{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEMGA3H7I7NRJYUCXUSIUPS7CE","short_pith_number":"pith:YEMGA3H7","schema_version":"1.0","canonical_sha256":"c118606cff47db14e282bd248a3e5f111e4fcf1fde779d8d45d0bf40d39a1d43","source":{"kind":"arxiv","id":"2401.02361","version":2},"attestation_state":"computed","paper":{"title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Huang, Shilin Xu, Xiangtai Li, Xiangyu Zhao, Xinjiang Wang, Yicheng Chen, Yining Li","submitted_at":"2024-01-04T17:00:49Z","abstract_excerpt":"Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Expression Comprehension (REC). Its effectiveness has led to its widespread adoption as a mainstream architecture for various downstream applications. However, despite its significance, the original Grounding-DINO model lacks comprehensive public technical details due to the unavailability of its training code. To bridge this gap, we present MM-Grounding-DINO, an open-source, comprehensive, and user-friendly baseline, w"},"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":"2401.02361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T17:00:49Z","cross_cats_sorted":[],"title_canon_sha256":"e49df36290911a70b9efb163c374e62a151fde0f912d6ca57e5be675f8ade39a","abstract_canon_sha256":"f295ef84210e5bfc44c8e79771ef0e6aeba7bf82cd4ae3e30222493ac93db802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:24.914556Z","signature_b64":"4RUn9raw0/OHvDG9Ag7TvikEBa0XjqrCXi5Q32pWLFHHB8oQ4XZZh25HKeHn8zANZXwXtsPiyKyH5Y3xu0SHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c118606cff47db14e282bd248a3e5f111e4fcf1fde779d8d45d0bf40d39a1d43","last_reissued_at":"2026-07-05T07:30:24.914046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:24.914046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haian Huang, Shilin Xu, Xiangtai Li, Xiangyu Zhao, Xinjiang Wang, Yicheng Chen, Yining Li","submitted_at":"2024-01-04T17:00:49Z","abstract_excerpt":"Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Expression Comprehension (REC). Its effectiveness has led to its widespread adoption as a mainstream architecture for various downstream applications. However, despite its significance, the original Grounding-DINO model lacks comprehensive public technical details due to the unavailability of its training code. To bridge this gap, we present MM-Grounding-DINO, an open-source, comprehensive, and user-friendly baseline, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02361","kind":"arxiv","version":2},"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/2401.02361/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":"2401.02361","created_at":"2026-07-05T07:30:24.914109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02361v2","created_at":"2026-07-05T07:30:24.914109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02361","created_at":"2026-07-05T07:30:24.914109+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEMGA3H7I7NR","created_at":"2026-07-05T07:30:24.914109+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEMGA3H7I7NRJYUC","created_at":"2026-07-05T07:30:24.914109+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEMGA3H7","created_at":"2026-07-05T07:30:24.914109+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08267","citing_title":"UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00338","citing_title":"DroneFINE: Domain-Aware Parameter-Efficient Fine-Tuning of Vision-Language Detectors for Drone Images","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06673","citing_title":"Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2601.19640","citing_title":"Focus on What Really Matters in Low-Altitude Governance: A Management-Centric Multi-Modal Benchmark with Implicitly Coordinated Vision-Language Reasoning Framework","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00503","citing_title":"PET-DINO: Unifying Visual Cues into Grounding DINO with Prompt-Enriched Training","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03841","citing_title":"Training a Student Expert via Semi-Supervised Foundation Model Distillation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10190","citing_title":"DetRefiner: Model-Agnostic Detection Refinement with Feature Fusion Transformer","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11998","citing_title":"The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05393","citing_title":"Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14684","citing_title":"DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03456","citing_title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE","json":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE.json","graph_json":"https://pith.science/api/pith-number/YEMGA3H7I7NRJYUCXUSIUPS7CE/graph.json","events_json":"https://pith.science/api/pith-number/YEMGA3H7I7NRJYUCXUSIUPS7CE/events.json","paper":"https://pith.science/paper/YEMGA3H7"},"agent_actions":{"view_html":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE","download_json":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE.json","view_paper":"https://pith.science/paper/YEMGA3H7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02361&json=true","fetch_graph":"https://pith.science/api/pith-number/YEMGA3H7I7NRJYUCXUSIUPS7CE/graph.json","fetch_events":"https://pith.science/api/pith-number/YEMGA3H7I7NRJYUCXUSIUPS7CE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE/action/storage_attestation","attest_author":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE/action/author_attestation","sign_citation":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE/action/citation_signature","submit_replication":"https://pith.science/pith/YEMGA3H7I7NRJYUCXUSIUPS7CE/action/replication_record"}},"created_at":"2026-07-05T07:30:24.914109+00:00","updated_at":"2026-07-05T07:30:24.914109+00:00"}