record","created_at":"2026-07-05T09:42:23Z","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":"d15108ea616a3b38e60e8cfc0003e679db8b1436054f4e8cd78b6b1eb0bee73a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T16:48:25Z","title_canon_sha256":"2dbf87f5623a53c4ac5be5703d277940242a200266de8e94adf269c2035c2944"},"schema_version":"1.0","source":{"id":"2403.06892","kind":"arxiv","version":2}},"canonical_sha256":"18ffe9753c67e447292af0266af046f11f6dda348ddfe837d22d2ed0087e67f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18ffe9753c67e447292af0266af046f11f6dda348ddfe837d22d2ed0087e67f3","first_computed_at":"2026-07-05T09:42:23.702410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:23.702410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AlKVNbT7f5UOkaUoNKbF6vqFfJCE/u+p3SpUo8iAYyT44HKVlf8lE0nJ3OvLBJDvDqv4dlbYe2RK3JDJJYOjBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:23.702950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06892","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c16dab4f6e93a488b05d73c31c2dcb1bb1fe0bbb08090152009a5b9b29808719","sha256:5712416d043b82a0b8c3f832a82b72d673c141232bd6d2c1100beb53955bbc74"],"state_sha256":"7ad0282d629140cd0fa9db3d54faad1ce10bdd2436fd1e9bdb420a95082e2ae9"}