{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LU2QXEEYIJBZQGCELNVQ727JEO","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":"95905343ec763b19ae5de69979da21478bccb6cd8efaf1bf89b58423c1dce163","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-10T14:25:14Z","title_canon_sha256":"a94724a2510423dc4ed8a0f81477239a265743df0d089510d09b02d29f922e3b"},"schema_version":"1.0","source":{"id":"2209.05946","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.05946","created_at":"2026-07-05T07:48:43Z"},{"alias_kind":"arxiv_version","alias_value":"2209.05946v2","created_at":"2026-07-05T07:48:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05946","created_at":"2026-07-05T07:48:43Z"},{"alias_kind":"pith_short_12","alias_value":"LU2QXEEYIJBZ","created_at":"2026-07-05T07:48:43Z"},{"alias_kind":"pith_short_16","alias_value":"LU2QXEEYIJBZQGCE","created_at":"2026-07-05T07:48:43Z"},{"alias_kind":"pith_short_8","alias_value":"LU2QXEEY","created_at":"2026-07-05T07:48:43Z"}],"graph_snapshots":[{"event_id":"sha256:adc7904961ac30e2a4f22f0985e30fb743105ebfc0e2a2b5f885955600c883b5","target":"graph","created_at":"2026-07-05T07:48:43Z","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/2209.05946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a \"visual vocabulary\" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-","authors_text":"Kyusong Lee, Peng Liu, Tiancheng Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-10T14:25:14Z","title":"OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05946","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":"sha256:8d73fc2ee5db7f591b83b2944cc15d7f5912dcd3b9b84c2cdac2cfc57f374261","target":"record","created_at":"2026-07-05T07:48:43Z","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":"95905343ec763b19ae5de69979da21478bccb6cd8efaf1bf89b58423c1dce163","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-10T14:25:14Z","title_canon_sha256":"a94724a2510423dc4ed8a0f81477239a265743df0d089510d09b02d29f922e3b"},"schema_version":"1.0","source":{"id":"2209.05946","kind":"arxiv","version":2}},"canonical_sha256":"5d350b909842439818445b6b0febe923b53b036a0890b720d96c59fe4d992483","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d350b909842439818445b6b0febe923b53b036a0890b720d96c59fe4d992483","first_computed_at":"2026-07-05T07:48:43.786890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:43.786890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUwxiXXkP1YTnHN6lPNAZ1ERPTRDAVU5/GG+MA3Nm1cD3X+gNmr+89ZgFR1MBvqf3+zyymUATlJ0gcbH5w6zDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:43.787304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.05946","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d73fc2ee5db7f591b83b2944cc15d7f5912dcd3b9b84c2cdac2cfc57f374261","sha256:adc7904961ac30e2a4f22f0985e30fb743105ebfc0e2a2b5f885955600c883b5"],"state_sha256":"7c9cd2a0a7486e60b3dfa164d9df0938e3db6f754381a8b91f496cc3cf3879cc"}