{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEMGA3H7I7NRJYUCXUSIUPS7CE","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":"f295ef84210e5bfc44c8e79771ef0e6aeba7bf82cd4ae3e30222493ac93db802","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T17:00:49Z","title_canon_sha256":"e49df36290911a70b9efb163c374e62a151fde0f912d6ca57e5be675f8ade39a"},"schema_version":"1.0","source":{"id":"2401.02361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02361","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02361v2","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02361","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"pith_short_12","alias_value":"YEMGA3H7I7NR","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"pith_short_16","alias_value":"YEMGA3H7I7NRJYUC","created_at":"2026-07-05T07:30:24Z"},{"alias_kind":"pith_short_8","alias_value":"YEMGA3H7","created_at":"2026-07-05T07:30:24Z"}],"graph_snapshots":[{"event_id":"sha256:e3b53ca181c827a36ba38cff99e24f94f95b3a7c5032ecff578ae7be8f99b3cb","target":"graph","created_at":"2026-07-05T07:30:24Z","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/2401.02361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haian Huang, Shilin Xu, Xiangtai Li, Xiangyu Zhao, Xinjiang Wang, Yicheng Chen, Yining Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T17:00:49Z","title":"An Open and Comprehensive Pipeline for Unified Object Grounding and Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02361","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":"sha256:06ab0cde61703901af6ab442dd7ffcca63c438312741654e0c8ca1029df92b29","target":"record","created_at":"2026-07-05T07:30:24Z","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":"f295ef84210e5bfc44c8e79771ef0e6aeba7bf82cd4ae3e30222493ac93db802","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T17:00:49Z","title_canon_sha256":"e49df36290911a70b9efb163c374e62a151fde0f912d6ca57e5be675f8ade39a"},"schema_version":"1.0","source":{"id":"2401.02361","kind":"arxiv","version":2}},"canonical_sha256":"c118606cff47db14e282bd248a3e5f111e4fcf1fde779d8d45d0bf40d39a1d43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c118606cff47db14e282bd248a3e5f111e4fcf1fde779d8d45d0bf40d39a1d43","first_computed_at":"2026-07-05T07:30:24.914046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:24.914046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4RUn9raw0/OHvDG9Ag7TvikEBa0XjqrCXi5Q32pWLFHHB8oQ4XZZh25HKeHn8zANZXwXtsPiyKyH5Y3xu0SHAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:24.914556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06ab0cde61703901af6ab442dd7ffcca63c438312741654e0c8ca1029df92b29","sha256:e3b53ca181c827a36ba38cff99e24f94f95b3a7c5032ecff578ae7be8f99b3cb"],"state_sha256":"028228ee297c6fc3464ec2a87944c94002fca70e71217244017c283174a478b4"}