{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XYL5LWMRRK3JDLOUGE5MA4QX2Y","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":"bb7f3b9bb741c42a335666a600e71196c457b2ecedefb2101a4ce08562b2d71f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T21:56:37Z","title_canon_sha256":"0100f80b672efe89c37bc03c1b47660a329e602e51be8e5469af14b6fafd83e7"},"schema_version":"1.0","source":{"id":"2310.00161","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00161","created_at":"2026-07-05T08:45:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00161v2","created_at":"2026-07-05T08:45:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00161","created_at":"2026-07-05T08:45:46Z"},{"alias_kind":"pith_short_12","alias_value":"XYL5LWMRRK3J","created_at":"2026-07-05T08:45:46Z"},{"alias_kind":"pith_short_16","alias_value":"XYL5LWMRRK3JDLOU","created_at":"2026-07-05T08:45:46Z"},{"alias_kind":"pith_short_8","alias_value":"XYL5LWMR","created_at":"2026-07-05T08:45:46Z"}],"graph_snapshots":[{"event_id":"sha256:1fe160a57509ee059ad3068862efacc7cd54e99d9eb8b941fad9602701bf7b60","target":"graph","created_at":"2026-07-05T08:45:46Z","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/2310.00161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new open-vocabulary detection approach based on region-centric image-language pretraining to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we incorporate the detector architecture on top of the classification backbone, which better serves the region-level recognition needs of detection by enabling the detector heads to learn from large-scale image-text pairs. Using only standard contrastive loss and no pseudo-labeling, our approach is a simple yet effective extension of the contrastive learning method to learn emerge","authors_text":"Anelia Angelova, Dahun Kim, Weicheng Kuo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T21:56:37Z","title":"Region-centric Image-Language Pretraining for Open-Vocabulary Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00161","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:f2b862fb5b31d75e240222d563dbe91d6446467c2dd4c44ca5b5d0b91cda39b0","target":"record","created_at":"2026-07-05T08:45:46Z","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":"bb7f3b9bb741c42a335666a600e71196c457b2ecedefb2101a4ce08562b2d71f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T21:56:37Z","title_canon_sha256":"0100f80b672efe89c37bc03c1b47660a329e602e51be8e5469af14b6fafd83e7"},"schema_version":"1.0","source":{"id":"2310.00161","kind":"arxiv","version":2}},"canonical_sha256":"be17d5d9918ab691add4313ac07217d6323a2c7bc8e096b7146419423fa4155e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be17d5d9918ab691add4313ac07217d6323a2c7bc8e096b7146419423fa4155e","first_computed_at":"2026-07-05T08:45:46.732265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:46.732265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3TG9/jaG3Q22tNyPqCMbGDLOJW2MUr6PJZS8U6uAWHa+Lwl85P0HBPbUXcal2ufEjrqireX8j38RGPjRb6yGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:46.732782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00161","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2b862fb5b31d75e240222d563dbe91d6446467c2dd4c44ca5b5d0b91cda39b0","sha256:1fe160a57509ee059ad3068862efacc7cd54e99d9eb8b941fad9602701bf7b60"],"state_sha256":"2ac49655833d3ced1d85d5891aea202dc5038ce1b6411f00164a6de3f01ce992"}