{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PRH3LIQUNQ2CDR7VDOKNJWIJ2V","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":"365c777b83f30301c5da6834d99b6c9e44dde218384d06ab13a3d1da385026a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T08:27:31Z","title_canon_sha256":"b3bca5e15f8428b9b0eff18e2d7a378b5826cc2a186e3e7c371a7eacfa4137b2"},"schema_version":"1.0","source":{"id":"2501.18954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18954","created_at":"2026-07-05T10:07:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18954v1","created_at":"2026-07-05T10:07:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18954","created_at":"2026-07-05T10:07:54Z"},{"alias_kind":"pith_short_12","alias_value":"PRH3LIQUNQ2C","created_at":"2026-07-05T10:07:54Z"},{"alias_kind":"pith_short_16","alias_value":"PRH3LIQUNQ2CDR7V","created_at":"2026-07-05T10:07:54Z"},{"alias_kind":"pith_short_8","alias_value":"PRH3LIQU","created_at":"2026-07-05T10:07:54Z"}],"graph_snapshots":[{"event_id":"sha256:b2aa99052158c164a30fcc76dc4e618a9f76560f0573c78ba2f69611773a3a3a","target":"graph","created_at":"2026-07-05T10:07:54Z","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/2501.18954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption gener","authors_text":"Jingke Meng, Junkai Yan, Qijie Mo, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T08:27:31Z","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18954","kind":"arxiv","version":1},"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:afc333bb70a05fa0eb3961a41038bc93445da8bfa9136012bd70197bef59fdca","target":"record","created_at":"2026-07-05T10:07:54Z","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":"365c777b83f30301c5da6834d99b6c9e44dde218384d06ab13a3d1da385026a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T08:27:31Z","title_canon_sha256":"b3bca5e15f8428b9b0eff18e2d7a378b5826cc2a186e3e7c371a7eacfa4137b2"},"schema_version":"1.0","source":{"id":"2501.18954","kind":"arxiv","version":1}},"canonical_sha256":"7c4fb5a2146c3421c7f51b94d4d909d55e299146a5e099215e9bfcf21c04e32b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c4fb5a2146c3421c7f51b94d4d909d55e299146a5e099215e9bfcf21c04e32b","first_computed_at":"2026-07-05T10:07:54.038721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:54.038721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UjPLaHA3Q9TheeNFQ+CW38TcKaMWhSJXtizjYCRJzT8SqxTou1DWS54ccTBvTw5dmKUccQg4oqU5of4grhHKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:54.039198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afc333bb70a05fa0eb3961a41038bc93445da8bfa9136012bd70197bef59fdca","sha256:b2aa99052158c164a30fcc76dc4e618a9f76560f0573c78ba2f69611773a3a3a"],"state_sha256":"69169610b2b00c60f7525f48a36f3fc15068dbe8198a3e0b6e8d201da83a1998"}