{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:37DWWUSAZDJJ35TRR7QS275KXU","short_pith_number":"pith:37DWWUSA","canonical_record":{"source":{"id":"2304.04514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T11:08:15Z","cross_cats_sorted":[],"title_canon_sha256":"15a7506c5550ff4537d183c6adb9174eec330c53822ad02d855ed12ee4ebcce5","abstract_canon_sha256":"4453acfd7ff99a35763c45ab5e040b0f02d847d06009a0944156bbf51f0b42ca"},"schema_version":"1.0"},"canonical_sha256":"dfc76b5240c8d29df6718fe12d7faabd3f44715b049d06663ed221a2a5b8106c","source":{"kind":"arxiv","id":"2304.04514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04514","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04514v1","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04514","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"37DWWUSAZDJJ","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"37DWWUSAZDJJ35TR","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"37DWWUSA","created_at":"2026-07-05T05:59:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:37DWWUSAZDJJ35TRR7QS275KXU","target":"record","payload":{"canonical_record":{"source":{"id":"2304.04514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T11:08:15Z","cross_cats_sorted":[],"title_canon_sha256":"15a7506c5550ff4537d183c6adb9174eec330c53822ad02d855ed12ee4ebcce5","abstract_canon_sha256":"4453acfd7ff99a35763c45ab5e040b0f02d847d06009a0944156bbf51f0b42ca"},"schema_version":"1.0"},"canonical_sha256":"dfc76b5240c8d29df6718fe12d7faabd3f44715b049d06663ed221a2a5b8106c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:26.984942Z","signature_b64":"xTKQHSviUflM3N4BZh5+DTTU5VPWwGE4cDmiTtzxOyD7mdEydJL1OYPMu+LwYR39tDvehPEWN8v3BYF88OhMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfc76b5240c8d29df6718fe12d7faabd3f44715b049d06663ed221a2a5b8106c","last_reissued_at":"2026-07-05T05:59:26.984496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:26.984496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.04514","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:59:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwN2Lb2760s1VH5xseGFqm4hqAtL/bHrh1dN6GcMTpBFisD+HjISpyEF2qHjpTxGs7t0DJDs7x7dDbY+DNn9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:26:59.629717Z"},"content_sha256":"ef3883db4552f408e69c2024b1e37e3e94230a58fde236018df023de93de7625","schema_version":"1.0","event_id":"sha256:ef3883db4552f408e69c2024b1e37e3e94230a58fde236018df023de93de7625"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:37DWWUSAZDJJ35TRR7QS275KXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hang Xu, Jianhua Han, Lewei Yao, Wei Zhang, Xiaodan Liang, Zhenguo Li","submitted_at":"2023-04-10T11:08:15Z","abstract_excerpt":"This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD). Unlike previous OVD frameworks that typically rely on a pre-trained vision-language model (e.g., CLIP) or exploit image-text pairs via a pseudo labeling process, DetCLIPv2 directly learns the fine-grained word-region alignment from massive image-text pairs in an end-to-end manner. To accomplish this, we employ a maximum word-region similarity between region proposals and textual words to guide the contrastive objective. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04514","kind":"arxiv","version":1},"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/2304.04514/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:59:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dC3AOIKrnjE85U1YK2xTfO/n/bk+Qo1C29zXPCphS9EIdVP1Vme31HQo720WoThkcDt0rUIizzObl4hcbRxuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:26:59.630353Z"},"content_sha256":"663a5f25540455f7ce8dd445ea0461571f7cf6b0ca0b9bf1ed1108734eba80e8","schema_version":"1.0","event_id":"sha256:663a5f25540455f7ce8dd445ea0461571f7cf6b0ca0b9bf1ed1108734eba80e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37DWWUSAZDJJ35TRR7QS275KXU/bundle.json","state_url":"https://pith.science/pith/37DWWUSAZDJJ35TRR7QS275KXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37DWWUSAZDJJ35TRR7QS275KXU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T05:26:59Z","links":{"resolver":"https://pith.science/pith/37DWWUSAZDJJ35TRR7QS275KXU","bundle":"https://pith.science/pith/37DWWUSAZDJJ35TRR7QS275KXU/bundle.json","state":"https://pith.science/pith/37DWWUSAZDJJ35TRR7QS275KXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37DWWUSAZDJJ35TRR7QS275KXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:37DWWUSAZDJJ35TRR7QS275KXU","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":"4453acfd7ff99a35763c45ab5e040b0f02d847d06009a0944156bbf51f0b42ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T11:08:15Z","title_canon_sha256":"15a7506c5550ff4537d183c6adb9174eec330c53822ad02d855ed12ee4ebcce5"},"schema_version":"1.0","source":{"id":"2304.04514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04514","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04514v1","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04514","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"37DWWUSAZDJJ","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"37DWWUSAZDJJ35TR","created_at":"2026-07-05T05:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"37DWWUSA","created_at":"2026-07-05T05:59:26Z"}],"graph_snapshots":[{"event_id":"sha256:663a5f25540455f7ce8dd445ea0461571f7cf6b0ca0b9bf1ed1108734eba80e8","target":"graph","created_at":"2026-07-05T05:59:26Z","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/2304.04514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD). Unlike previous OVD frameworks that typically rely on a pre-trained vision-language model (e.g., CLIP) or exploit image-text pairs via a pseudo labeling process, DetCLIPv2 directly learns the fine-grained word-region alignment from massive image-text pairs in an end-to-end manner. To accomplish this, we employ a maximum word-region similarity between region proposals and textual words to guide the contrastive objective. To","authors_text":"Dan Xu, Hang Xu, Jianhua Han, Lewei Yao, Wei Zhang, Xiaodan Liang, Zhenguo Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T11:08:15Z","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04514","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:ef3883db4552f408e69c2024b1e37e3e94230a58fde236018df023de93de7625","target":"record","created_at":"2026-07-05T05:59:26Z","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":"4453acfd7ff99a35763c45ab5e040b0f02d847d06009a0944156bbf51f0b42ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T11:08:15Z","title_canon_sha256":"15a7506c5550ff4537d183c6adb9174eec330c53822ad02d855ed12ee4ebcce5"},"schema_version":"1.0","source":{"id":"2304.04514","kind":"arxiv","version":1}},"canonical_sha256":"dfc76b5240c8d29df6718fe12d7faabd3f44715b049d06663ed221a2a5b8106c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfc76b5240c8d29df6718fe12d7faabd3f44715b049d06663ed221a2a5b8106c","first_computed_at":"2026-07-05T05:59:26.984496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:26.984496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xTKQHSviUflM3N4BZh5+DTTU5VPWwGE4cDmiTtzxOyD7mdEydJL1OYPMu+LwYR39tDvehPEWN8v3BYF88OhMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:26.984942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef3883db4552f408e69c2024b1e37e3e94230a58fde236018df023de93de7625","sha256:663a5f25540455f7ce8dd445ea0461571f7cf6b0ca0b9bf1ed1108734eba80e8"],"state_sha256":"591866db355da7835e64c1778e5e42d40f2f228e64e0c02c73df3bd1967a64f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3bvdTe8cQSIbjnfnSlOHc2ULHok4GFP1L/3MrdCxxKI42t1A28ze/WI2o4BAjDpg7dDBuQ11DbW24TmTnyLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:26:59.636012Z","bundle_sha256":"c295d1c6fc574a73c64593b4cc2d3ae82ec10a416162589156737356561fb53f"}}